{"id": "arxiv:0", "title": "Learning from compressed observations", "text": "The problem of statistical learning is to construct a predictor of a random variable $Y$ as a function of a related random variable $X$ on the basis of an i.i.d. training sample from the joint distribution of $(X,Y)$. Allowable predictors are drawn from some specified class, and the goal is to approach asymptotically the performance (expected loss) of the best predictor in the class. We consider the setting in which one has perfect observation of the $X$-part of the sample, while the $Y$-part has to be communicated at some finite bit rate. The encoding of the $Y$-values is allowed to depend on the $X$-values. Under suitable regularity conditions on the admissible predictors, the underlying family of probability distributions and the loss function, we give an information-theoretic characterization of achievable predictor performance in terms of conditional distortion-rate functions. The ideas are illustrated on the example of nonparametric regression in Gaussian noise.", "source": "arxiv/ml"}
{"id": "arxiv:1", "title": "Sensor Networks with Random Links: Topology Design for Distributed Consensus", "text": "In a sensor network, in practice, the communication among sensors is subject to:(1) errors or failures at random times; (3) costs; and(2) constraints since sensors and networks operate under scarce resources, such as power, data rate, or communication. The signal-to-noise ratio (SNR) is usually a main factor in determining the probability of error (or of communication failure) in a link. These probabilities are then a proxy for the SNR under which the links operate. The paper studies the problem of designing the topology, i.e., assigning the probabilities of reliable communication among sensors (or of link failures) to maximize the rate of convergence of average consensus, when the link communication costs are taken into account, and there is an overall communication budget constraint. To consider this problem, we address a number of preliminary issues: (1) model the network as a random topology; (2) establish necessary and sufficient conditions for mean square sense (mss) and almost sure (a.s.) convergence of average consensus when network links fail; and, in particular, (3) show that a necessary and sufficient condition for both mss and a.s. convergence is for the algebraic connectivity of the mean graph describing the network topology to be strictly positive. With these results, we formulate topology design, subject to random link failures and to a communication cost constraint, as a constrained convex optimization problem to which we apply semidefinite programming techniques. We show by an extensive numerical study that the optimal design improves significantly the convergence speed of the consensus algorithm and can achieve the asymptotic performance of a non-random network at a fraction of the communication cost.", "source": "arxiv/ml"}
{"id": "arxiv:2", "title": "The on-line shortest path problem under partial monitoring", "text": "The on-line shortest path problem is considered under various models of partial monitoring. Given a weighted directed acyclic graph whose edge weights can change in an arbitrary (adversarial) way, a decision maker has to choose in each round of a game a path between two distinguished vertices such that the loss of the chosen path (defined as the sum of the weights of its composing edges) be as small as possible. In a setting generalizing the multi-armed bandit problem, after choosing a path, the decision maker learns only the weights of those edges that belong to the chosen path. For this problem, an algorithm is given whose average cumulative loss in n rounds exceeds that of the best path, matched off-line to the entire sequence of the edge weights, by a quantity that is proportional to 1/\\sqrt{n} and depends only polynomially on the number of edges of the graph. The algorithm can be implemented with linear complexity in the number of rounds n and in the number of edges. An extension to the so-called label efficient setting is also given, in which the decision maker is informed about the weights of the edges corresponding to the chosen path at a total of m << n time instances. Another extension is shown where the decision maker competes against a time-varying path, a generalization of the problem of tracking the best expert. A version of the multi-armed bandit setting for shortest path is also discussed where the decision maker learns only the total weight of the chosen path but not the weights of the individual edges on the path. Applications to routing in packet switched networks along with simulation results are also presented.", "source": "arxiv/ml"}
{"id": "arxiv:3", "title": "A neural network approach to ordinal regression", "text": "Ordinal regression is an important type of learning, which has properties of both classification and regression. Here we describe a simple and effective approach to adapt a traditional neural network to learn ordinal categories. Our approach is a generalization of the perceptron method for ordinal regression. On several benchmark datasets, our method (NNRank) outperforms a neural network classification method. Compared with the ordinal regression methods using Gaussian processes and support vector machines, NNRank achieves comparable performance. Moreover, NNRank has the advantages of traditional neural networks: learning in both online and batch modes, handling very large training datasets, and making rapid predictions. These features make NNRank a useful and complementary tool for large-scale data processing tasks such as information retrieval, web page ranking, collaborative filtering, and protein ranking in Bioinformatics.", "source": "arxiv/ml"}
{"id": "arxiv:4", "title": "Parametric Learning and Monte Carlo Optimization", "text": "This paper uncovers and explores the close relationship between Monte Carlo Optimization of a parametrized integral (MCO), Parametric machine-Learning (PL), and `blackbox' or `oracle'-based optimization (BO). We make four contributions. First, we prove that MCO is mathematically identical to a broad class of PL problems. This identity potentially provides a new application domain for all broadly applicable PL techniques: MCO. Second, we introduce immediate sampling, a new version of the Probability Collectives (PC) algorithm for blackbox optimization. Immediate sampling transforms the original BO problem into an MCO problem. Accordingly, by combining these first two contributions, we can apply all PL techniques to BO. In our third contribution we validate this way of improving BO by demonstrating that cross-validation and bagging improve immediate sampling. Finally, conventional MC and MCO procedures ignore the relationship between the sample point locations and the associated values of the integrand; only the values of the integrand at those locations are considered. We demonstrate that one can exploit the sample location information using PL techniques, for example by forming a fit of the sample locations to the associated values of the integrand. This provides an additional way to apply PL techniques to improve MCO.", "source": "arxiv/ml"}
{"id": "arxiv:5", "title": "Preconditioned Temporal Difference Learning", "text": "This paper has been withdrawn by the author. This draft is withdrawn for its poor quality in english, unfortunately produced by the author when he was just starting his science route. Look at the ICML version instead: http://icml2008.cs.helsinki.fi/papers/111.pdf", "source": "arxiv/ml"}
{"id": "arxiv:6", "title": "A Note on the Inapproximability of Correlation Clustering", "text": "We consider inapproximability of the correlation clustering problem defined as follows: Given a graph $G = (V,E)$ where each edge is labeled either \"+\" (similar) or \"-\" (dissimilar), correlation clustering seeks to partition the vertices into clusters so that the number of pairs correctly (resp. incorrectly) classified with respect to the labels is maximized (resp. minimized). The two complementary problems are called MaxAgree and MinDisagree, respectively, and have been studied on complete graphs, where every edge is labeled, and general graphs, where some edge might not have been labeled. Natural edge-weighted versions of both problems have been studied as well. Let S-MaxAgree denote the weighted problem where all weights are taken from set S, we show that S-MaxAgree with weights bounded by $O(|V|^{1/2-\\delta})$ essentially belongs to the same hardness class in the following sense: if there is a polynomial time algorithm that approximates S-MaxAgree within a factor of $\\lambda = O(\\log{|V|})$ with high probability, then for any choice of S', S'-MaxAgree can be approximated in polynomial time within a factor of $(\\lambda + \\epsilon)$, where $\\epsilon > 0$ can be arbitrarily small, with high probability. A similar statement also holds for $S-MinDisagree. This result implies it is hard (assuming $NP \\neq RP$) to approximate unweighted MaxAgree within a factor of $80/79-\\epsilon$, improving upon a previous known factor of $116/115-\\epsilon$ by Charikar et. al. \\cite{Chari05}.", "source": "arxiv/ml"}
{"id": "arxiv:7", "title": "Joint universal lossy coding and identification of stationary mixing sources", "text": "The problem of joint universal source coding and modeling, treated in the context of lossless codes by Rissanen, was recently generalized to fixed-rate lossy coding of finitely parametrized continuous-alphabet i.i.d. sources. We extend these results to variable-rate lossy block coding of stationary ergodic sources and show that, for bounded metric distortion measures, any finitely parametrized family of stationary sources satisfying suitable mixing, smoothness and Vapnik-Chervonenkis learnability conditions admits universal schemes for joint lossy source coding and identification. We also give several explicit examples of parametric sources satisfying the regularity conditions.", "source": "arxiv/ml"}
{"id": "arxiv:8", "title": "Supervised Feature Selection via Dependence Estimation", "text": "We introduce a framework for filtering features that employs the Hilbert-Schmidt Independence Criterion (HSIC) as a measure of dependence between the features and the labels. The key idea is that good features should maximise such dependence. Feature selection for various supervised learning problems (including classification and regression) is unified under this framework, and the solutions can be approximated using a backward-elimination algorithm. We demonstrate the usefulness of our method on both artificial and real world datasets.", "source": "arxiv/ml"}
{"id": "arxiv:9", "title": "Equivalence of LP Relaxation and Max-Product for Weighted Matching in General Graphs", "text": "Max-product belief propagation is a local, iterative algorithm to find the mode/MAP estimate of a probability distribution. While it has been successfully employed in a wide variety of applications, there are relatively few theoretical guarantees of convergence and correctness for general loopy graphs that may have many short cycles. Of these, even fewer provide exact ``necessary and sufficient'' characterizations. In this paper we investigate the problem of using max-product to find the maximum weight matching in an arbitrary graph with edge weights. This is done by first constructing a probability distribution whose mode corresponds to the optimal matching, and then running max-product. Weighted matching can also be posed as an integer program, for which there is an LP relaxation. This relaxation is not always tight. In this paper we show that \\begin{enumerate} \\item If the LP relaxation is tight, then max-product always converges, and that too to the correct answer. \\item If the LP relaxation is loose, then max-product does not converge. \\end{enumerate} This provides an exact, data-dependent characterization of max-product performance, and a precise connection to LP relaxation, which is a well-studied optimization technique. Also, since LP relaxation is known to be tight for bipartite graphs, our results generalize other recent results on using max-product to find weighted matchings in bipartite graphs.", "source": "arxiv/ml"}
{"id": "arxiv:10", "title": "HMM Speaker Identification Using Linear and Non-linear Merging Techniques", "text": "Speaker identification is a powerful, non-invasive and in-expensive biometric technique. The recognition accuracy, however, deteriorates when noise levels affect a specific band of frequency. In this paper, we present a sub-band based speaker identification that intends to improve the live testing performance. Each frequency sub-band is processed and classified independently. We also compare the linear and non-linear merging techniques for the sub-bands recognizer. Support vector machines and Gaussian Mixture models are the non-linear merging techniques that are investigated. Results showed that the sub-band based method used with linear merging techniques enormously improved the performance of the speaker identification over the performance of wide-band recognizers when tested live. A live testing improvement of 9.78% was achieved", "source": "arxiv/ml"}
{"id": "arxiv:11", "title": "Statistical Mechanics of Nonlinear On-line Learning for Ensemble Teachers", "text": "We analyze the generalization performance of a student in a model composed of nonlinear perceptrons: a true teacher, ensemble teachers, and the student. We calculate the generalization error of the student analytically or numerically using statistical mechanics in the framework of on-line learning. We treat two well-known learning rules: Hebbian learning and perceptron learning. As a result, it is proven that the nonlinear model shows qualitatively different behaviors from the linear model. Moreover, it is clarified that Hebbian learning and perceptron learning show qualitatively different behaviors from each other. In Hebbian learning, we can analytically obtain the solutions. In this case, the generalization error monotonically decreases. The steady value of the generalization error is independent of the learning rate. The larger the number of teachers is and the more variety the ensemble teachers have, the smaller the generalization error is. In perceptron learning, we have to numerically obtain the solutions. In this case, the dynamical behaviors of the generalization error are non-monotonic. The smaller the learning rate is, the larger the number of teachers is; and the more variety the ensemble teachers have, the smaller the minimum value of the generalization error is.", "source": "arxiv/ml"}
{"id": "arxiv:12", "title": "On the monotonization of the training set", "text": "We consider the problem of minimal correction of the training set to make it consistent with monotonic constraints. This problem arises during analysis of data sets via techniques that require monotone data. We show that this problem is NP-hard in general and is equivalent to finding a maximal independent set in special orgraphs. Practically important cases of that problem considered in detail. These are the cases when a partial order given on the replies set is a total order or has a dimension 2. We show that the second case can be reduced to maximization of a quadratic convex function on a convex set. For this case we construct an approximate polynomial algorithm based on convex optimization.", "source": "arxiv/ml"}
{"id": "arxiv:13", "title": "Mixed membership stochastic blockmodels", "text": "Observations consisting of measurements on relationships for pairs of objects arise in many settings, such as protein interaction and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing such data with probabilisic models can be delicate because the simple exchangeability assumptions underlying many boilerplate models no longer hold. In this paper, we describe a latent variable model of such data called the mixed membership stochastic blockmodel. This model extends blockmodels for relational data to ones which capture mixed membership latent relational structure, thus providing an object-specific low-dimensional representation. We develop a general variational inference algorithm for fast approximate posterior inference. We explore applications to social and protein interaction networks.", "source": "arxiv/ml"}
{"id": "arxiv:14", "title": "Loop corrections for message passing algorithms in continuous variable models", "text": "In this paper we derive the equations for Loop Corrected Belief Propagation on a continuous variable Gaussian model. Using the exactness of the averages for belief propagation for Gaussian models, a different way of obtaining the covariances is found, based on Belief Propagation on cavity graphs. We discuss the relation of this loop correction algorithm to Expectation Propagation algorithms for the case in which the model is no longer Gaussian, but slightly perturbed by nonlinear terms.", "source": "arxiv/ml"}
{"id": "arxiv:15", "title": "A Novel Model of Working Set Selection for SMO Decomposition Methods", "text": "In the process of training Support Vector Machines (SVMs) by decomposition methods, working set selection is an important technique, and some exciting schemes were employed into this field. To improve working set selection, we propose a new model for working set selection in sequential minimal optimization (SMO) decomposition methods. In this model, it selects B as working set without reselection. Some properties are given by simple proof, and experiments demonstrate that the proposed method is in general faster than existing methods.", "source": "arxiv/ml"}
{"id": "arxiv:16", "title": "Getting started in probabilistic graphical models", "text": "Probabilistic graphical models (PGMs) have become a popular tool for computational analysis of biological data in a variety of domains. But, what exactly are they and how do they work? How can we use PGMs to discover patterns that are biologically relevant? And to what extent can PGMs help us formulate new hypotheses that are testable at the bench? This note sketches out some answers and illustrates the main ideas behind the statistical approach to biological pattern discovery.", "source": "arxiv/ml"}
{"id": "arxiv:17", "title": "A tutorial on conformal prediction", "text": "Conformal prediction uses past experience to determine precise levels of confidence in new predictions. Given an error probability $\\epsilon$, together with a method that makes a prediction $\\hat{y}$ of a label $y$, it produces a set of labels, typically containing $\\hat{y}$, that also contains $y$ with probability $1-\\epsilon$. Conformal prediction can be applied to any method for producing $\\hat{y}$: a nearest-neighbor method, a support-vector machine, ridge regression, etc. Conformal prediction is designed for an on-line setting in which labels are predicted successively, each one being revealed before the next is predicted. The most novel and valuable feature of conformal prediction is that if the successive examples are sampled independently from the same distribution, then the successive predictions will be right $1-\\epsilon$ of the time, even though they are based on an accumulating dataset rather than on independent datasets. In addition to the model under which successive examples are sampled independently, other on-line compression models can also use conformal prediction. The widely used Gaussian linear model is one of these. This tutorial presents a self-contained account of the theory of conformal prediction and works through several numerical examples. A more comprehensive treatment of the topic is provided in \"Algorithmic Learning in a Random World\", by Vladimir Vovk, Alex Gammerman, and Glenn Shafer (Springer, 2005).", "source": "arxiv/ml"}
{"id": "arxiv:18", "title": "Scale-sensitive Psi-dimensions: the Capacity Measures for Classifiers Taking Values in R^Q", "text": "Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such \"VC dimensions\" exist for models taking values in {0, 1}, {1,..., Q} and R. We introduce the generalizations appropriate for the missing case, the one of models with values in R^Q. This provides us with a new guaranteed risk for M-SVMs which appears superior to the existing one.", "source": "arxiv/ml"}
{"id": "arxiv:19", "title": "The Role of Time in the Creation of Knowledge", "text": "This paper I assume that in humans the creation of knowledge depends on a discrete time, or stage, sequential decision-making process subjected to a stochastic, information transmitting environment. For each time-stage, this environment randomly transmits Shannon type information-packets to the decision-maker, who examines each of them for relevancy and then determines his optimal choices. Using this set of relevant information-packets, the decision-maker adapts, over time, to the stochastic nature of his environment, and optimizes the subjective expected rate-of-growth of knowledge. The decision-maker's optimal actions, lead to a decision function that involves, over time, his view of the subjective entropy of the environmental process and other important parameters at each time-stage of the process. Using this model of human behavior, one could create psychometric experiments using computer simulation and real decision-makers, to play programmed games to measure the resulting human performance.", "source": "arxiv/ml"}
{"id": "arxiv:20", "title": "Clustering and Feature Selection using Sparse Principal Component Analysis", "text": "In this paper, we study the application of sparse principal component analysis (PCA) to clustering and feature selection problems. Sparse PCA seeks sparse factors, or linear combinations of the data variables, explaining a maximum amount of variance in the data while having only a limited number of nonzero coefficients. PCA is often used as a simple clustering technique and sparse factors allow us here to interpret the clusters in terms of a reduced set of variables. We begin with a brief introduction and motivation on sparse PCA and detail our implementation of the algorithm in d'Aspremont et al. (2005). We then apply these results to some classic clustering and feature selection problems arising in biology.", "source": "arxiv/ml"}
{"id": "arxiv:21", "title": "Model Selection Through Sparse Maximum Likelihood Estimation", "text": "We consider the problem of estimating the parameters of a Gaussian or binary distribution in such a way that the resulting undirected graphical model is sparse. Our approach is to solve a maximum likelihood problem with an added l_1-norm penalty term. The problem as formulated is convex but the memory requirements and complexity of existing interior point methods are prohibitive for problems with more than tens of nodes. We present two new algorithms for solving problems with at least a thousand nodes in the Gaussian case. Our first algorithm uses block coordinate descent, and can be interpreted as recursive l_1-norm penalized regression. Our second algorithm, based on Nesterov's first order method, yields a complexity estimate with a better dependence on problem size than existing interior point methods. Using a log determinant relaxation of the log partition function (Wainwright & Jordan (2006)), we show that these same algorithms can be used to solve an approximate sparse maximum likelihood problem for the binary case. We test our algorithms on synthetic data, as well as on gene expression and senate voting records data.", "source": "arxiv/ml"}
{"id": "arxiv:22", "title": "Optimal Solutions for Sparse Principal Component Analysis", "text": "Given a sample covariance matrix, we examine the problem of maximizing the variance explained by a linear combination of the input variables while constraining the number of nonzero coefficients in this combination. This is known as sparse principal component analysis and has a wide array of applications in machine learning and engineering. We formulate a new semidefinite relaxation to this problem and derive a greedy algorithm that computes a full set of good solutions for all target numbers of non zero coefficients, with total complexity O(n^3), where n is the number of variables. We then use the same relaxation to derive sufficient conditions for global optimality of a solution, which can be tested in O(n^3) per pattern. We discuss applications in subset selection and sparse recovery and show on artificial examples and biological data that our algorithm does provide globally optimal solutions in many cases.", "source": "arxiv/ml"}
{"id": "arxiv:23", "title": "A New Generalization of Chebyshev Inequality for Random Vectors", "text": "In this article, we derive a new generalization of Chebyshev inequality for random vectors. We demonstrate that the new generalization is much less conservative than the classical generalization.", "source": "arxiv/ml"}
{"id": "arxiv:24", "title": "Clusters, Graphs, and Networks for Analysing Internet-Web-Supported Communication within a Virtual Community", "text": "The proposal is to use clusters, graphs and networks as models in order to analyse the Web structure. Clusters, graphs and networks provide knowledge representation and organization. Clusters were generated by co-site analysis. The sample is a set of academic Web sites from the countries belonging to the European Union. These clusters are here revisited from the point of view of graph theory and social network analysis. This is a quantitative and structural analysis. In fact, the Internet is a computer network that connects people and organizations. Thus we may consider it to be a social network. The set of Web academic sites represents an empirical social network, and is viewed as a virtual community. The network structural properties are here analysed applying together cluster analysis, graph theory and social network analysis.", "source": "arxiv/ml"}
{"id": "arxiv:25", "title": "Universal Reinforcement Learning", "text": "We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence future observations and costs. The goal is to minimize the long-term average cost. We propose a novel algorithm, known as the active LZ algorithm, for optimal control based on ideas from the Lempel-Ziv scheme for universal data compression and prediction. We establish that, under the active LZ algorithm, if there exists an integer $K$ such that the future is conditionally independent of the past given a window of $K$ consecutive actions and observations, then the average cost converges to the optimum. Experimental results involving the game of Rock-Paper-Scissors illustrate merits of the algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:26", "title": "Consistency of the group Lasso and multiple kernel learning", "text": "We consider the least-square regression problem with regularization by a block 1-norm, i.e., a sum of Euclidean norms over spaces of dimensions larger than one. This problem, referred to as the group Lasso, extends the usual regularization by the 1-norm where all spaces have dimension one, where it is commonly referred to as the Lasso. In this paper, we study the asymptotic model consistency of the group Lasso. We derive necessary and sufficient conditions for the consistency of group Lasso under practical assumptions, such as model misspecification. When the linear predictors and Euclidean norms are replaced by functions and reproducing kernel Hilbert norms, the problem is usually referred to as multiple kernel learning and is commonly used for learning from heterogeneous data sources and for non linear variable selection. Using tools from functional analysis, and in particular covariance operators, we extend the consistency results to this infinite dimensional case and also propose an adaptive scheme to obtain a consistent model estimate, even when the necessary condition required for the non adaptive scheme is not satisfied.", "source": "arxiv/ml"}
{"id": "arxiv:27", "title": "Quantum Algorithms for Learning and Testing Juntas", "text": "In this article we develop quantum algorithms for learning and testing juntas, i.e. Boolean functions which depend only on an unknown set of k out of n input variables. Our aim is to develop efficient algorithms: - whose sample complexity has no dependence on n, the dimension of the domain the Boolean functions are defined over; - with no access to any classical or quantum membership (\"black-box\") queries. Instead, our algorithms use only classical examples generated uniformly at random and fixed quantum superpositions of such classical examples; - which require only a few quantum examples but possibly many classical random examples (which are considered quite \"cheap\" relative to quantum examples). Our quantum algorithms are based on a subroutine FS which enables sampling according to the Fourier spectrum of f; the FS subroutine was used in earlier work of Bshouty and Jackson on quantum learning. Our results are as follows: - We give an algorithm for testing k-juntas to accuracy $\\epsilon$ that uses $O(k/\\epsilon)$ quantum examples. This improves on the number of examples used by the best known classical algorithm. - We establish the following lower bound: any FS-based k-junta testing algorithm requires $\\Omega(\\sqrt{k})$ queries. - We give an algorithm for learning $k$-juntas to accuracy $\\epsilon$ that uses $O(\\epsilon^{-1} k\\log k)$ quantum examples and $O(2^k \\log(1/\\epsilon))$ random examples. We show that this learning algorithms is close to optimal by giving a related lower bound.", "source": "arxiv/ml"}
{"id": "arxiv:28", "title": "Virtual screening with support vector machines and structure kernels", "text": "Support vector machines and kernel methods have recently gained considerable attention in chemoinformatics. They offer generally good performance for problems of supervised classification or regression, and provide a flexible and computationally efficient framework to include relevant information and prior knowledge about the data and problems to be handled. In particular, with kernel methods molecules do not need to be represented and stored explicitly as vectors or fingerprints, but only to be compared to each other through a comparison function technically called a kernel. While classical kernels can be used to compare vector or fingerprint representations of molecules, completely new kernels were developed in the recent years to directly compare the 2D or 3D structures of molecules, without the need for an explicit vectorization step through the extraction of molecular descriptors. While still in their infancy, these approaches have already demonstrated their relevance on several toxicity prediction and structure-activity relationship problems.", "source": "arxiv/ml"}
{"id": "arxiv:29", "title": "Structure or Noise?", "text": "We show how rate-distortion theory provides a mechanism for automated theory building by naturally distinguishing between regularity and randomness. We start from the simple principle that model variables should, as much as possible, render the future and past conditionally independent. From this, we construct an objective function for model making whose extrema embody the trade-off between a model's structural complexity and its predictive power. The solutions correspond to a hierarchy of models that, at each level of complexity, achieve optimal predictive power at minimal cost. In the limit of maximal prediction the resulting optimal model identifies a process's intrinsic organization by extracting the underlying causal states. In this limit, the model's complexity is given by the statistical complexity, which is known to be minimal for achieving maximum prediction. Examples show how theory building can profit from analyzing a process's causal compressibility, which is reflected in the optimal models' rate-distortion curve--the process's characteristic for optimally balancing structure and noise at different levels of representation.", "source": "arxiv/ml"}
{"id": "arxiv:30", "title": "Cost-minimising strategies for data labelling : optimal stopping and active learning", "text": "Supervised learning deals with the inference of a distribution over an output or label space $\\CY$ conditioned on points in an observation space $\\CX$, given a training dataset $D$ of pairs in $\\CX \\times \\CY$. However, in a lot of applications of interest, acquisition of large amounts of observations is easy, while the process of generating labels is time-consuming or costly. One way to deal with this problem is {\\em active} learning, where points to be labelled are selected with the aim of creating a model with better performance than that of an model trained on an equal number of randomly sampled points. In this paper, we instead propose to deal with the labelling cost directly: The learning goal is defined as the minimisation of a cost which is a function of the expected model performance and the total cost of the labels used. This allows the development of general strategies and specific algorithms for (a) optimal stopping, where the expected cost dictates whether label acquisition should continue (b) empirical evaluation, where the cost is used as a performance metric for a given combination of inference, stopping and sampling methods. Though the main focus of the paper is optimal stopping, we also aim to provide the background for further developments and discussion in the related field of active learning.", "source": "arxiv/ml"}
{"id": "arxiv:31", "title": "Defensive forecasting for optimal prediction with expert advice", "text": "The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of \"second-guessing\" experts, whose advice depends on the learner's prediction; this paper assumes that the dependence on the learner's prediction is continuous.", "source": "arxiv/ml"}
{"id": "arxiv:32", "title": "Optimal Causal Inference: Estimating Stored Information and Approximating Causal Architecture", "text": "We introduce an approach to inferring the causal architecture of stochastic dynamical systems that extends rate distortion theory to use causal shielding---a natural principle of learning. We study two distinct cases of causal inference: optimal causal filtering and optimal causal estimation. Filtering corresponds to the ideal case in which the probability distribution of measurement sequences is known, giving a principled method to approximate a system's causal structure at a desired level of representation. We show that, in the limit in which a model complexity constraint is relaxed, filtering finds the exact causal architecture of a stochastic dynamical system, known as the causal-state partition. From this, one can estimate the amount of historical information the process stores. More generally, causal filtering finds a graded model-complexity hierarchy of approximations to the causal architecture. Abrupt changes in the hierarchy, as a function of approximation, capture distinct scales of structural organization. For nonideal cases with finite data, we show how the correct number of underlying causal states can be found by optimal causal estimation. A previously derived model complexity control term allows us to correct for the effect of statistical fluctuations in probability estimates and thereby avoid over-fitting.", "source": "arxiv/ml"}
{"id": "arxiv:33", "title": "On Semimeasures Predicting Martin-Loef Random Sequences", "text": "Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a universal sequence predictor in case of unknown mu. Despite some nearby results and proofs in the literature, the stronger result of convergence for all (Martin-Loef) random sequences remained open. Such a convergence result would be particularly interesting and natural, since randomness can be defined in terms of M itself. We show that there are universal semimeasures M which do not converge for all random sequences, i.e. we give a partial negative answer to the open problem. We also provide a positive answer for some non-universal semimeasures. We define the incomputable measure D as a mixture over all computable measures and the enumerable semimeasure W as a mixture over all enumerable nearly-measures. We show that W converges to D and D to mu on all random sequences. The Hellinger distance measuring closeness of two distributions plays a central role.", "source": "arxiv/ml"}
{"id": "arxiv:34", "title": "Continuous and randomized defensive forecasting: unified view", "text": "Defensive forecasting is a method of transforming laws of probability (stated in game-theoretic terms as strategies for Sceptic) into forecasting algorithms. There are two known varieties of defensive forecasting: \"continuous\", in which Sceptic's moves are assumed to depend on the forecasts in a (semi)continuous manner and which produces deterministic forecasts, and \"randomized\", in which the dependence of Sceptic's moves on the forecasts is arbitrary and Forecaster's moves are allowed to be randomized. This note shows that the randomized variety can be obtained from the continuous variety by smearing Sceptic's moves to make them continuous.", "source": "arxiv/ml"}
{"id": "arxiv:35", "title": "A Dichotomy Theorem for General Minimum Cost Homomorphism Problem", "text": "In the constraint satisfaction problem ($CSP$), the aim is to find an assignment of values to a set of variables subject to specified constraints. In the minimum cost homomorphism problem ($MinHom$), one is additionally given weights $c_{va}$ for every variable $v$ and value $a$, and the aim is to find an assignment $f$ to the variables that minimizes $\\sum_{v} c_{vf(v)}$. Let $MinHom(\\Gamma)$ denote the $MinHom$ problem parameterized by the set of predicates allowed for constraints. $MinHom(\\Gamma)$ is related to many well-studied combinatorial optimization problems, and concrete applications can be found in, for instance, defence logistics and machine learning. We show that $MinHom(\\Gamma)$ can be studied by using algebraic methods similar to those used for CSPs. With the aid of algebraic techniques, we classify the computational complexity of $MinHom(\\Gamma)$ for all choices of $\\Gamma$. Our result settles a general dichotomy conjecture previously resolved only for certain classes of directed graphs, [Gutin, Hell, Rafiey, Yeo, European J. of Combinatorics, 2008].", "source": "arxiv/ml"}
{"id": "arxiv:36", "title": "Filtering Additive Measurement Noise with Maximum Entropy in the Mean", "text": "The purpose of this note is to show how the method of maximum entropy in the mean (MEM) may be used to improve parametric estimation when the measurements are corrupted by large level of noise. The method is developed in the context on a concrete example: that of estimation of the parameter in an exponential distribution. We compare the performance of our method with the bayesian and maximum likelihood approaches.", "source": "arxiv/ml"}
{"id": "arxiv:37", "title": "On Universal Prediction and Bayesian Confirmation", "text": "The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or fail, in particular in complex situations. Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves various (philosophical) problems of traditional Bayesian sequence prediction. We show that Solomonoff's model possesses many desirable properties: Strong total and weak instantaneous bounds, and in contrast to most classical continuous prior densities has no zero p(oste)rior problem, i.e. can confirm universal hypotheses, is reparametrization and regrouping invariant, and avoids the old-evidence and updating problem. It even performs well (actually better) in non-computable environments.", "source": "arxiv/ml"}
{"id": "arxiv:38", "title": "Learning for Dynamic Bidding in Cognitive Radio Resources", "text": "In this paper, we model the various wireless users in a cognitive radio network as a collection of selfish, autonomous agents that strategically interact in order to acquire the dynamically available spectrum opportunities. Our main focus is on developing solutions for wireless users to successfully compete with each other for the limited and time-varying spectrum opportunities, given the experienced dynamics in the wireless network. We categorize these dynamics into two types: one is the disturbance due to the environment (e.g. wireless channel conditions, source traffic characteristics, etc.) and the other is the impact caused by competing users. To analyze the interactions among users given the environment disturbance, we propose a general stochastic framework for modeling how the competition among users for spectrum opportunities evolves over time. At each stage of the dynamic resource allocation, a central spectrum moderator auctions the available resources and the users strategically bid for the required resources. The joint bid actions affect the resource allocation and hence, the rewards and future strategies of all users. Based on the observed resource allocation and corresponding rewards from previous allocations, we propose a best response learning algorithm that can be deployed by wireless users to improve their bidding policy at each stage. The simulation results show that by deploying the proposed best response learning algorithm, the wireless users can significantly improve their own performance in terms of both the packet loss rate and the incurred cost for the used resources.", "source": "arxiv/ml"}
{"id": "arxiv:39", "title": "Mutual information for the selection of relevant variables in spectrometric nonlinear modelling", "text": "Data from spectrophotometers form vectors of a large number of exploitable variables. Building quantitative models using these variables most often requires using a smaller set of variables than the initial one. Indeed, a too large number of input variables to a model results in a too large number of parameters, leading to overfitting and poor generalization abilities. In this paper, we suggest the use of the mutual information measure to select variables from the initial set. The mutual information measures the information content in input variables with respect to the model output, without making any assumption on the model that will be used; it is thus suitable for nonlinear modelling. In addition, it leads to the selection of variables among the initial set, and not to linear or nonlinear combinations of them. Without decreasing the model performances compared to other variable projection methods, it allows therefore a greater interpretability of the results.", "source": "arxiv/ml"}
{"id": "arxiv:40", "title": "Fast Algorithm and Implementation of Dissimilarity Self-Organizing Maps", "text": "In many real world applications, data cannot be accurately represented by vectors. In those situations, one possible solution is to rely on dissimilarity measures that enable sensible comparison between observations. Kohonen's Self-Organizing Map (SOM) has been adapted to data described only through their dissimilarity matrix. This algorithm provides both non linear projection and clustering of non vector data. Unfortunately, the algorithm suffers from a high cost that makes it quite difficult to use with voluminous data sets. In this paper, we propose a new algorithm that provides an important reduction of the theoretical cost of the dissimilarity SOM without changing its outcome (the results are exactly the same as the ones obtained with the original algorithm). Moreover, we introduce implementation methods that result in very short running times. Improvements deduced from the theoretical cost model are validated on simulated and real world data (a word list clustering problem). We also demonstrate that the proposed implementation methods reduce by a factor up to 3 the running time of the fast algorithm over a standard implementation.", "source": "arxiv/ml"}
{"id": "arxiv:41", "title": "Une adaptation des cartes auto-organisatrices pour des donn\\'ees d\\'ecrites par un tableau de dissimilarit\\'es", "text": "Many data analysis methods cannot be applied to data that are not represented by a fixed number of real values, whereas most of real world observations are not readily available in such a format. Vector based data analysis methods have therefore to be adapted in order to be used with non standard complex data. A flexible and general solution for this adaptation is to use a (dis)similarity measure. Indeed, thanks to expert knowledge on the studied data, it is generally possible to define a measure that can be used to make pairwise comparison between observations. General data analysis methods are then obtained by adapting existing methods to (dis)similarity matrices. In this article, we propose an adaptation of Kohonen's Self Organizing Map (SOM) to (dis)similarity data. The proposed algorithm is an adapted version of the vector based batch SOM. The method is validated on real world data: we provide an analysis of the usage patterns of the web site of the Institut National de Recherche en Informatique et Automatique, constructed thanks to web log mining method.", "source": "arxiv/ml"}
{"id": "arxiv:42", "title": "Self-organizing maps and symbolic data", "text": "In data analysis new forms of complex data have to be considered like for example (symbolic data, functional data, web data, trees, SQL query and multimedia data, ...). In this context classical data analysis for knowledge discovery based on calculating the center of gravity can not be used because input are not $\\mathbb{R}^p$ vectors. In this paper, we present an application on real world symbolic data using the self-organizing map. To this end, we propose an extension of the self-organizing map that can handle symbolic data.", "source": "arxiv/ml"}
{"id": "arxiv:43", "title": "Fast Selection of Spectral Variables with B-Spline Compression", "text": "The large number of spectral variables in most data sets encountered in spectral chemometrics often renders the prediction of a dependent variable uneasy. The number of variables hopefully can be reduced, by using either projection techniques or selection methods; the latter allow for the interpretation of the selected variables. Since the optimal approach of testing all possible subsets of variables with the prediction model is intractable, an incremental selection approach using a nonparametric statistics is a good option, as it avoids the computationally intensive use of the model itself. It has two drawbacks however: the number of groups of variables to test is still huge, and colinearities can make the results unstable. To overcome these limitations, this paper presents a method to select groups of spectral variables. It consists in a forward-backward procedure applied to the coefficients of a B-Spline representation of the spectra. The criterion used in the forward-backward procedure is the mutual information, allowing to find nonlinear dependencies between variables, on the contrary of the generally used correlation. The spline representation is used to get interpretability of the results, as groups of consecutive spectral variables will be selected. The experiments conducted on NIR spectra from fescue grass and diesel fuels show that the method provides clearly identified groups of selected variables, making interpretation easy, while keeping a low computational load. The prediction performances obtained using the selected coefficients are higher than those obtained by the same method applied directly to the original variables and similar to those obtained using traditional models, although using significantly less spectral variables.", "source": "arxiv/ml"}
{"id": "arxiv:44", "title": "Resampling methods for parameter-free and robust feature selection with mutual information", "text": "Combining the mutual information criterion with a forward feature selection strategy offers a good trade-off between optimality of the selected feature subset and computation time. However, it requires to set the parameter(s) of the mutual information estimator and to determine when to halt the forward procedure. These two choices are difficult to make because, as the dimensionality of the subset increases, the estimation of the mutual information becomes less and less reliable. This paper proposes to use resampling methods, a K-fold cross-validation and the permutation test, to address both issues. The resampling methods bring information about the variance of the estimator, information which can then be used to automatically set the parameter and to calculate a threshold to stop the forward procedure. The procedure is illustrated on a synthetic dataset as well as on real-world examples.", "source": "arxiv/ml"}
{"id": "arxiv:45", "title": "Evolving Classifiers: Methods for Incremental Learning", "text": "The ability of a classifier to take on new information and classes by evolving the classifier without it having to be fully retrained is known as incremental learning. Incremental learning has been successfully applied to many classification problems, where the data is changing and is not all available at once. In this paper there is a comparison between Learn++, which is one of the most recent incremental learning algorithms, and the new proposed method of Incremental Learning Using Genetic Algorithm (ILUGA). Learn++ has shown good incremental learning capabilities on benchmark datasets on which the new ILUGA method has been tested. ILUGA has also shown good incremental learning ability using only a few classifiers and does not suffer from catastrophic forgetting. The results obtained for ILUGA on the Optical Character Recognition (OCR) and Wine datasets are good, with an overall accuracy of 93% and 94% respectively showing a 4% improvement over Learn++.MT for the difficult multi-class OCR dataset.", "source": "arxiv/ml"}
{"id": "arxiv:46", "title": "Classification of Images Using Support Vector Machines", "text": "Support Vector Machines (SVMs) are a relatively new supervised classification technique to the land cover mapping community. They have their roots in Statistical Learning Theory and have gained prominence because they are robust, accurate and are effective even when using a small training sample. By their nature SVMs are essentially binary classifiers, however, they can be adopted to handle the multiple classification tasks common in remote sensing studies. The two approaches commonly used are the One-Against-One (1A1) and One-Against-All (1AA) techniques. In this paper, these approaches are evaluated in as far as their impact and implication for land cover mapping. The main finding from this research is that whereas the 1AA technique is more predisposed to yielding unclassified and mixed pixels, the resulting classification accuracy is not significantly different from 1A1 approach. It is the authors conclusions that ultimately the choice of technique adopted boils down to personal preference and the uniqueness of the dataset at hand.", "source": "arxiv/ml"}
{"id": "arxiv:47", "title": "Prediction with expert advice for the Brier game", "text": "We show that the Brier game of prediction is mixable and find the optimal learning rate and substitution function for it. The resulting prediction algorithm is applied to predict results of football and tennis matches. The theoretical performance guarantee turns out to be rather tight on these data sets, especially in the case of the more extensive tennis data.", "source": "arxiv/ml"}
{"id": "arxiv:48", "title": "Association Rules in the Relational Calculus", "text": "One of the most utilized data mining tasks is the search for association rules. Association rules represent significant relationships between items in transactions. We extend the concept of association rule to represent a much broader class of associations, which we refer to as \\emph{entity-relationship rules.} Semantically, entity-relationship rules express associations between properties of related objects. Syntactically, these rules are based on a broad subclass of safe domain relational calculus queries. We propose a new definition of support and confidence for entity-relationship rules and for the frequency of entity-relationship queries. We prove that the definition of frequency satisfies standard probability axioms and the Apriori property.", "source": "arxiv/ml"}
{"id": "arxiv:49", "title": "The structure of verbal sequences analyzed with unsupervised learning techniques", "text": "Data mining allows the exploration of sequences of phenomena, whereas one usually tends to focus on isolated phenomena or on the relation between two phenomena. It offers invaluable tools for theoretical analyses and exploration of the structure of sentences, texts, dialogues, and speech. We report here the results of an attempt at using it for inspecting sequences of verbs from French accounts of road accidents. This analysis comes from an original approach of unsupervised training allowing the discovery of the structure of sequential data. The entries of the analyzer were only made of the verbs appearing in the sentences. It provided a classification of the links between two successive verbs into four distinct clusters, allowing thus text segmentation. We give here an interpretation of these clusters by applying a statistical analysis to independent semantic annotations.", "source": "arxiv/ml"}
{"id": "arxiv:50", "title": "Consistency of trace norm minimization", "text": "Regularization by the sum of singular values, also referred to as the trace norm, is a popular technique for estimating low rank rectangular matrices. In this paper, we extend some of the consistency results of the Lasso to provide necessary and sufficient conditions for rank consistency of trace norm minimization with the square loss. We also provide an adaptive version that is rank consistent even when the necessary condition for the non adaptive version is not fulfilled.", "source": "arxiv/ml"}
{"id": "arxiv:51", "title": "An efficient reduction of ranking to classification", "text": "This paper describes an efficient reduction of the learning problem of ranking to binary classification. The reduction guarantees an average pairwise misranking regret of at most that of the binary classifier regret, improving a recent result of Balcan et al which only guarantees a factor of 2. Moreover, our reduction applies to a broader class of ranking loss functions, admits a simpler proof, and the expected running time complexity of our algorithm in terms of number of calls to a classifier or preference function is improved from $\\Omega(n^2)$ to $O(n \\log n)$. In addition, when the top $k$ ranked elements only are required ($k \\ll n$), as in many applications in information extraction or search engines, the time complexity of our algorithm can be further reduced to $O(k \\log k + n)$. Our reduction and algorithm are thus practical for realistic applications where the number of points to rank exceeds several thousands. Much of our results also extend beyond the bipartite case previously studied. Our rediction is a randomized one. To complement our result, we also derive lower bounds on any deterministic reduction from binary (preference) classification to ranking, implying that our use of a randomized reduction is essentially necessary for the guarantees we provide.", "source": "arxiv/ml"}
{"id": "arxiv:52", "title": "Combining haplotypers", "text": "Statistically resolving the underlying haplotype pair for a genotype measurement is an important intermediate step in gene mapping studies, and has received much attention recently. Consequently, a variety of methods for this problem have been developed. Different methods employ different statistical models, and thus implicitly encode different assumptions about the nature of the underlying haplotype structure. Depending on the population sample in question, their relative performance can vary greatly, and it is unclear which method to choose for a particular sample. Instead of choosing a single method, we explore combining predictions returned by different methods in a principled way, and thereby circumvent the problem of method selection. We propose several techniques for combining haplotype reconstructions and analyze their computational properties. In an experimental study on real-world haplotype data we show that such techniques can provide more accurate and robust reconstructions, and are useful for outlier detection. Typically, the combined prediction is at least as accurate as or even more accurate than the best individual method, effectively circumventing the method selection problem.", "source": "arxiv/ml"}
{"id": "arxiv:53", "title": "A Tutorial on Spectral Clustering", "text": "In recent years, spectral clustering has become one of the most popular modern clustering algorithms. It is simple to implement, can be solved efficiently by standard linear algebra software, and very often outperforms traditional clustering algorithms such as the k-means algorithm. On the first glance spectral clustering appears slightly mysterious, and it is not obvious to see why it works at all and what it really does. The goal of this tutorial is to give some intuition on those questions. We describe different graph Laplacians and their basic properties, present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches. Advantages and disadvantages of the different spectral clustering algorithms are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:54", "title": "Building Rules on Top of Ontologies for the Semantic Web with Inductive Logic Programming", "text": "Building rules on top of ontologies is the ultimate goal of the logical layer of the Semantic Web. To this aim an ad-hoc mark-up language for this layer is currently under discussion. It is intended to follow the tradition of hybrid knowledge representation and reasoning systems such as $\\mathcal{AL}$-log that integrates the description logic $\\mathcal{ALC}$ and the function-free Horn clausal language \\textsc{Datalog}. In this paper we consider the problem of automating the acquisition of these rules for the Semantic Web. We propose a general framework for rule induction that adopts the methodological apparatus of Inductive Logic Programming and relies on the expressive and deductive power of $\\mathcal{AL}$-log. The framework is valid whatever the scope of induction (description vs. prediction) is. Yet, for illustrative purposes, we also discuss an instantiation of the framework which aims at description and turns out to be useful in Ontology Refinement. Keywords: Inductive Logic Programming, Hybrid Knowledge Representation and Reasoning Systems, Ontologies, Semantic Web. Note: To appear in Theory and Practice of Logic Programming (TPLP)", "source": "arxiv/ml"}
{"id": "arxiv:55", "title": "Empirical Evaluation of Four Tensor Decomposition Algorithms", "text": "Higher-order tensor decompositions are analogous to the familiar Singular Value Decomposition (SVD), but they transcend the limitations of matrices (second-order tensors). SVD is a powerful tool that has achieved impressive results in information retrieval, collaborative filtering, computational linguistics, computational vision, and other fields. However, SVD is limited to two-dimensional arrays of data (two modes), and many potential applications have three or more modes, which require higher-order tensor decompositions. This paper evaluates four algorithms for higher-order tensor decomposition: Higher-Order Singular Value Decomposition (HO-SVD), Higher-Order Orthogonal Iteration (HOOI), Slice Projection (SP), and Multislice Projection (MP). We measure the time (elapsed run time), space (RAM and disk space requirements), and fit (tensor reconstruction accuracy) of the four algorithms, under a variety of conditions. We find that standard implementations of HO-SVD and HOOI do not scale up to larger tensors, due to increasing RAM requirements. We recommend HOOI for tensors that are small enough for the available RAM and MP for larger tensors.", "source": "arxiv/ml"}
{"id": "arxiv:56", "title": "Inverse Sampling for Nonasymptotic Sequential Estimation of Bounded Variable Means", "text": "In this paper, we consider the nonasymptotic sequential estimation of means of random variables bounded in between zero and one. We have rigorously demonstrated that, in order to guarantee prescribed relative precision and confidence level, it suffices to continue sampling until the sample sum is no less than a certain bound and then take the average of samples as an estimate for the mean of the bounded random variable. We have developed an explicit formula and a bisection search method for the determination of such bound of sample sum, without any knowledge of the bounded variable. Moreover, we have derived bounds for the distribution of sample size. In the special case of Bernoulli random variables, we have established analytical and numerical methods to further reduce the bound of sample sum and thus improve the efficiency of sampling. Furthermore, the fallacy of existing results are detected and analyzed.", "source": "arxiv/ml"}
{"id": "arxiv:57", "title": "Image Classification Using SVMs: One-against-One Vs One-against-All", "text": "Support Vector Machines (SVMs) are a relatively new supervised classification technique to the land cover mapping community. They have their roots in Statistical Learning Theory and have gained prominence because they are robust, accurate and are effective even when using a small training sample. By their nature SVMs are essentially binary classifiers, however, they can be adopted to handle the multiple classification tasks common in remote sensing studies. The two approaches commonly used are the One-Against-One (1A1) and One-Against-All (1AA) techniques. In this paper, these approaches are evaluated in as far as their impact and implication for land cover mapping. The main finding from this research is that whereas the 1AA technique is more predisposed to yielding unclassified and mixed pixels, the resulting classification accuracy is not significantly different from 1A1 approach. It is the authors conclusion therefore that ultimately the choice of technique adopted boils down to personal preference and the uniqueness of the dataset at hand.", "source": "arxiv/ml"}
{"id": "arxiv:58", "title": "Clustering with Transitive Distance and K-Means Duality", "text": "Recent spectral clustering methods are a propular and powerful technique for data clustering. These methods need to solve the eigenproblem whose computational complexity is $O(n^3)$, where $n$ is the number of data samples. In this paper, a non-eigenproblem based clustering method is proposed to deal with the clustering problem. Its performance is comparable to the spectral clustering algorithms but it is more efficient with computational complexity $O(n^2)$. We show that with a transitive distance and an observed property, called K-means duality, our algorithm can be used to handle data sets with complex cluster shapes, multi-scale clusters, and noise. Moreover, no parameters except the number of clusters need to be set in our algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:59", "title": "Derivations of Normalized Mutual Information in Binary Classifications", "text": "This correspondence studies the basic problem of classifications - how to evaluate different classifiers. Although the conventional performance indexes, such as accuracy, are commonly used in classifier selection or evaluation, information-based criteria, such as mutual information, are becoming popular in feature/model selections. In this work, we propose to assess classifiers in terms of normalized mutual information (NI), which is novel and well defined in a compact range for classifier evaluation. We derive close-form relations of normalized mutual information with respect to accuracy, precision, and recall in binary classifications. By exploring the relations among them, we reveal that NI is actually a set of nonlinear functions, with a concordant power-exponent form, to each performance index. The relations can also be expressed with respect to precision and recall, or to false alarm and hitting rate (recall).", "source": "arxiv/ml"}
{"id": "arxiv:60", "title": "Covariance and PCA for Categorical Variables", "text": "Covariances from categorical variables are defined using a regular simplex expression for categories. The method follows the variance definition by Gini, and it gives the covariance as a solution of simultaneous equations. The calculated results give reasonable values for test data. A method of principal component analysis (RS-PCA) is also proposed using regular simplex expressions, which allows easy interpretation of the principal components. The proposed methods apply to variable selection problem of categorical data USCensus1990 data. The proposed methods give appropriate criterion for the variable selection problem of categorical", "source": "arxiv/ml"}
{"id": "arxiv:61", "title": "On the Relationship between the Posterior and Optimal Similarity", "text": "For a classification problem described by the joint density $P(\\omega,x)$, models of $P(\\omega\\eq\\omega'|x,x')$ (the ``Bayesian similarity measure'') have been shown to be an optimal similarity measure for nearest neighbor classification. This paper analyzes demonstrates several additional properties of that conditional distribution. The paper first shows that we can reconstruct, up to class labels, the class posterior distribution $P(\\omega|x)$ given $P(\\omega\\eq\\omega'|x,x')$, gives a procedure for recovering the class labels, and gives an asymptotically Bayes-optimal classification procedure. It also shows, given such an optimal similarity measure, how to construct a classifier that outperforms the nearest neighbor classifier and achieves Bayes-optimal classification rates. The paper then analyzes Bayesian similarity in a framework where a classifier faces a number of related classification tasks (multitask learning) and illustrates that reconstruction of the class posterior distribution is not possible in general. Finally, the paper identifies a distinct class of classification problems using $P(\\omega\\eq\\omega'|x,x')$ and shows that using $P(\\omega\\eq\\omega'|x,x')$ to solve those problems is the Bayes optimal solution.", "source": "arxiv/ml"}
{"id": "arxiv:62", "title": "A Reactive Tabu Search Algorithm for Stimuli Generation in Psycholinguistics", "text": "The generation of meaningless \"words\" matching certain statistical and/or linguistic criteria is frequently needed for experimental purposes in Psycholinguistics. Such stimuli receive the name of pseudowords or nonwords in the Cognitive Neuroscience literatue. The process for building nonwords sometimes has to be based on linguistic units such as syllables or morphemes, resulting in a numerical explosion of combinations when the size of the nonwords is increased. In this paper, a reactive tabu search scheme is proposed to generate nonwords of variables size. The approach builds pseudowords by using a modified Metaheuristic algorithm based on a local search procedure enhanced by a feedback-based scheme. Experimental results show that the new algorithm is a practical and effective tool for nonword generation.", "source": "arxiv/ml"}
{"id": "arxiv:63", "title": "Equations of States in Singular Statistical Estimation", "text": "Learning machines which have hierarchical structures or hidden variables are singular statistical models because they are nonidentifiable and their Fisher information matrices are singular. In singular statistical models, neither the Bayes a posteriori distribution converges to the normal distribution nor the maximum likelihood estimator satisfies asymptotic normality. This is the main reason why it has been difficult to predict their generalization performances from trained states. In this paper, we study four errors, (1) Bayes generalization error, (2) Bayes training error, (3) Gibbs generalization error, and (4) Gibbs training error, and prove that there are mathematical relations among these errors. The formulas proved in this paper are equations of states in statistical estimation because they hold for any true distribution, any parametric model, and any a priori distribution. Also we show that Bayes and Gibbs generalization errors are estimated by Bayes and Gibbs training errors, and propose widely applicable information criteria which can be applied to both regular and singular statistical models.", "source": "arxiv/ml"}
{"id": "arxiv:64", "title": "A Universal Kernel for Learning Regular Languages", "text": "We give a universal kernel that renders all the regular languages linearly separable. We are not able to compute this kernel efficiently and conjecture that it is intractable, but we do have an efficient $\\eps$-approximation.", "source": "arxiv/ml"}
{"id": "arxiv:65", "title": "Automatic Pattern Classification by Unsupervised Learning Using Dimensionality Reduction of Data with Mirroring Neural Networks", "text": "This paper proposes an unsupervised learning technique by using Multi-layer Mirroring Neural Network and Forgy's clustering algorithm. Multi-layer Mirroring Neural Network is a neural network that can be trained with generalized data inputs (different categories of image patterns) to perform non-linear dimensionality reduction and the resultant low-dimensional code is used for unsupervised pattern classification using Forgy's algorithm. By adapting the non-linear activation function (modified sigmoidal function) and initializing the weights and bias terms to small random values, mirroring of the input pattern is initiated. In training, the weights and bias terms are changed in such a way that the input presented is reproduced at the output by back propagating the error. The mirroring neural network is capable of reducing the input vector to a great degree (approximately 1/30th the original size) and also able to reconstruct the input pattern at the output layer from this reduced code units. The feature set (output of central hidden layer) extracted from this network is fed to Forgy's algorithm, which classify input data patterns into distinguishable classes. In the implementation of Forgy's algorithm, initial seed points are selected in such a way that they are distant enough to be perfectly grouped into different categories. Thus a new method of unsupervised learning is formulated and demonstrated in this paper. This method gave impressive results when applied to classification of different image patterns.", "source": "arxiv/ml"}
{"id": "arxiv:66", "title": "Reconstruction of Markov Random Fields from Samples: Some Easy Observations and Algorithms", "text": "Markov random fields are used to model high dimensional distributions in a number of applied areas. Much recent interest has been devoted to the reconstruction of the dependency structure from independent samples from the Markov random fields. We analyze a simple algorithm for reconstructing the underlying graph defining a Markov random field on $n$ nodes and maximum degree $d$ given observations. We show that under mild non-degeneracy conditions it reconstructs the generating graph with high probability using $\\Theta(d \\epsilon^{-2}\\delta^{-4} \\log n)$ samples where $\\epsilon,\\delta$ depend on the local interactions. For most local interaction $\\eps,\\delta$ are of order $\\exp(-O(d))$. Our results are optimal as a function of $n$ up to a multiplicative constant depending on $d$ and the strength of the local interactions. Our results seem to be the first results for general models that guarantee that {\\em the} generating model is reconstructed. Furthermore, we provide explicit $O(n^{d+2} \\epsilon^{-2}\\delta^{-4} \\log n)$ running time bound. In cases where the measure on the graph has correlation decay, the running time is $O(n^2 \\log n)$ for all fixed $d$. We also discuss the effect of observing noisy samples and show that as long as the noise level is low, our algorithm is effective. On the other hand, we construct an example where large noise implies non-identifiability even for generic noise and interactions. Finally, we briefly show that in some simple cases, models with hidden nodes can also be recovered.", "source": "arxiv/ml"}
{"id": "arxiv:67", "title": "A New Theoretic Foundation for Cross-Layer Optimization", "text": "Cross-layer optimization solutions have been proposed in recent years to improve the performance of network users operating in a time-varying, error-prone wireless environment. However, these solutions often rely on ad-hoc optimization approaches, which ignore the different environmental dynamics experienced at various layers by a user and violate the layered network architecture of the protocol stack by requiring layers to provide access to their internal protocol parameters to other layers. This paper presents a new theoretic foundation for cross-layer optimization, which allows each layer to make autonomous decisions individually, while maximizing the utility of the wireless user by optimally determining what information needs to be exchanged among layers. Hence, this cross-layer framework does not change the current layered architecture. Specifically, because the wireless user interacts with the environment at various layers of the protocol stack, the cross-layer optimization problem is formulated as a layered Markov decision process (MDP) in which each layer adapts its own protocol parameters and exchanges information (messages) with other layers in order to cooperatively maximize the performance of the wireless user. The message exchange mechanism for determining the optimal cross-layer transmission strategies has been designed for both off-line optimization and on-line dynamic adaptation. We also show that many existing cross-layer optimization algorithms can be formulated as simplified, sub-optimal, versions of our layered MDP framework.", "source": "arxiv/ml"}
{"id": "arxiv:68", "title": "Density estimation in linear time", "text": "We consider the problem of choosing a density estimate from a set of distributions F, minimizing the L1-distance to an unknown distribution (Devroye, Lugosi 2001). Devroye and Lugosi analyze two algorithms for the problem: Scheffe tournament winner and minimum distance estimate. The Scheffe tournament estimate requires fewer computations than the minimum distance estimate, but has strictly weaker guarantees than the latter. We focus on the computational aspect of density estimation. We present two algorithms, both with the same guarantee as the minimum distance estimate. The first one, a modification of the minimum distance estimate, uses the same number (quadratic in |F|) of computations as the Scheffe tournament. The second one, called ``efficient minimum loss-weight estimate,'' uses only a linear number of computations, assuming that F is preprocessed. We also give examples showing that the guarantees of the algorithms cannot be improved and explore randomized algorithms for density estimation.", "source": "arxiv/ml"}
{"id": "arxiv:69", "title": "Graph kernels between point clouds", "text": "Point clouds are sets of points in two or three dimensions. Most kernel methods for learning on sets of points have not yet dealt with the specific geometrical invariances and practical constraints associated with point clouds in computer vision and graphics. In this paper, we present extensions of graph kernels for point clouds, which allow to use kernel methods for such ob jects as shapes, line drawings, or any three-dimensional point clouds. In order to design rich and numerically efficient kernels with as few free parameters as possible, we use kernels between covariance matrices and their factorizations on graphical models. We derive polynomial time dynamic programming recursions and present applications to recognition of handwritten digits and Chinese characters from few training examples.", "source": "arxiv/ml"}
{"id": "arxiv:70", "title": "Improving the Performance of PieceWise Linear Separation Incremental Algorithms for Practical Hardware Implementations", "text": "In this paper we shall review the common problems associated with Piecewise Linear Separation incremental algorithms. This kind of neural models yield poor performances when dealing with some classification problems, due to the evolving schemes used to construct the resulting networks. So as to avoid this undesirable behavior we shall propose a modification criterion. It is based upon the definition of a function which will provide information about the quality of the network growth process during the learning phase. This function is evaluated periodically as the network structure evolves, and will permit, as we shall show through exhaustive benchmarks, to considerably improve the performance(measured in terms of network complexity and generalization capabilities) offered by the networks generated by these incremental models.", "source": "arxiv/ml"}
{"id": "arxiv:71", "title": "Improved Collaborative Filtering Algorithm via Information Transformation", "text": "In this paper, we propose a spreading activation approach for collaborative filtering (SA-CF). By using the opinion spreading process, the similarity between any users can be obtained. The algorithm has remarkably higher accuracy than the standard collaborative filtering (CF) using Pearson correlation. Furthermore, we introduce a free parameter $\\beta$ to regulate the contributions of objects to user-user correlations. The numerical results indicate that decreasing the influence of popular objects can further improve the algorithmic accuracy and personality. We argue that a better algorithm should simultaneously require less computation and generate higher accuracy. Accordingly, we further propose an algorithm involving only the top-$N$ similar neighbors for each target user, which has both less computational complexity and higher algorithmic accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:72", "title": "Online EM Algorithm for Latent Data Models", "text": "In this contribution, we propose a generic online (also sometimes called adaptive or recursive) version of the Expectation-Maximisation (EM) algorithm applicable to latent variable models of independent observations. Compared to the algorithm of Titterington (1984), this approach is more directly connected to the usual EM algorithm and does not rely on integration with respect to the complete data distribution. The resulting algorithm is usually simpler and is shown to achieve convergence to the stationary points of the Kullback-Leibler divergence between the marginal distribution of the observation and the model distribution at the optimal rate, i.e., that of the maximum likelihood estimator. In addition, the proposed approach is also suitable for conditional (or regression) models, as illustrated in the case of the mixture of linear regressions model.", "source": "arxiv/ml"}
{"id": "arxiv:73", "title": "Staring at Economic Aggregators through Information Lenses", "text": "It is hard to exaggerate the role of economic aggregators -- functions that summarize numerous and / or heterogeneous data -- in economic models since the early XX$^{th}$ century. In many cases, as witnessed by the pioneering works of Cobb and Douglas, these functions were information quantities tailored to economic theories, i.e. they were built to fit economic phenomena. In this paper, we look at these functions from the complementary side: information. We use a recent toolbox built on top of a vast class of distortions coined by Bregman, whose application field rivals metrics' in various subfields of mathematics. This toolbox makes it possible to find the quality of an aggregator (for consumptions, prices, labor, capital, wages, etc.), from the standpoint of the information it carries. We prove a rather striking result. From the informational standpoint, well-known economic aggregators do belong to the \\textit{optimal} set. As common economic assumptions enter the analysis, this large set shrinks, and it essentially ends up \\textit{exactly fitting} either CES, or Cobb-Douglas, or both. To summarize, in the relevant economic contexts, one could not have crafted better some aggregator from the information standpoint. We also discuss global economic behaviors of optimal information aggregators in general, and present a brief panorama of the links between economic and information aggregators. Keywords: Economic Aggregators, CES, Cobb-Douglas, Bregman divergences", "source": "arxiv/ml"}
{"id": "arxiv:74", "title": "Online variants of the cross-entropy method", "text": "The cross-entropy method is a simple but efficient method for global optimization. In this paper we provide two online variants of the basic CEM, together with a proof of convergence.", "source": "arxiv/ml"}
{"id": "arxiv:75", "title": "Factored Value Iteration Converges", "text": "In this paper we propose a novel algorithm, factored value iteration (FVI), for the approximate solution of factored Markov decision processes (fMDPs). The traditional approximate value iteration algorithm is modified in two ways. For one, the least-squares projection operator is modified so that it does not increase max-norm, and thus preserves convergence. The other modification is that we uniformly sample polynomially many samples from the (exponentially large) state space. This way, the complexity of our algorithm becomes polynomial in the size of the fMDP description length. We prove that the algorithm is convergent. We also derive an upper bound on the difference between our approximate solution and the optimal one, and also on the error introduced by sampling. We analyze various projection operators with respect to their computation complexity and their convergence when combined with approximate value iteration.", "source": "arxiv/ml"}
{"id": "arxiv:76", "title": "The optimal assignment kernel is not positive definite", "text": "We prove that the optimal assignment kernel, proposed recently as an attempt to embed labeled graphs and more generally tuples of basic data to a Hilbert space, is in fact not always positive definite.", "source": "arxiv/ml"}
{"id": "arxiv:77", "title": "Information Width", "text": "Kolmogorov argued that the concept of information exists also in problems with no underlying stochastic model (as Shannon's information representation) for instance, the information contained in an algorithm or in the genome. He introduced a combinatorial notion of entropy and information $I(x:\\sy)$ conveyed by a binary string $x$ about the unknown value of a variable $\\sy$. The current paper poses the following questions: what is the relationship between the information conveyed by $x$ about $\\sy$ to the description complexity of $x$ ? is there a notion of cost of information ? are there limits on how efficient $x$ conveys information ? To answer these questions Kolmogorov's definition is extended and a new concept termed {\\em information width} which is similar to $n$-widths in approximation theory is introduced. Information of any input source, e.g., sample-based, general side-information or a hybrid of both can be evaluated by a single common formula. An application to the space of binary functions is considered.", "source": "arxiv/ml"}
{"id": "arxiv:78", "title": "On the Complexity of Binary Samples", "text": "Consider a class $\\mH$ of binary functions $h: X\\to\\{-1, +1\\}$ on a finite interval $X=[0, B]\\subset \\Real$. Define the {\\em sample width} of $h$ on a finite subset (a sample) $S\\subset X$ as $\\w_S(h) \\equiv \\min_{x\\in S} |\\w_h(x)|$, where $\\w_h(x) = h(x) \\max\\{a\\geq 0: h(z)=h(x), x-a\\leq z\\leq x+a\\}$. Let $\\mathbb{S}_\\ell$ be the space of all samples in $X$ of cardinality $\\ell$ and consider sets of wide samples, i.e., {\\em hypersets} which are defined as $A_{\\beta, h} = \\{S\\in \\mathbb{S}_\\ell: \\w_{S}(h) \\geq \\beta\\}$. Through an application of the Sauer-Shelah result on the density of sets an upper estimate is obtained on the growth function (or trace) of the class $\\{A_{\\beta, h}: h\\in\\mH\\}$, $\\beta>0$, i.e., on the number of possible dichotomies obtained by intersecting all hypersets with a fixed collection of samples $S\\in\\mathbb{S}_\\ell$ of cardinality $m$. The estimate is $2\\sum_{i=0}^{2\\lfloor B/(2\\beta)\\rfloor}{m-\\ell\\choose i}$.", "source": "arxiv/ml"}
{"id": "arxiv:79", "title": "New Estimation Procedures for PLS Path Modelling", "text": "Given R groups of numerical variables X1, ... XR, we assume that each group is the result of one underlying latent variable, and that all latent variables are bound together through a linear equation system. Moreover, we assume that some explanatory latent variables may interact pairwise in one or more equations. We basically consider PLS Path Modelling's algorithm to estimate both latent variables and the model's coefficients. New \"external\" estimation schemes are proposed that draw latent variables towards strong group structures in a more flexible way. New \"internal\" estimation schemes are proposed to enable PLSPM to make good use of variable group complementarity and to deal with interactions. Application examples are given.", "source": "arxiv/ml"}
{"id": "arxiv:80", "title": "Learning Balanced Mixtures of Discrete Distributions with Small Sample", "text": "We study the problem of partitioning a small sample of $n$ individuals from a mixture of $k$ product distributions over a Boolean cube $\\{0, 1\\}^K$ according to their distributions. Each distribution is described by a vector of allele frequencies in $\\R^K$. Given two distributions, we use $\\gamma$ to denote the average $\\ell_2^2$ distance in frequencies across $K$ dimensions, which measures the statistical divergence between them. We study the case assuming that bits are independently distributed across $K$ dimensions. This work demonstrates that, for a balanced input instance for $k = 2$, a certain graph-based optimization function returns the correct partition with high probability, where a weighted graph $G$ is formed over $n$ individuals, whose pairwise hamming distances between their corresponding bit vectors define the edge weights, so long as $K = \\Omega(\\ln n/\\gamma)$ and $Kn = \\tilde\\Omega(\\ln n/\\gamma^2)$. The function computes a maximum-weight balanced cut of $G$, where the weight of a cut is the sum of the weights across all edges in the cut. This result demonstrates a nice property in the high-dimensional feature space: one can trade off the number of features that are required with the size of the sample to accomplish certain tasks like clustering.", "source": "arxiv/ml"}
{"id": "arxiv:81", "title": "Bayesian Nonlinear Principal Component Analysis Using Random Fields", "text": "We propose a novel model for nonlinear dimension reduction motivated by the probabilistic formulation of principal component analysis. Nonlinearity is achieved by specifying different transformation matrices at different locations of the latent space and smoothing the transformation using a Markov random field type prior. The computation is made feasible by the recent advances in sampling from von Mises-Fisher distributions.", "source": "arxiv/ml"}
{"id": "arxiv:82", "title": "A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization", "text": "We present a general approach for collaborative filtering (CF) using spectral regularization to learn linear operators from \"users\" to the \"objects\" they rate. Recent low-rank type matrix completion approaches to CF are shown to be special cases. However, unlike existing regularization based CF methods, our approach can be used to also incorporate information such as attributes of the users or the objects -- a limitation of existing regularization based CF methods. We then provide novel representer theorems that we use to develop new estimation methods. We provide learning algorithms based on low-rank decompositions, and test them on a standard CF dataset. The experiments indicate the advantages of generalizing the existing regularization based CF methods to incorporate related information about users and objects. Finally, we show that certain multi-task learning methods can be also seen as special cases of our proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:83", "title": "Combining Expert Advice Efficiently", "text": "We show how models for prediction with expert advice can be defined concisely and clearly using hidden Markov models (HMMs); standard HMM algorithms can then be used to efficiently calculate, among other things, how the expert predictions should be weighted according to the model. We cast many existing models as HMMs and recover the best known running times in each case. We also describe two new models: the switch distribution, which was recently developed to improve Bayesian/Minimum Description Length model selection, and a new generalisation of the fixed share algorithm based on run-length coding. We give loss bounds for all models and shed new light on their relationships.", "source": "arxiv/ml"}
{"id": "arxiv:84", "title": "A Radar-Shaped Statistic for Testing and Visualizing Uniformity Properties in Computer Experiments", "text": "In the study of computer codes, filling space as uniformly as possible is important to describe the complexity of the investigated phenomenon. However, this property is not conserved by reducing the dimension. Some numeric experiment designs are conceived in this sense as Latin hypercubes or orthogonal arrays, but they consider only the projections onto the axes or the coordinate planes. In this article we introduce a statistic which allows studying the good distribution of points according to all 1-dimensional projections. By angularly scanning the domain, we obtain a radar type representation, allowing the uniformity defects of a design to be identified with respect to its projections onto straight lines. The advantages of this new tool are demonstrated on usual examples of space-filling designs (SFD) and a global statistic independent of the angle of rotation is studied.", "source": "arxiv/ml"}
{"id": "arxiv:85", "title": "Compressed Counting", "text": "Counting is among the most fundamental operations in computing. For example, counting the pth frequency moment has been a very active area of research, in theoretical computer science, databases, and data mining. When p=1, the task (i.e., counting the sum) can be accomplished using a simple counter. Compressed Counting (CC) is proposed for efficiently computing the pth frequency moment of a data stream signal A_t, where 0<p<=2. CC is applicable if the streaming data follow the Turnstile model, with the restriction that at the time t for the evaluation, A_t[i]>= 0, which includes the strict Turnstile model as a special case. For natural data streams encountered in practice, this restriction is minor. The underly technique for CC is what we call skewed stable random projections, which captures the intuition that, when p=1 a simple counter suffices, and when p = 1+/\\Delta with small \\Delta, the sample complexity of a counter system should be low (continuously as a function of \\Delta). We show at small \\Delta the sample complexity (number of projections) k = O(1/\\epsilon) instead of O(1/\\epsilon^2). Compressed Counting can serve a basic building block for other tasks in statistics and computing, for example, estimation entropies of data streams, parameter estimations using the method of moments and maximum likelihood. Finally, another contribution is an algorithm for approximating the logarithmic norm, \\sum_{i=1}^D\\log A_t[i], and logarithmic distance. The logarithmic distance is useful in machine learning practice with heavy-tailed data.", "source": "arxiv/ml"}
{"id": "arxiv:86", "title": "Sign Language Tutoring Tool", "text": "In this project, we have developed a sign language tutor that lets users learn isolated signs by watching recorded videos and by trying the same signs. The system records the user's video and analyses it. If the sign is recognized, both verbal and animated feedback is given to the user. The system is able to recognize complex signs that involve both hand gestures and head movements and expressions. Our performance tests yield a 99% recognition rate on signs involving only manual gestures and 85% recognition rate on signs that involve both manual and non manual components, such as head movement and facial expressions.", "source": "arxiv/ml"}
{"id": "arxiv:87", "title": "Pure Exploration for Multi-Armed Bandit Problems", "text": "We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of forecasters that perform an on-line exploration of the arms. These forecasters are assessed in terms of their simple regret, a regret notion that captures the fact that exploration is only constrained by the number of available rounds (not necessarily known in advance), in contrast to the case when the cumulative regret is considered and when exploitation needs to be performed at the same time. We believe that this performance criterion is suited to situations when the cost of pulling an arm is expressed in terms of resources rather than rewards. We discuss the links between the simple and the cumulative regret. One of the main results in the case of a finite number of arms is a general lower bound on the simple regret of a forecaster in terms of its cumulative regret: the smaller the latter, the larger the former. Keeping this result in mind, we then exhibit upper bounds on the simple regret of some forecasters. The paper ends with a study devoted to continuous-armed bandit problems; we show that the simple regret can be minimized with respect to a family of probability distributions if and only if the cumulative regret can be minimized for it. Based on this equivalence, we are able to prove that the separable metric spaces are exactly the metric spaces on which these regrets can be minimized with respect to the family of all probability distributions with continuous mean-payoff functions.", "source": "arxiv/ml"}
{"id": "arxiv:88", "title": "Knowledge Technologies", "text": "Several technologies are emerging that provide new ways to capture, store, present and use knowledge. This book is the first to provide a comprehensive introduction to five of the most important of these technologies: Knowledge Engineering, Knowledge Based Engineering, Knowledge Webs, Ontologies and Semantic Webs. For each of these, answers are given to a number of key questions (What is it? How does it operate? How is a system developed? What can it be used for? What tools are available? What are the main issues?). The book is aimed at students, researchers and practitioners interested in Knowledge Management, Artificial Intelligence, Design Engineering and Web Technologies. During the 1990s, Nick worked at the University of Nottingham on the application of AI techniques to knowledge management and on various knowledge acquisition projects to develop expert systems for military applications. In 1999, he joined Epistemics where he worked on numerous knowledge projects and helped establish knowledge management programmes at large organisations in the engineering, technology and legal sectors. He is author of the book \"Knowledge Acquisition in Practice\", which describes a step-by-step procedure for acquiring and implementing expertise. He maintains strong links with leading research organisations working on knowledge technologies, such as knowledge-based engineering, ontologies and semantic technologies.", "source": "arxiv/ml"}
{"id": "arxiv:89", "title": "What Can We Learn Privately?", "text": "Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept classes can be learned privately, namely, by an algorithm whose output does not depend too heavily on any one input or specific training example? More precisely, we investigate learning algorithms that satisfy differential privacy, a notion that provides strong confidentiality guarantees in contexts where aggregate information is released about a database containing sensitive information about individuals. We demonstrate that, ignoring computational constraints, it is possible to privately agnostically learn any concept class using a sample size approximately logarithmic in the cardinality of the concept class. Therefore, almost anything learnable is learnable privately: specifically, if a concept class is learnable by a (non-private) algorithm with polynomial sample complexity and output size, then it can be learned privately using a polynomial number of samples. We also present a computationally efficient private PAC learner for the class of parity functions. Local (or randomized response) algorithms are a practical class of private algorithms that have received extensive investigation. We provide a precise characterization of local private learning algorithms. We show that a concept class is learnable by a local algorithm if and only if it is learnable in the statistical query (SQ) model. Finally, we present a separation between the power of interactive and noninteractive local learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:90", "title": "Privacy Preserving ID3 over Horizontally, Vertically and Grid Partitioned Data", "text": "We consider privacy preserving decision tree induction via ID3 in the case where the training data is horizontally or vertically distributed. Furthermore, we consider the same problem in the case where the data is both horizontally and vertically distributed, a situation we refer to as grid partitioned data. We give an algorithm for privacy preserving ID3 over horizontally partitioned data involving more than two parties. For grid partitioned data, we discuss two different evaluation methods for preserving privacy ID3, namely, first merging horizontally and developing vertically or first merging vertically and next developing horizontally. Next to introducing privacy preserving data mining over grid-partitioned data, the main contribution of this paper is that we show, by means of a complexity analysis that the former evaluation method is the more efficient.", "source": "arxiv/ml"}
{"id": "arxiv:91", "title": "Figuring out Actors in Text Streams: Using Collocations to establish Incremental Mind-maps", "text": "The recognition, involvement, and description of main actors influences the story line of the whole text. This is of higher importance as the text per se represents a flow of words and expressions that once it is read it is lost. In this respect, the understanding of a text and moreover on how the actor exactly behaves is not only a major concern: as human beings try to store a given input on short-term memory while associating diverse aspects and actors with incidents, the following approach represents a virtual architecture, where collocations are concerned and taken as the associative completion of the actors' acting. Once that collocations are discovered, they become managed in separated memory blocks broken down by the actors. As for human beings, the memory blocks refer to associative mind-maps. We then present several priority functions to represent the actual temporal situation inside a mind-map to enable the user to reconstruct the recent events from the discovered temporal results.", "source": "arxiv/ml"}
{"id": "arxiv:92", "title": "Robustness and Regularization of Support Vector Machines", "text": "We consider regularized support vector machines (SVMs) and show that they are precisely equivalent to a new robust optimization formulation. We show that this equivalence of robust optimization and regularization has implications for both algorithms, and analysis. In terms of algorithms, the equivalence suggests more general SVM-like algorithms for classification that explicitly build in protection to noise, and at the same time control overfitting. On the analysis front, the equivalence of robustness and regularization, provides a robust optimization interpretation for the success of regularized SVMs. We use the this new robustness interpretation of SVMs to give a new proof of consistency of (kernelized) SVMs, thus establishing robustness as the reason regularized SVMs generalize well.", "source": "arxiv/ml"}
{"id": "arxiv:93", "title": "Recorded Step Directional Mutation for Faster Convergence", "text": "Two meta-evolutionary optimization strategies described in this paper accelerate the convergence of evolutionary programming algorithms while still retaining much of their ability to deal with multi-modal problems. The strategies, called directional mutation and recorded step in this paper, can operate independently but together they greatly enhance the ability of evolutionary programming algorithms to deal with fitness landscapes characterized by long narrow valleys. The directional mutation aspect of this combined method uses correlated meta-mutation but does not introduce a full covariance matrix. These new methods are thus much more economical in terms of storage for problems with high dimensionality. Additionally, directional mutation is rotationally invariant which is a substantial advantage over self-adaptive methods which use a single variance per coordinate for problems where the natural orientation of the problem is not oriented along the axes.", "source": "arxiv/ml"}
{"id": "arxiv:94", "title": "Support Vector Machine Classification with Indefinite Kernels", "text": "We propose a method for support vector machine classification using indefinite kernels. Instead of directly minimizing or stabilizing a nonconvex loss function, our algorithm simultaneously computes support vectors and a proxy kernel matrix used in forming the loss. This can be interpreted as a penalized kernel learning problem where indefinite kernel matrices are treated as a noisy observations of a true Mercer kernel. Our formulation keeps the problem convex and relatively large problems can be solved efficiently using the projected gradient or analytic center cutting plane methods. We compare the performance of our technique with other methods on several classic data sets.", "source": "arxiv/ml"}
{"id": "arxiv:95", "title": "A Unified Semi-Supervised Dimensionality Reduction Framework for Manifold Learning", "text": "We present a general framework of semi-supervised dimensionality reduction for manifold learning which naturally generalizes existing supervised and unsupervised learning frameworks which apply the spectral decomposition. Algorithms derived under our framework are able to employ both labeled and unlabeled examples and are able to handle complex problems where data form separate clusters of manifolds. Our framework offers simple views, explains relationships among existing frameworks and provides further extensions which can improve existing algorithms. Furthermore, a new semi-supervised kernelization framework called ``KPCA trick'' is proposed to handle non-linear problems.", "source": "arxiv/ml"}
{"id": "arxiv:96", "title": "Bolasso: model consistent Lasso estimation through the bootstrap", "text": "We consider the least-square linear regression problem with regularization by the l1-norm, a problem usually referred to as the Lasso. In this paper, we present a detailed asymptotic analysis of model consistency of the Lasso. For various decays of the regularization parameter, we compute asymptotic equivalents of the probability of correct model selection (i.e., variable selection). For a specific rate decay, we show that the Lasso selects all the variables that should enter the model with probability tending to one exponentially fast, while it selects all other variables with strictly positive probability. We show that this property implies that if we run the Lasso for several bootstrapped replications of a given sample, then intersecting the supports of the Lasso bootstrap estimates leads to consistent model selection. This novel variable selection algorithm, referred to as the Bolasso, is compared favorably to other linear regression methods on synthetic data and datasets from the UCI machine learning repository.", "source": "arxiv/ml"}
{"id": "arxiv:97", "title": "On Kernelization of Supervised Mahalanobis Distance Learners", "text": "This paper focuses on the problem of kernelizing an existing supervised Mahalanobis distance learner. The following features are included in the paper. Firstly, three popular learners, namely, \"neighborhood component analysis\", \"large margin nearest neighbors\" and \"discriminant neighborhood embedding\", which do not have kernel versions are kernelized in order to improve their classification performances. Secondly, an alternative kernelization framework called \"KPCA trick\" is presented. Implementing a learner in the new framework gains several advantages over the standard framework, e.g. no mathematical formulas and no reprogramming are required for a kernel implementation, the framework avoids troublesome problems such as singularity, etc. Thirdly, while the truths of representer theorems are just assumptions in previous papers related to ours, here, representer theorems are formally proven. The proofs validate both the kernel trick and the KPCA trick in the context of Mahalanobis distance learning. Fourthly, unlike previous works which always apply brute force methods to select a kernel, we investigate two approaches which can be efficiently adopted to construct an appropriate kernel for a given dataset. Finally, numerical results on various real-world datasets are presented.", "source": "arxiv/ml"}
{"id": "arxiv:98", "title": "Isotropic PCA and Affine-Invariant Clustering", "text": "We present a new algorithm for clustering points in R^n. The key property of the algorithm is that it is affine-invariant, i.e., it produces the same partition for any affine transformation of the input. It has strong guarantees when the input is drawn from a mixture model. For a mixture of two arbitrary Gaussians, the algorithm correctly classifies the sample assuming only that the two components are separable by a hyperplane, i.e., there exists a halfspace that contains most of one Gaussian and almost none of the other in probability mass. This is nearly the best possible, improving known results substantially. For k > 2 components, the algorithm requires only that there be some (k-1)-dimensional subspace in which the emoverlap in every direction is small. Here we define overlap to be the ratio of the following two quantities: 1) the average squared distance between a point and the mean of its component, and 2) the average squared distance between a point and the mean of the mixture. The main result may also be stated in the language of linear discriminant analysis: if the standard Fisher discriminant is small enough, labels are not needed to estimate the optimal subspace for projection. Our main tools are isotropic transformation, spectral projection and a simple reweighting technique. We call this combination isotropic PCA.", "source": "arxiv/ml"}
{"id": "arxiv:99", "title": "Multiple Random Oracles Are Better Than One", "text": "We study the problem of learning k-juntas given access to examples drawn from a number of different product distributions. Thus we wish to learn a function f : {-1,1}^n -> {-1,1} that depends on k (unknown) coordinates. While the best known algorithms for the general problem of learning a k-junta require running time of n^k * poly(n,2^k), we show that given access to k different product distributions with biases separated by \\gamma>0, the functions may be learned in time poly(n,2^k,\\gamma^{-k}). More generally, given access to t <= k different product distributions, the functions may be learned in time n^{k/t} * poly(n,2^k,\\gamma^{-k}). Our techniques involve novel results in Fourier analysis relating Fourier expansions with respect to different biases and a generalization of Russo's formula.", "source": "arxiv/ml"}
{"id": "arxiv:100", "title": "Dependence Structure Estimation via Copula", "text": "Dependence strucuture estimation is one of the important problems in machine learning domain and has many applications in different scientific areas. In this paper, a theoretical framework for such estimation based on copula and copula entropy -- the probabilistic theory of representation and measurement of statistical dependence, is proposed. Graphical models are considered as a special case of the copula framework. A method of the framework for estimating maximum spanning copula is proposed. Due to copula, the method is irrelevant to the properties of individual variables, insensitive to outlier and able to deal with non-Gaussianity. Experiments on both simulated data and real dataset demonstrated the effectiveness of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:101", "title": "Introduction to Relational Networks for Classification", "text": "The use of computational intelligence techniques for classification has been used in numerous applications. This paper compares the use of a Multi Layer Perceptron Neural Network and a new Relational Network on classifying the HIV status of women at ante-natal clinics. The paper discusses the architecture of the relational network and its merits compared to a neural network and most other computational intelligence classifiers. Results gathered from the study indicate comparable classification accuracies as well as revealed relationships between data features in the classification data. Much higher classification accuracies are recommended for future research in the area of HIV classification as well as missing data estimation.", "source": "arxiv/ml"}
{"id": "arxiv:102", "title": "The Effect of Structural Diversity of an Ensemble of Classifiers on Classification Accuracy", "text": "This paper aims to showcase the measure of structural diversity of an ensemble of 9 classifiers and then map a relationship between this structural diversity and accuracy. The structural diversity was induced by having different architectures or structures of the classifiers The Genetical Algorithms (GA) were used to derive the relationship between diversity and the classification accuracy by evolving the classifiers and then picking 9 classifiers out on an ensemble of 60 classifiers. It was found that as the ensemble became diverse the accuracy improved. However at a certain diversity measure the accuracy began to drop. The Kohavi-Wolpert variance method is used to measure the diversity of the ensemble. A method of voting is used to aggregate the results from each classifier. The lowest error was observed at a diversity measure of 0.16 with a mean square error of 0.274, when taking 0.2024 as maximum diversity measured. The parameters that were varied were: the number of hidden nodes, learning rate and the activation function.", "source": "arxiv/ml"}
{"id": "arxiv:103", "title": "A Quadratic Loss Multi-Class SVM", "text": "Using a support vector machine requires to set two types of hyperparameters: the soft margin parameter C and the parameters of the kernel. To perform this model selection task, the method of choice is cross-validation. Its leave-one-out variant is known to produce an estimator of the generalization error which is almost unbiased. Its major drawback rests in its time requirement. To overcome this difficulty, several upper bounds on the leave-one-out error of the pattern recognition SVM have been derived. Among those bounds, the most popular one is probably the radius-margin bound. It applies to the hard margin pattern recognition SVM, and by extension to the 2-norm SVM. In this report, we introduce a quadratic loss M-SVM, the M-SVM^2, as a direct extension of the 2-norm SVM to the multi-class case. For this machine, a generalized radius-margin bound is then established.", "source": "arxiv/ml"}
{"id": "arxiv:104", "title": "On Recovery of Sparse Signals via $\\ell_1$ Minimization", "text": "This article considers constrained $\\ell_1$ minimization methods for the recovery of high dimensional sparse signals in three settings: noiseless, bounded error and Gaussian noise. A unified and elementary treatment is given in these noise settings for two $\\ell_1$ minimization methods: the Dantzig selector and $\\ell_1$ minimization with an $\\ell_2$ constraint. The results of this paper improve the existing results in the literature by weakening the conditions and tightening the error bounds. The improvement on the conditions shows that signals with larger support can be recovered accurately. This paper also establishes connections between restricted isometry property and the mutual incoherence property. Some results of Candes, Romberg and Tao (2006) and Donoho, Elad, and Temlyakov (2006) are extended.", "source": "arxiv/ml"}
{"id": "arxiv:105", "title": "On-line Learning of an Unlearnable True Teacher through Mobile Ensemble Teachers", "text": "On-line learning of a hierarchical learning model is studied by a method from statistical mechanics. In our model a student of a simple perceptron learns from not a true teacher directly, but ensemble teachers who learn from the true teacher with a perceptron learning rule. Since the true teacher and the ensemble teachers are expressed as non-monotonic perceptron and simple ones, respectively, the ensemble teachers go around the unlearnable true teacher with the distance between them fixed in an asymptotic steady state. The generalization performance of the student is shown to exceed that of the ensemble teachers in a transient state, as was shown in similar ensemble-teachers models. Further, it is found that moving the ensemble teachers even in the steady state, in contrast to the fixed ensemble teachers, is efficient for the performance of the student.", "source": "arxiv/ml"}
{"id": "arxiv:106", "title": "Rollout Sampling Approximate Policy Iteration", "text": "Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.", "source": "arxiv/ml"}
{"id": "arxiv:107", "title": "An optimization problem on the sphere", "text": "We prove existence and uniqueness of the minimizer for the average geodesic distance to the points of a geodesically convex set on the sphere. This implies a corresponding existence and uniqueness result for an optimal algorithm for halfspace learning, when data and target functions are drawn from the uniform distribution.", "source": "arxiv/ml"}
{"id": "arxiv:108", "title": "A Kernel Method for the Two-Sample Problem", "text": "We propose a framework for analyzing and comparing distributions, allowing us to design statistical tests to determine if two samples are drawn from different distributions. Our test statistic is the largest difference in expectations over functions in the unit ball of a reproducing kernel Hilbert space (RKHS). We present two tests based on large deviation bounds for the test statistic, while a third is based on the asymptotic distribution of this statistic. The test statistic can be computed in quadratic time, although efficient linear time approximations are available. Several classical metrics on distributions are recovered when the function space used to compute the difference in expectations is allowed to be more general (eg. a Banach space). We apply our two-sample tests to a variety of problems, including attribute matching for databases using the Hungarian marriage method, where they perform strongly. Excellent performance is also obtained when comparing distributions over graphs, for which these are the first such tests.", "source": "arxiv/ml"}
{"id": "arxiv:109", "title": "The Margitron: A Generalised Perceptron with Margin", "text": "We identify the classical Perceptron algorithm with margin as a member of a broader family of large margin classifiers which we collectively call the Margitron. The Margitron, (despite its) sharing the same update rule with the Perceptron, is shown in an incremental setting to converge in a finite number of updates to solutions possessing any desirable fraction of the maximum margin. Experiments comparing the Margitron with decomposition SVMs on tasks involving linear kernels and 2-norm soft margin are also reported.", "source": "arxiv/ml"}
{"id": "arxiv:110", "title": "Sample Selection Bias Correction Theory", "text": "This paper presents a theoretical analysis of sample selection bias correction. The sample bias correction technique commonly used in machine learning consists of reweighting the cost of an error on each training point of a biased sample to more closely reflect the unbiased distribution. This relies on weights derived by various estimation techniques based on finite samples. We analyze the effect of an error in that estimation on the accuracy of the hypothesis returned by the learning algorithm for two estimation techniques: a cluster-based estimation technique and kernel mean matching. We also report the results of sample bias correction experiments with several data sets using these techniques. Our analysis is based on the novel concept of distributional stability which generalizes the existing concept of point-based stability. Much of our work and proof techniques can be used to analyze other importance weighting techniques and their effect on accuracy when using a distributionally stable algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:111", "title": "Learning Low-Density Separators", "text": "We define a novel, basic, unsupervised learning problem - learning the lowest density homogeneous hyperplane separator of an unknown probability distribution. This task is relevant to several problems in machine learning, such as semi-supervised learning and clustering stability. We investigate the question of existence of a universally consistent algorithm for this problem. We propose two natural learning paradigms and prove that, on input unlabeled random samples generated by any member of a rich family of distributions, they are guaranteed to converge to the optimal separator for that distribution. We complement this result by showing that no learning algorithm for our task can achieve uniform learning rates (that are independent of the data generating distribution).", "source": "arxiv/ml"}
{"id": "arxiv:112", "title": "From Data Topology to a Modular Classifier", "text": "This article describes an approach to designing a distributed and modular neural classifier. This approach introduces a new hierarchical clustering that enables one to determine reliable regions in the representation space by exploiting supervised information. A multilayer perceptron is then associated with each of these detected clusters and charged with recognizing elements of the associated cluster while rejecting all others. The obtained global classifier is comprised of a set of cooperating neural networks and completed by a K-nearest neighbor classifier charged with treating elements rejected by all the neural networks. Experimental results for the handwritten digit recognition problem and comparison with neural and statistical nonmodular classifiers are given.", "source": "arxiv/ml"}
{"id": "arxiv:113", "title": "Utilisation des grammaires probabilistes dans les t\\^aches de segmentation et d'annotation prosodique", "text": "Nous pr\\'esentons dans cette contribution une approche \\`a la fois symbolique et probabiliste permettant d'extraire l'information sur la segmentation du signal de parole \\`a partir d'information prosodique. Nous utilisons pour ce faire des grammaires probabilistes poss\\'edant une structure hi\\'erarchique minimale. La phase de construction des grammaires ainsi que leur pouvoir de pr\\'ediction sont \\'evalu\\'es qualitativement ainsi que quantitativement. ----- Methodologically oriented, the present work sketches an approach for prosodic information retrieval and speech segmentation, based on both symbolic and probabilistic information. We have recourse to probabilistic grammars, within which we implement a minimal hierarchical structure. Both the stages of probabilistic grammar building and its testing in prediction are explored and quantitatively and qualitatively evaluated.", "source": "arxiv/ml"}
{"id": "arxiv:114", "title": "Belief Propagation and Beyond for Particle Tracking", "text": "We describe a novel approach to statistical learning from particles tracked while moving in a random environment. The problem consists in inferring properties of the environment from recorded snapshots. We consider here the case of a fluid seeded with identical passive particles that diffuse and are advected by a flow. Our approach rests on efficient algorithms to estimate the weighted number of possible matchings among particles in two consecutive snapshots, the partition function of the underlying graphical model. The partition function is then maximized over the model parameters, namely diffusivity and velocity gradient. A Belief Propagation (BP) scheme is the backbone of our algorithm, providing accurate results for the flow parameters we want to learn. The BP estimate is additionally improved by incorporating Loop Series (LS) contributions. For the weighted matching problem, LS is compactly expressed as a Cauchy integral, accurately estimated by a saddle point approximation. Numerical experiments show that the quality of our improved BP algorithm is comparable to the one of a fully polynomial randomized approximation scheme, based on the Markov Chain Monte Carlo (MCMC) method, while the BP-based scheme is substantially faster than the MCMC scheme.", "source": "arxiv/ml"}
{"id": "arxiv:115", "title": "Decoding Beta-Decay Systematics: A Global Statistical Model for Beta^- Halflives", "text": "Statistical modeling of nuclear data provides a novel approach to nuclear systematics complementary to established theoretical and phenomenological approaches based on quantum theory. Continuing previous studies in which global statistical modeling is pursued within the general framework of machine learning theory, we implement advances in training algorithms designed to improved generalization, in application to the problem of reproducing and predicting the halflives of nuclear ground states that decay 100% by the beta^- mode. More specifically, fully-connected, multilayer feedforward artificial neural network models are developed using the Levenberg-Marquardt optimization algorithm together with Bayesian regularization and cross-validation. The predictive performance of models emerging from extensive computer experiments is compared with that of traditional microscopic and phenomenological models as well as with the performance of other learning systems, including earlier neural network models as well as the support vector machines recently applied to the same problem. In discussing the results, emphasis is placed on predictions for nuclei that are far from the stability line, and especially those involved in the r-process nucleosynthesis. It is found that the new statistical models can match or even surpass the predictive performance of conventional models for beta-decay systematics and accordingly should provide a valuable additional tool for exploring the expanding nuclear landscape.", "source": "arxiv/ml"}
{"id": "arxiv:116", "title": "Learning Graph Matching", "text": "As a fundamental problem in pattern recognition, graph matching has applications in a variety of fields, from computer vision to computational biology. In graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a correspondence between the nodes of different graphs. Many formulations of this problem can be cast in general as a quadratic assignment problem, where a linear term in the objective function encodes node compatibility and a quadratic term encodes edge compatibility. The main research focus in this theme is about designing efficient algorithms for approximately solving the quadratic assignment problem, since it is NP-hard. In this paper we turn our attention to a different question: how to estimate compatibility functions such that the solution of the resulting graph matching problem best matches the expected solution that a human would manually provide. We present a method for learning graph matching: the training examples are pairs of graphs and the `labels' are matches between them. Our experimental results reveal that learning can substantially improve the performance of standard graph matching algorithms. In particular, we find that simple linear assignment with such a learning scheme outperforms Graduated Assignment with bistochastic normalisation, a state-of-the-art quadratic assignment relaxation algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:117", "title": "Statistical Learning of Arbitrary Computable Classifiers", "text": "Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest is the sample complexity: the number of samples required to learn to a specified level of accuracy. Here we consider learning over the set of all computable labeling functions. Since the VC-dimension is infinite and a priori (uniform) bounds on the number of samples are impossible, we let the learning algorithm decide when it has seen sufficient samples to have learned. We first show that learning in this setting is indeed possible, and develop a learning algorithm. We then show, however, that bounding sample complexity independently of the distribution is impossible. Notably, this impossibility is entirely due to the requirement that the learning algorithm be computable, and not due to the statistical nature of the problem.", "source": "arxiv/ml"}
{"id": "arxiv:118", "title": "Agnostically Learning Juntas from Random Walks", "text": "We prove that the class of functions g:{-1,+1}^n -> {-1,+1} that only depend on an unknown subset of k<<n variables (so-called k-juntas) is agnostically learnable from a random walk in time polynomial in n, 2^{k^2}, epsilon^{-k}, and log(1/delta). In other words, there is an algorithm with the claimed running time that, given epsilon, delta > 0 and access to a random walk on {-1,+1}^n labeled by an arbitrary function f:{-1,+1}^n -> {-1,+1}, finds with probability at least 1-delta a k-junta that is (opt(f)+epsilon)-close to f, where opt(f) denotes the distance of a closest k-junta to f.", "source": "arxiv/ml"}
{"id": "arxiv:119", "title": "On Sequences with Non-Learnable Subsequences", "text": "The remarkable results of Foster and Vohra was a starting point for a series of papers which show that any sequence of outcomes can be learned (with no prior knowledge) using some universal randomized forecasting algorithm and forecast-dependent checking rules. We show that for the class of all computationally efficient outcome-forecast-based checking rules, this property is violated. Moreover, we present a probabilistic algorithm generating with probability close to one a sequence with a subsequence which simultaneously miscalibrates all partially weakly computable randomized forecasting algorithms. %subsequences non-learnable by each randomized algorithm. According to the Dawid's prequential framework we consider partial recursive randomized algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:120", "title": "Prediction with Expert Advice in Games with Unbounded One-Step Gains", "text": "The games of prediction with expert advice are considered in this paper. We present some modification of Kalai and Vempala algorithm of following the perturbed leader for the case of unrestrictedly large one-step gains. We show that in general case the cumulative gain of any probabilistic prediction algorithm can be much worse than the gain of some expert of the pool. Nevertheless, we give the lower bound for this cumulative gain in general case and construct a universal algorithm which has the optimal performance; we also prove that in case when one-step gains of experts of the pool have ``limited deviations'' the performance of our algorithm is close to the performance of the best expert.", "source": "arxiv/ml"}
{"id": "arxiv:121", "title": "Computationally Efficient Estimators for Dimension Reductions Using Stable Random Projections", "text": "The method of stable random projections is a tool for efficiently computing the $l_\\alpha$ distances using low memory, where $0<\\alpha \\leq 2$ is a tuning parameter. The method boils down to a statistical estimation task and various estimators have been proposed, based on the geometric mean, the harmonic mean, and the fractional power etc. This study proposes the optimal quantile estimator, whose main operation is selecting, which is considerably less expensive than taking fractional power, the main operation in previous estimators. Our experiments report that the optimal quantile estimator is nearly one order of magnitude more computationally efficient than previous estimators. For large-scale learning tasks in which storing and computing pairwise distances is a serious bottleneck, this estimator should be desirable. In addition to its computational advantages, the optimal quantile estimator exhibits nice theoretical properties. It is more accurate than previous estimators when $\\alpha>1$. We derive its theoretical error bounds and establish the explicit (i.e., no hidden constants) sample complexity bound.", "source": "arxiv/ml"}
{"id": "arxiv:122", "title": "On Approximating the Lp Distances for p>2", "text": "Applications in machine learning and data mining require computing pairwise Lp distances in a data matrix A. For massive high-dimensional data, computing all pairwise distances of A can be infeasible. In fact, even storing A or all pairwise distances of A in the memory may be also infeasible. This paper proposes a simple method for p = 2, 4, 6, ... We first decompose the l_p (where p is even) distances into a sum of 2 marginal norms and p-1 ``inner products'' at different orders. Then we apply normal or sub-Gaussian random projections to approximate the resultant ``inner products,'' assuming that the marginal norms can be computed exactly by a linear scan. We propose two strategies for applying random projections. The basic projection strategy requires only one projection matrix but it is more difficult to analyze, while the alternative projection strategy requires p-1 projection matrices but its theoretical analysis is much easier. In terms of the accuracy, at least for p=4, the basic strategy is always more accurate than the alternative strategy if the data are non-negative, which is common in reality.", "source": "arxiv/ml"}
{"id": "arxiv:123", "title": "On empirical meaning of randomness with respect to a real parameter", "text": "We study the empirical meaning of randomness with respect to a family of probability distributions $P_\\theta$, where $\\theta$ is a real parameter, using algorithmic randomness theory. In the case when for a computable probability distribution $P_\\theta$ an effectively strongly consistent estimate exists, we show that the Levin's a priory semicomputable semimeasure of the set of all $P_\\theta$-random sequences is positive if and only if the parameter $\\theta$ is a computable real number. The different methods for generating ``meaningful'' $P_\\theta$-random sequences with noncomputable $\\theta$ are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:124", "title": "Sparse Online Learning via Truncated Gradient", "text": "We propose a general method called truncated gradient to induce sparsity in the weights of online learning algorithms with convex loss functions. This method has several essential properties: The degree of sparsity is continuous -- a parameter controls the rate of sparsification from no sparsification to total sparsification. The approach is theoretically motivated, and an instance of it can be regarded as an online counterpart of the popular $L_1$-regularization method in the batch setting. We prove that small rates of sparsification result in only small additional regret with respect to typical online learning guarantees. The approach works well empirically. We apply the approach to several datasets and find that for datasets with large numbers of features, substantial sparsity is discoverable.", "source": "arxiv/ml"}
{"id": "arxiv:125", "title": "Graph Kernels", "text": "We present a unified framework to study graph kernels, special cases of which include the random walk graph kernel \\citep{GaeFlaWro03,BorOngSchVisetal05}, marginalized graph kernel \\citep{KasTsuIno03,KasTsuIno04,MahUedAkuPeretal04}, and geometric kernel on graphs \\citep{Gaertner02}. Through extensions of linear algebra to Reproducing Kernel Hilbert Spaces (RKHS) and reduction to a Sylvester equation, we construct an algorithm that improves the time complexity of kernel computation from $O(n^6)$ to $O(n^3)$. When the graphs are sparse, conjugate gradient solvers or fixed-point iterations bring our algorithm into the sub-cubic domain. Experiments on graphs from bioinformatics and other application domains show that it is often more than a thousand times faster than previous approaches. We then explore connections between diffusion kernels \\citep{KonLaf02}, regularization on graphs \\citep{SmoKon03}, and graph kernels, and use these connections to propose new graph kernels. Finally, we show that rational kernels \\citep{CorHafMoh02,CorHafMoh03,CorHafMoh04} when specialized to graphs reduce to the random walk graph kernel.", "source": "arxiv/ml"}
{"id": "arxiv:126", "title": "Catching Up Faster by Switching Sooner: A Prequential Solution to the AIC-BIC Dilemma", "text": "Bayesian model averaging, model selection and its approximations such as BIC are generally statistically consistent, but sometimes achieve slower rates og convergence than other methods such as AIC and leave-one-out cross-validation. On the other hand, these other methods can br inconsistent. We identify the \"catch-up phenomenon\" as a novel explanation for the slow convergence of Bayesian methods. Based on this analysis we define the switch distribution, a modification of the Bayesian marginal distribution. We show that, under broad conditions,model selection and prediction based on the switch distribution is both consistent and achieves optimal convergence rates, thereby resolving the AIC-BIC dilemma. The method is practical; we give an efficient implementation. The switch distribution has a data compression interpretation, and can thus be viewed as a \"prequential\" or MDL method; yet it is different from the MDL methods that are usually considered in the literature. We compare the switch distribution to Bayes factor model selection and leave-one-out cross-validation.", "source": "arxiv/ml"}
{"id": "arxiv:127", "title": "Algorithm Selection as a Bandit Problem with Unbounded Losses", "text": "Algorithm selection is typically based on models of algorithm performance, learned during a separate offline training sequence, which can be prohibitively expensive. In recent work, we adopted an online approach, in which a performance model is iteratively updated and used to guide selection on a sequence of problem instances. The resulting exploration-exploitation trade-off was represented as a bandit problem with expert advice, using an existing solver for this game, but this required the setting of an arbitrary bound on algorithm runtimes, thus invalidating the optimal regret of the solver. In this paper, we propose a simpler framework for representing algorithm selection as a bandit problem, with partial information, and an unknown bound on losses. We adapt an existing solver to this game, proving a bound on its expected regret, which holds also for the resulting algorithm selection technique. We present preliminary experiments with a set of SAT solvers on a mixed SAT-UNSAT benchmark.", "source": "arxiv/ml"}
{"id": "arxiv:128", "title": "Multi-Instance Learning by Treating Instances As Non-I.I.D. Samples", "text": "Multi-instance learning attempts to learn from a training set consisting of labeled bags each containing many unlabeled instances. Previous studies typically treat the instances in the bags as independently and identically distributed. However, the instances in a bag are rarely independent, and therefore a better performance can be expected if the instances are treated in an non-i.i.d. way that exploits the relations among instances. In this paper, we propose a simple yet effective multi-instance learning method, which regards each bag as a graph and uses a specific kernel to distinguish the graphs by considering the features of the nodes as well as the features of the edges that convey some relations among instances. The effectiveness of the proposed method is validated by experiments.", "source": "arxiv/ml"}
{"id": "arxiv:129", "title": "Algorithms for Dynamic Spectrum Access with Learning for Cognitive Radio", "text": "We study the problem of dynamic spectrum sensing and access in cognitive radio systems as a partially observed Markov decision process (POMDP). A group of cognitive users cooperatively tries to exploit vacancies in primary (licensed) channels whose occupancies follow a Markovian evolution. We first consider the scenario where the cognitive users have perfect knowledge of the distribution of the signals they receive from the primary users. For this problem, we obtain a greedy channel selection and access policy that maximizes the instantaneous reward, while satisfying a constraint on the probability of interfering with licensed transmissions. We also derive an analytical universal upper bound on the performance of the optimal policy. Through simulation, we show that our scheme achieves good performance relative to the upper bound and improved performance relative to an existing scheme. We then consider the more practical scenario where the exact distribution of the signal from the primary is unknown. We assume a parametric model for the distribution and develop an algorithm that can learn the true distribution, still guaranteeing the constraint on the interference probability. We show that this algorithm outperforms the naive design that assumes a worst case value for the parameter. We also provide a proof for the convergence of the learning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:130", "title": "On Probability Distributions for Trees: Representations, Inference and Learning", "text": "We study probability distributions over free algebras of trees. Probability distributions can be seen as particular (formal power) tree series [Berstel et al 82, Esik et al 03], i.e. mappings from trees to a semiring K . A widely studied class of tree series is the class of rational (or recognizable) tree series which can be defined either in an algebraic way or by means of multiplicity tree automata. We argue that the algebraic representation is very convenient to model probability distributions over a free algebra of trees. First, as in the string case, the algebraic representation allows to design learning algorithms for the whole class of probability distributions defined by rational tree series. Note that learning algorithms for rational tree series correspond to learning algorithms for weighted tree automata where both the structure and the weights are learned. Second, the algebraic representation can be easily extended to deal with unranked trees (like XML trees where a symbol may have an unbounded number of children). Both properties are particularly relevant for applications: nondeterministic automata are required for the inference problem to be relevant (recall that Hidden Markov Models are equivalent to nondeterministic string automata); nowadays applications for Web Information Extraction, Web Services and document processing consider unranked trees.", "source": "arxiv/ml"}
{"id": "arxiv:131", "title": "Universal Denoising of Discrete-time Continuous-Amplitude Signals", "text": "We consider the problem of reconstructing a discrete-time signal (sequence) with continuous-valued components corrupted by a known memoryless channel. When performance is measured using a per-symbol loss function satisfying mild regularity conditions, we develop a sequence of denoisers that, although independent of the distribution of the underlying `clean' sequence, is universally optimal in the limit of large sequence length. This sequence of denoisers is universal in the sense of performing as well as any sliding window denoising scheme which may be optimized for the underlying clean signal. Our results are initially developed in a ``semi-stochastic'' setting, where the noiseless signal is an unknown individual sequence, and the only source of randomness is due to the channel noise. It is subsequently shown that in the fully stochastic setting, where the noiseless sequence is a stationary stochastic process, our schemes universally attain optimum performance. The proposed schemes draw from nonparametric density estimation techniques and are practically implementable. We demonstrate efficacy of the proposed schemes in denoising gray-scale images in the conventional additive white Gaussian noise setting, with additional promising results for less conventional noise distributions.", "source": "arxiv/ml"}
{"id": "arxiv:132", "title": "Positive factor networks: A graphical framework for modeling non-negative sequential data", "text": "We present a novel graphical framework for modeling non-negative sequential data with hierarchical structure. Our model corresponds to a network of coupled non-negative matrix factorization (NMF) modules, which we refer to as a positive factor network (PFN). The data model is linear, subject to non-negativity constraints, so that observation data consisting of an additive combination of individually representable observations is also representable by the network. This is a desirable property for modeling problems in computational auditory scene analysis, since distinct sound sources in the environment are often well-modeled as combining additively in the corresponding magnitude spectrogram. We propose inference and learning algorithms that leverage existing NMF algorithms and that are straightforward to implement. We present a target tracking example and provide results for synthetic observation data which serve to illustrate the interesting properties of PFNs and motivate their potential usefulness in applications such as music transcription, source separation, and speech recognition. We show how a target process characterized by a hierarchical state transition model can be represented as a PFN. Our results illustrate that a PFN which is defined in terms of a single target observation can then be used to effectively track the states of multiple simultaneous targets. Our results show that the quality of the inferred target states degrades gradually as the observation noise is increased. We also present results for an example in which meaningful hierarchical features are extracted from a spectrogram. Such a hierarchical representation could be useful for music transcription and source separation applications. We also propose a network for language modeling.", "source": "arxiv/ml"}
{"id": "arxiv:133", "title": "Mutual information is copula entropy", "text": "We prove that mutual information is actually negative copula entropy, based on which a method for mutual information estimation is proposed.", "source": "arxiv/ml"}
{"id": "arxiv:134", "title": "Building an interpretable fuzzy rule base from data using Orthogonal Least Squares Application to a depollution problem", "text": "In many fields where human understanding plays a crucial role, such as bioprocesses, the capacity of extracting knowledge from data is of critical importance. Within this framework, fuzzy learning methods, if properly used, can greatly help human experts. Amongst these methods, the aim of orthogonal transformations, which have been proven to be mathematically robust, is to build rules from a set of training data and to select the most important ones by linear regression or rank revealing techniques. The OLS algorithm is a good representative of those methods. However, it was originally designed so that it only cared about numerical performance. Thus, we propose some modifications of the original method to take interpretability into account. After recalling the original algorithm, this paper presents the changes made to the original method, then discusses some results obtained from benchmark problems. Finally, the algorithm is applied to a real-world fault detection depollution problem.", "source": "arxiv/ml"}
{"id": "arxiv:135", "title": "Multi-Instance Multi-Label Learning", "text": "In this paper, we propose the MIML (Multi-Instance Multi-Label learning) framework where an example is described by multiple instances and associated with multiple class labels. Compared to traditional learning frameworks, the MIML framework is more convenient and natural for representing complicated objects which have multiple semantic meanings. To learn from MIML examples, we propose the MimlBoost and MimlSvm algorithms based on a simple degeneration strategy, and experiments show that solving problems involving complicated objects with multiple semantic meanings in the MIML framework can lead to good performance. Considering that the degeneration process may lose information, we propose the D-MimlSvm algorithm which tackles MIML problems directly in a regularization framework. Moreover, we show that even when we do not have access to the real objects and thus cannot capture more information from real objects by using the MIML representation, MIML is still useful. We propose the InsDif and SubCod algorithms. InsDif works by transforming single-instances into the MIML representation for learning, while SubCod works by transforming single-label examples into the MIML representation for learning. Experiments show that in some tasks they are able to achieve better performance than learning the single-instances or single-label examples directly.", "source": "arxiv/ml"}
{"id": "arxiv:136", "title": "A game-theoretic version of Oakes' example for randomized forecasting", "text": "Using the game-theoretic framework for probability, Vovk and Shafer. have shown that it is always possible, using randomization, to make sequential probability forecasts that pass any countable set of well-behaved statistical tests. This result generalizes work by other authors, who consider only tests of calbration. We complement this result with a lower bound. We show that Vovk and Shafer's result is valid only when the forecasts are computed with unrestrictedly increasing degree of accuracy. When some level of discreteness is fixed, we present a game-theoretic generalization of Oakes' example for randomized forecasting that is a test failing any given method of deferministic forecasting; originally, this example was presented for deterministic calibration.", "source": "arxiv/ml"}
{"id": "arxiv:137", "title": "A Variational Inference Framework for Soft-In-Soft-Out Detection in Multiple Access Channels", "text": "We propose a unified framework for deriving and studying soft-in-soft-out (SISO) detection in interference channels using the concept of variational inference. The proposed framework may be used in multiple-access interference (MAI), inter-symbol interference (ISI), and multiple-input multiple-outpu (MIMO) channels. Without loss of generality, we will focus our attention on turbo multiuser detection, to facilitate a more concrete discussion. It is shown that, with some loss of optimality, variational inference avoids the exponential complexity of a posteriori probability (APP) detection by optimizing a closely-related, but much more manageable, objective function called variational free energy. In addition to its systematic appeal, there are several other advantages to this viewpoint. First of all, it provides unified and rigorous justifications for numerous detectors that were proposed on radically different grounds, and facilitates convenient joint detection and decoding (utilizing the turbo principle) when error-control codes are incorporated. Secondly, efficient joint parameter estimation and data detection is possible via the variational expectation maximization (EM) algorithm, such that the detrimental effect of inaccurate channel knowledge at the receiver may be dealt with systematically. We are also able to extend BPSK-based SISO detection schemes to arbitrary square QAM constellations in a rigorous manner using a variational argument.", "source": "arxiv/ml"}
{"id": "arxiv:138", "title": "A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations", "text": "Recognizing analogies, synonyms, antonyms, and associations appear to be four distinct tasks, requiring distinct NLP algorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four semantic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algorithms for each semantic phenomenon; we need to seek a unified approach. We propose to subsume a broad range of phenomena under analogies. To limit the scope of this paper, we restrict our attention to the subsumption of synonyms, antonyms, and associations. We introduce a supervised corpus-based machine learning algorithm for classifying analogous word pairs, and we show that it can solve multiple-choice SAT analogy questions, TOEFL synonym questions, ESL synonym-antonym questions, and similar-associated-both questions from cognitive psychology.", "source": "arxiv/ml"}
{"id": "arxiv:139", "title": "Quantum classification", "text": "Quantum classification is defined as the task of predicting the associated class of an unknown quantum state drawn from an ensemble of pure states given a finite number of copies of this state. By recasting the state discrimination problem within the framework of Machine Learning (ML), we can use the notion of learning reduction coming from classical ML to solve different variants of the classification task, such as the weighted binary and the multiclass versions.", "source": "arxiv/ml"}
{"id": "arxiv:140", "title": "Principal Graphs and Manifolds", "text": "In many physical, statistical, biological and other investigations it is desirable to approximate a system of points by objects of lower dimension and/or complexity. For this purpose, Karl Pearson invented principal component analysis in 1901 and found 'lines and planes of closest fit to system of points'. The famous k-means algorithm solves the approximation problem too, but by finite sets instead of lines and planes. This chapter gives a brief practical introduction into the methods of construction of general principal objects, i.e. objects embedded in the 'middle' of the multidimensional data set. As a basis, the unifying framework of mean squared distance approximation of finite datasets is selected. Principal graphs and manifolds are constructed as generalisations of principal components and k-means principal points. For this purpose, the family of expectation/maximisation algorithms with nearest generalisations is presented. Construction of principal graphs with controlled complexity is based on the graph grammar approach.", "source": "arxiv/ml"}
{"id": "arxiv:141", "title": "Entropy Concentration and the Empirical Coding Game", "text": "We give a characterization of Maximum Entropy/Minimum Relative Entropy inference by providing two `strong entropy concentration' theorems. These theorems unify and generalize Jaynes' `concentration phenomenon' and Van Campenhout and Cover's `conditional limit theorem'. The theorems characterize exactly in what sense a prior distribution Q conditioned on a given constraint, and the distribution P, minimizing the relative entropy D(P ||Q) over all distributions satisfying the constraint, are `close' to each other. We then apply our theorems to establish the relationship between entropy concentration and a game-theoretic characterization of Maximum Entropy Inference due to Topsoe and others.", "source": "arxiv/ml"}
{"id": "arxiv:142", "title": "A New Framework of Multistage Estimation", "text": "In this paper, we have established a unified framework of multistage parameter estimation. We demonstrate that a wide variety of statistical problems such as fixed-sample-size interval estimation, point estimation with error control, bounded-width confidence intervals, interval estimation following hypothesis testing, construction of confidence sequences, can be cast into the general framework of constructing sequential random intervals with prescribed coverage probabilities. We have developed exact methods for the construction of such sequential random intervals in the context of multistage sampling. In particular, we have established inclusion principle and coverage tuning techniques to control and adjust the coverage probabilities of sequential random intervals. We have obtained concrete sampling schemes which are unprecedentedly efficient in terms of sampling effort as compared to existing procedures.", "source": "arxiv/ml"}
{"id": "arxiv:143", "title": "Predictive Hypothesis Identification", "text": "While statistics focusses on hypothesis testing and on estimating (properties of) the true sampling distribution, in machine learning the performance of learning algorithms on future data is the primary issue. In this paper we bridge the gap with a general principle (PHI) that identifies hypotheses with best predictive performance. This includes predictive point and interval estimation, simple and composite hypothesis testing, (mixture) model selection, and others as special cases. For concrete instantiations we will recover well-known methods, variations thereof, and new ones. PHI nicely justifies, reconciles, and blends (a reparametrization invariant variation of) MAP, ML, MDL, and moment estimation. One particular feature of PHI is that it can genuinely deal with nested hypotheses.", "source": "arxiv/ml"}
{"id": "arxiv:144", "title": "Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning", "text": "For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations. This is usually done through the penalization of predictor functions by Euclidean or Hilbertian norms. In this paper, we explore penalizing by sparsity-inducing norms such as the l1-norm or the block l1-norm. We assume that the kernel decomposes into a large sum of individual basis kernels which can be embedded in a directed acyclic graph; we show that it is then possible to perform kernel selection through a hierarchical multiple kernel learning framework, in polynomial time in the number of selected kernels. This framework is naturally applied to non linear variable selection; our extensive simulations on synthetic datasets and datasets from the UCI repository show that efficiently exploring the large feature space through sparsity-inducing norms leads to state-of-the-art predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:145", "title": "When is there a representer theorem? Vector versus matrix regularizers", "text": "We consider a general class of regularization methods which learn a vector of parameters on the basis of linear measurements. It is well known that if the regularizer is a nondecreasing function of the inner product then the learned vector is a linear combination of the input data. This result, known as the {\\em representer theorem}, is at the basis of kernel-based methods in machine learning. In this paper, we prove the necessity of the above condition, thereby completing the characterization of kernel methods based on regularization. We further extend our analysis to regularization methods which learn a matrix, a problem which is motivated by the application to multi-task learning. In this context, we study a more general representer theorem, which holds for a larger class of regularizers. We provide a necessary and sufficient condition for these class of matrix regularizers and highlight them with some concrete examples of practical importance. Our analysis uses basic principles from matrix theory, especially the useful notion of matrix nondecreasing function.", "source": "arxiv/ml"}
{"id": "arxiv:146", "title": "Low congestion online routing and an improved mistake bound for online prediction of graph labeling", "text": "In this paper, we show a connection between a certain online low-congestion routing problem and an online prediction of graph labeling. More specifically, we prove that if there exists a routing scheme that guarantees a congestion of $\\alpha$ on any edge, there exists an online prediction algorithm with mistake bound $\\alpha$ times the cut size, which is the size of the cut induced by the label partitioning of graph vertices. With previous known bound of $O(\\log n)$ for $\\alpha$ for the routing problem on trees with $n$ vertices, we obtain an improved prediction algorithm for graphs with high effective resistance. In contrast to previous approaches that move the graph problem into problems in vector space using graph Laplacian and rely on the analysis of the perceptron algorithm, our proof are purely combinatorial. Further more, our approach directly generalizes to the case where labels are not binary.", "source": "arxiv/ml"}
{"id": "arxiv:147", "title": "Clustered Multi-Task Learning: A Convex Formulation", "text": "In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from the others. In the context of learning linear functions for supervised classification or regression, this can be achieved by including a priori information about the weight vectors associated with the tasks, and how they are expected to be related to each other. In this paper, we assume that tasks are clustered into groups, which are unknown beforehand, and that tasks within a group have similar weight vectors. We design a new spectral norm that encodes this a priori assumption, without the prior knowledge of the partition of tasks into groups, resulting in a new convex optimization formulation for multi-task learning. We show in simulations on synthetic examples and on the IEDB MHC-I binding dataset, that our approach outperforms well-known convex methods for multi-task learning, as well as related non convex methods dedicated to the same problem.", "source": "arxiv/ml"}
{"id": "arxiv:148", "title": "Algorithmic information theory", "text": "We introduce algorithmic information theory, also known as the theory of Kolmogorov complexity. We explain the main concepts of this quantitative approach to defining `information'. We discuss the extent to which Kolmogorov's and Shannon's information theory have a common purpose, and where they are fundamentally different. We indicate how recent developments within the theory allow one to formally distinguish between `structural' (meaningful) and `random' information as measured by the Kolmogorov structure function, which leads to a mathematical formalization of Occam's razor in inductive inference. We end by discussing some of the philosophical implications of the theory.", "source": "arxiv/ml"}
{"id": "arxiv:149", "title": "Predicting Abnormal Returns From News Using Text Classification", "text": "We show how text from news articles can be used to predict intraday price movements of financial assets using support vector machines. Multiple kernel learning is used to combine equity returns with text as predictive features to increase classification performance and we develop an analytic center cutting plane method to solve the kernel learning problem efficiently. We observe that while the direction of returns is not predictable using either text or returns, their size is, with text features producing significantly better performance than historical returns alone.", "source": "arxiv/ml"}
{"id": "arxiv:150", "title": "A New Framework of Multistage Hypothesis Tests", "text": "In this paper, we have established a general framework of multistage hypothesis tests which applies to arbitrarily many mutually exclusive and exhaustive composite hypotheses. Within the new framework, we have constructed specific multistage tests which rigorously control the risk of committing decision errors and are more efficient than previous tests in terms of average sample number and the number of sampling operations. Without truncation, the sample numbers of our testing plans are absolutely bounded.", "source": "arxiv/ml"}
{"id": "arxiv:151", "title": "Generalized Prediction Intervals for Arbitrary Distributed High-Dimensional Data", "text": "This paper generalizes the traditional statistical concept of prediction intervals for arbitrary probability density functions in high-dimensional feature spaces by introducing significance level distributions, which provides interval-independent probabilities for continuous random variables. The advantage of the transformation of a probability density function into a significance level distribution is that it enables one-class classification or outlier detection in a direct manner.", "source": "arxiv/ml"}
{"id": "arxiv:152", "title": "Robust Near-Isometric Matching via Structured Learning of Graphical Models", "text": "Models for near-rigid shape matching are typically based on distance-related features, in order to infer matches that are consistent with the isometric assumption. However, real shapes from image datasets, even when expected to be related by \"almost isometric\" transformations, are actually subject not only to noise but also, to some limited degree, to variations in appearance and scale. In this paper, we introduce a graphical model that parameterises appearance, distance, and angle features and we learn all of the involved parameters via structured prediction. The outcome is a model for near-rigid shape matching which is robust in the sense that it is able to capture the possibly limited but still important scale and appearance variations. Our experimental results reveal substantial improvements upon recent successful models, while maintaining similar running times.", "source": "arxiv/ml"}
{"id": "arxiv:153", "title": "Learning Hidden Markov Models using Non-Negative Matrix Factorization", "text": "The Baum-Welsh algorithm together with its derivatives and variations has been the main technique for learning Hidden Markov Models (HMM) from observational data. We present an HMM learning algorithm based on the non-negative matrix factorization (NMF) of higher order Markovian statistics that is structurally different from the Baum-Welsh and its associated approaches. The described algorithm supports estimation of the number of recurrent states of an HMM and iterates the non-negative matrix factorization (NMF) algorithm to improve the learned HMM parameters. Numerical examples are provided as well.", "source": "arxiv/ml"}
{"id": "arxiv:154", "title": "Surrogate Learning - An Approach for Semi-Supervised Classification", "text": "We consider the task of learning a classifier from the feature space $\\mathcal{X}$ to the set of classes $\\mathcal{Y} = \\{0, 1\\}$, when the features can be partitioned into class-conditionally independent feature sets $\\mathcal{X}_1$ and $\\mathcal{X}_2$. We show the surprising fact that the class-conditional independence can be used to represent the original learning task in terms of 1) learning a classifier from $\\mathcal{X}_2$ to $\\mathcal{X}_1$ and 2) learning the class-conditional distribution of the feature set $\\mathcal{X}_1$. This fact can be exploited for semi-supervised learning because the former task can be accomplished purely from unlabeled samples. We present experimental evaluation of the idea in two real world applications.", "source": "arxiv/ml"}
{"id": "arxiv:155", "title": "Multi-Armed Bandits in Metric Spaces", "text": "In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of trials so as to maximize the total payoff of the chosen strategies. While the performance of bandit algorithms with a small finite strategy set is quite well understood, bandit problems with large strategy sets are still a topic of very active investigation, motivated by practical applications such as online auctions and web advertisement. The goal of such research is to identify broad and natural classes of strategy sets and payoff functions which enable the design of efficient solutions. In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric. We refer to this problem as the \"Lipschitz MAB problem\". We present a complete solution for the multi-armed problem in this setting. That is, for every metric space (L,X) we define an isometry invariant which bounds from below the performance of Lipschitz MAB algorithms for X, and we present an algorithm which comes arbitrarily close to meeting this bound. Furthermore, our technique gives even better results for benign payoff functions.", "source": "arxiv/ml"}
{"id": "arxiv:156", "title": "Thresholded Basis Pursuit: An LP Algorithm for Achieving Optimal Support Recovery for Sparse and Approximately Sparse Signals from Noisy Random Measurements", "text": "In this paper we present a linear programming solution for sign pattern recovery of a sparse signal from noisy random projections of the signal. We consider two types of noise models, input noise, where noise enters before the random projection; and output noise, where noise enters after the random projection. Sign pattern recovery involves the estimation of sign pattern of a sparse signal. Our idea is to pretend that no noise exists and solve the noiseless $\\ell_1$ problem, namely, $\\min \\|\\beta\\|_1 ~ s.t. ~ y=G \\beta$ and quantizing the resulting solution. We show that the quantized solution perfectly reconstructs the sign pattern of a sufficiently sparse signal. Specifically, we show that the sign pattern of an arbitrary k-sparse, n-dimensional signal $x$ can be recovered with $SNR=\\Omega(\\log n)$ and measurements scaling as $m= \\Omega(k \\log{n/k})$ for all sparsity levels $k$ satisfying $0< k \\leq \\alpha n$, where $\\alpha$ is a sufficiently small positive constant. Surprisingly, this bound matches the optimal \\emph{Max-Likelihood} performance bounds in terms of $SNR$, required number of measurements, and admissible sparsity level in an order-wise sense. In contrast to our results, previous results based on LASSO and Max-Correlation techniques either assume significantly larger $SNR$, sublinear sparsity levels or restrictive assumptions on signal sets. Our proof technique is based on noisy perturbation of the noiseless $\\ell_1$ problem, in that, we estimate the maximum admissible noise level before sign pattern recovery fails.", "source": "arxiv/ml"}
{"id": "arxiv:157", "title": "Bias-Variance Techniques for Monte Carlo Optimization: Cross-validation for the CE Method", "text": "In this paper, we examine the CE method in the broad context of Monte Carlo Optimization (MCO) and Parametric Learning (PL), a type of machine learning. A well-known overarching principle used to improve the performance of many PL algorithms is the bias-variance tradeoff. This tradeoff has been used to improve PL algorithms ranging from Monte Carlo estimation of integrals, to linear estimation, to general statistical estimation. Moreover, as described by, MCO is very closely related to PL. Owing to this similarity, the bias-variance tradeoff affects MCO performance, just as it does PL performance. In this article, we exploit the bias-variance tradeoff to enhance the performance of MCO algorithms. We use the technique of cross-validation, a technique based on the bias-variance tradeoff, to significantly improve the performance of the Cross Entropy (CE) method, which is an MCO algorithm. In previous work we have confirmed that other PL techniques improve the perfomance of other MCO algorithms. We conclude that the many techniques pioneered in PL could be investigated as ways to improve MCO algorithms in general, and the CE method in particular.", "source": "arxiv/ml"}
{"id": "arxiv:158", "title": "Blind Cognitive MAC Protocols", "text": "We consider the design of cognitive Medium Access Control (MAC) protocols enabling an unlicensed (secondary) transmitter-receiver pair to communicate over the idle periods of a set of licensed channels, i.e., the primary network. The objective is to maximize data throughput while maintaining the synchronization between secondary users and avoiding interference with licensed (primary) users. No statistical information about the primary traffic is assumed to be available a-priori to the secondary user. We investigate two distinct sensing scenarios. In the first, the secondary transmitter is capable of sensing all the primary channels, whereas it senses one channel only in the second scenario. In both cases, we propose MAC protocols that efficiently learn the statistics of the primary traffic online. Our simulation results demonstrate that the proposed blind protocols asymptotically achieve the throughput obtained when prior knowledge of primary traffic statistics is available.", "source": "arxiv/ml"}
{"id": "arxiv:159", "title": "A Gaussian Belief Propagation Solver for Large Scale Support Vector Machines", "text": "Support vector machines (SVMs) are an extremely successful type of classification and regression algorithms. Building an SVM entails solving a constrained convex quadratic programming problem, which is quadratic in the number of training samples. We introduce an efficient parallel implementation of an support vector regression solver, based on the Gaussian Belief Propagation algorithm (GaBP). In this paper, we demonstrate that methods from the complex system domain could be utilized for performing efficient distributed computation. We compare the proposed algorithm to previously proposed distributed and single-node SVM solvers. Our comparison shows that the proposed algorithm is just as accurate as these solvers, while being significantly faster, especially for large datasets. We demonstrate scalability of the proposed algorithm to up to 1,024 computing nodes and hundreds of thousands of data points using an IBM Blue Gene supercomputer. As far as we know, our work is the largest parallel implementation of belief propagation ever done, demonstrating the applicability of this algorithm for large scale distributed computing systems.", "source": "arxiv/ml"}
{"id": "arxiv:160", "title": "Faster and better: a machine learning approach to corner detection", "text": "The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application. The repeatability is importand because the same scene viewed from different positions should yield features which correspond to the same real-world 3D locations [Schmid et al 2000]. The efficiency is important because this determines whether the detector combined with further processing can operate at frame rate. Three advances are described in this paper. First, we present a new heuristic for feature detection, and using machine learning we derive a feature detector from this which can fully process live PAL video using less than 5% of the available processing time. By comparison, most other detectors cannot even operate at frame rate (Harris detector 115%, SIFT 195%). Second, we generalize the detector, allowing it to be optimized for repeatability, with little loss of efficiency. Third, we carry out a rigorous comparison of corner detectors based on the above repeatability criterion applied to 3D scenes. We show that despite being principally constructed for speed, on these stringent tests, our heuristic detector significantly outperforms existing feature detectors. Finally, the comparison demonstrates that using machine learning produces significant improvements in repeatability, yielding a detector that is both very fast and very high quality.", "source": "arxiv/ml"}
{"id": "arxiv:161", "title": "A Simple Linear Ranking Algorithm Using Query Dependent Intercept Variables", "text": "The LETOR website contains three information retrieval datasets used as a benchmark for testing machine learning ideas for ranking. Algorithms participating in the challenge are required to assign score values to search results for a collection of queries, and are measured using standard IR ranking measures (NDCG, precision, MAP) that depend only the relative score-induced order of the results. Similarly to many of the ideas proposed in the participating algorithms, we train a linear classifier. In contrast with other participating algorithms, we define an additional free variable (intercept, or benchmark) for each query. This allows expressing the fact that results for different queries are incomparable for the purpose of determining relevance. The cost of this idea is the addition of relatively few nuisance parameters. Our approach is simple, and we used a standard logistic regression library to test it. The results beat the reported participating algorithms. Hence, it seems promising to combine our approach with other more complex ideas.", "source": "arxiv/ml"}
{"id": "arxiv:162", "title": "The many faces of optimism - Extended version", "text": "The exploration-exploitation dilemma has been an intriguing and unsolved problem within the framework of reinforcement learning. \"Optimism in the face of uncertainty\" and model building play central roles in advanced exploration methods. Here, we integrate several concepts and obtain a fast and simple algorithm. We show that the proposed algorithm finds a near-optimal policy in polynomial time, and give experimental evidence that it is robust and efficient compared to its ascendants.", "source": "arxiv/ml"}
{"id": "arxiv:163", "title": "The use of entropy to measure structural diversity", "text": "In this paper entropy based methods are compared and used to measure structural diversity of an ensemble of 21 classifiers. This measure is mostly applied in ecology, whereby species counts are used as a measure of diversity. The measures used were Shannon entropy, Simpsons and the Berger Parker diversity indexes. As the diversity indexes increased so did the accuracy of the ensemble. An ensemble dominated by classifiers with the same structure produced poor accuracy. Uncertainty rule from information theory was also used to further define diversity. Genetic algorithms were used to find the optimal ensemble by using the diversity indices as the cost function. The method of voting was used to aggregate the decisions.", "source": "arxiv/ml"}
{"id": "arxiv:164", "title": "A Minimum Relative Entropy Principle for Learning and Acting", "text": "This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is an agent that has been designed specifically for a particular environment. This adaptive control problem is formalized as the problem of minimizing the relative entropy of the adaptive agent from the expert that is most suitable for the unknown environment. If the agent is a passive observer, then the optimal solution is the well-known Bayesian predictor. However, if the agent is active, then its past actions need to be treated as causal interventions on the I/O stream rather than normal probability conditions. Here it is shown that the solution to this new variational problem is given by a stochastic controller called the Bayesian control rule, which implements adaptive behavior as a mixture of experts. Furthermore, it is shown that under mild assumptions, the Bayesian control rule converges to the control law of the most suitable expert.", "source": "arxiv/ml"}
{"id": "arxiv:165", "title": "Quantum reinforcement learning", "text": "The key approaches for machine learning, especially learning in unknown probabilistic environments are new representations and computation mechanisms. In this paper, a novel quantum reinforcement learning (QRL) method is proposed by combining quantum theory and reinforcement learning (RL). Inspired by the state superposition principle and quantum parallelism, a framework of value updating algorithm is introduced. The state (action) in traditional RL is identified as the eigen state (eigen action) in QRL. The state (action) set can be represented with a quantum superposition state and the eigen state (eigen action) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement. The probability of the eigen action is determined by the probability amplitude, which is parallelly updated according to rewards. Some related characteristics of QRL such as convergence, optimality and balancing between exploration and exploitation are also analyzed, which shows that this approach makes a good tradeoff between exploration and exploitation using the probability amplitude and can speed up learning through the quantum parallelism. To evaluate the performance and practicability of QRL, several simulated experiments are given and the results demonstrate the effectiveness and superiority of QRL algorithm for some complex problems. The present work is also an effective exploration on the application of quantum computation to artificial intelligence.", "source": "arxiv/ml"}
{"id": "arxiv:166", "title": "Efficient Exact Inference in Planar Ising Models", "text": "We give polynomial-time algorithms for the exact computation of lowest-energy (ground) states, worst margin violators, log partition functions, and marginal edge probabilities in certain binary undirected graphical models. Our approach provides an interesting alternative to the well-known graph cut paradigm in that it does not impose any submodularity constraints; instead we require planarity to establish a correspondence with perfect matchings (dimer coverings) in an expanded dual graph. We implement a unified framework while delegating complex but well-understood subproblems (planar embedding, maximum-weight perfect matching) to established algorithms for which efficient implementations are freely available. Unlike graph cut methods, we can perform penalized maximum-likelihood as well as maximum-margin parameter estimation in the associated conditional random fields (CRFs), and employ marginal posterior probabilities as well as maximum a posteriori (MAP) states for prediction. Maximum-margin CRF parameter estimation on image denoising and segmentation problems shows our approach to be efficient and effective. A C++ implementation is available from http://nic.schraudolph.org/isinf/", "source": "arxiv/ml"}
{"id": "arxiv:167", "title": "Learning Isometric Separation Maps", "text": "Maximum Variance Unfolding (MVU) and its variants have been very successful in embedding data-manifolds in lower dimensional spaces, often revealing the true intrinsic dimension. In this paper we show how to also incorporate supervised class information into an MVU-like method without breaking its convexity. We call this method the Isometric Separation Map and we show that the resulting kernel matrix can be used as a binary/multiclass Support Vector Machine-like method in a semi-supervised (transductive) framework. We also show that the method always finds a kernel matrix that linearly separates the training data exactly without projecting them in infinite dimensional spaces. In traditional SVMs we choose a kernel and hope that the data become linearly separable in the kernel space. In this paper we show how the hyperplane can be chosen ad-hoc and the kernel is trained so that data are always linearly separable. Comparisons with Large Margin SVMs show comparable performance.", "source": "arxiv/ml"}
{"id": "arxiv:168", "title": "A Novel Clustering Algorithm Based on a Modified Model of Random Walk", "text": "We introduce a modified model of random walk, and then develop two novel clustering algorithms based on it. In the algorithms, each data point in a dataset is considered as a particle which can move at random in space according to the preset rules in the modified model. Further, this data point may be also viewed as a local control subsystem, in which the controller adjusts its transition probability vector in terms of the feedbacks of all data points, and then its transition direction is identified by an event-generating function. Finally, the positions of all data points are updated. As they move in space, data points collect gradually and some separating parts emerge among them automatically. As a consequence, data points that belong to the same class are located at a same position, whereas those that belong to different classes are away from one another. Moreover, the experimental results have demonstrated that data points in the test datasets are clustered reasonably and efficiently, and the comparison with other algorithms also provides an indication of the effectiveness of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:169", "title": "A Theory of Truncated Inverse Sampling", "text": "In this paper, we have established a new framework of truncated inverse sampling for estimating mean values of non-negative random variables such as binomial, Poisson, hyper-geometrical, and bounded variables. We have derived explicit formulas and computational methods for designing sampling schemes to ensure prescribed levels of precision and confidence for point estimators. Moreover, we have developed interval estimation methods.", "source": "arxiv/ml"}
{"id": "arxiv:170", "title": "A branch-and-bound feature selection algorithm for U-shaped cost functions", "text": "This paper presents the formulation of a combinatorial optimization problem with the following characteristics: i.the search space is the power set of a finite set structured as a Boolean lattice; ii.the cost function forms a U-shaped curve when applied to any lattice chain. This formulation applies for feature selection in the context of pattern recognition. The known approaches for this problem are branch-and-bound algorithms and heuristics, that explore partially the search space. Branch-and-bound algorithms are equivalent to the full search, while heuristics are not. This paper presents a branch-and-bound algorithm that differs from the others known by exploring the lattice structure and the U-shaped chain curves of the search space. The main contribution of this paper is the architecture of this algorithm that is based on the representation and exploration of the search space by new lattice properties proven here. Several experiments, with well known public data, indicate the superiority of the proposed method to SFFS, which is a popular heuristic that gives good results in very short computational time. In all experiments, the proposed method got better or equal results in similar or even smaller computational time.", "source": "arxiv/ml"}
{"id": "arxiv:171", "title": "Temporal Difference Updating without a Learning Rate", "text": "We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating rule for discounted state value estimates. The resulting equation is similar to the standard equation for temporal difference learning with eligibility traces, so called TD(lambda), however it lacks the parameter alpha that specifies the learning rate. In the place of this free parameter there is now an equation for the learning rate that is specific to each state transition. We experimentally test this new learning rule against TD(lambda) and find that it offers superior performance in various settings. Finally, we make some preliminary investigations into how to extend our new temporal difference algorithm to reinforcement learning. To do this we combine our update equation with both Watkins' Q(lambda) and Sarsa(lambda) and find that it again offers superior performance without a learning rate parameter.", "source": "arxiv/ml"}
{"id": "arxiv:172", "title": "On the Possibility of Learning in Reactive Environments with Arbitrary Dependence", "text": "We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions.", "source": "arxiv/ml"}
{"id": "arxiv:173", "title": "Entropy, Perception, and Relativity", "text": "In this paper, I expand Shannon's definition of entropy into a new form of entropy that allows integration of information from different random events. Shannon's notion of entropy is a special case of my more general definition of entropy. I define probability using a so-called performance function, which is de facto an exponential distribution. Assuming that my general notion of entropy reflects the true uncertainty about a probabilistic event, I understand that our perceived uncertainty differs. I claim that our perception is the result of two opposing forces similar to the two famous antagonists in Chinese philosophy: Yin and Yang. Based on this idea, I show that our perceived uncertainty matches the true uncertainty in points determined by the golden ratio. I demonstrate that the well-known sigmoid function, which we typically employ in artificial neural networks as a non-linear threshold function, describes the actual performance. Furthermore, I provide a motivation for the time dilation in Einstein's Special Relativity, basically claiming that although time dilation conforms with our perception, it does not correspond to reality. At the end of the paper, I show how to apply this theoretical framework to practical applications. I present recognition rates for a pattern recognition problem, and also propose a network architecture that can take advantage of general entropy to solve complex decision problems.", "source": "arxiv/ml"}
{"id": "arxiv:174", "title": "Effect of Tuned Parameters on a LSA MCQ Answering Model", "text": "This paper presents the current state of a work in progress, whose objective is to better understand the effects of factors that significantly influence the performance of Latent Semantic Analysis (LSA). A difficult task, which consists in answering (French) biology Multiple Choice Questions, is used to test the semantic properties of the truncated singular space and to study the relative influence of main parameters. A dedicated software has been designed to fine tune the LSA semantic space for the Multiple Choice Questions task. With optimal parameters, the performances of our simple model are quite surprisingly equal or superior to those of 7th and 8th grades students. This indicates that semantic spaces were quite good despite their low dimensions and the small sizes of training data sets. Besides, we present an original entropy global weighting of answers' terms of each question of the Multiple Choice Questions which was necessary to achieve the model's success.", "source": "arxiv/ml"}
{"id": "arxiv:175", "title": "Adaptive Base Class Boost for Multi-class Classification", "text": "We develop the concept of ABC-Boost (Adaptive Base Class Boost) for multi-class classification and present ABC-MART, a concrete implementation of ABC-Boost. The original MART (Multiple Additive Regression Trees) algorithm has been very successful in large-scale applications. For binary classification, ABC-MART recovers MART. For multi-class classification, ABC-MART considerably improves MART, as evaluated on several public data sets.", "source": "arxiv/ml"}
{"id": "arxiv:176", "title": "Stability Bound for Stationary Phi-mixing and Beta-mixing Processes", "text": "Most generalization bounds in learning theory are based on some measure of the complexity of the hypothesis class used, independently of any algorithm. In contrast, the notion of algorithmic stability can be used to derive tight generalization bounds that are tailored to specific learning algorithms by exploiting their particular properties. However, as in much of learning theory, existing stability analyses and bounds apply only in the scenario where the samples are independently and identically distributed. In many machine learning applications, however, this assumption does not hold. The observations received by the learning algorithm often have some inherent temporal dependence. This paper studies the scenario where the observations are drawn from a stationary phi-mixing or beta-mixing sequence, a widely adopted assumption in the study of non-i.i.d. processes that implies a dependence between observations weakening over time. We prove novel and distinct stability-based generalization bounds for stationary phi-mixing and beta-mixing sequences. These bounds strictly generalize the bounds given in the i.i.d. case and apply to all stable learning algorithms, thereby extending the use of stability-bounds to non-i.i.d. scenarios. We also illustrate the application of our phi-mixing generalization bounds to general classes of learning algorithms, including Support Vector Regression, Kernel Ridge Regression, and Support Vector Machines, and many other kernel regularization-based and relative entropy-based regularization algorithms. These novel bounds can thus be viewed as the first theoretical basis for the use of these algorithms in non-i.i.d. scenarios.", "source": "arxiv/ml"}
{"id": "arxiv:177", "title": "Robust Regression and Lasso", "text": "Lasso, or $\\ell^1$ regularized least squares, has been explored extensively for its remarkable sparsity properties. It is shown in this paper that the solution to Lasso, in addition to its sparsity, has robustness properties: it is the solution to a robust optimization problem. This has two important consequences. First, robustness provides a connection of the regularizer to a physical property, namely, protection from noise. This allows a principled selection of the regularizer, and in particular, generalizations of Lasso that also yield convex optimization problems are obtained by considering different uncertainty sets. Secondly, robustness can itself be used as an avenue to exploring different properties of the solution. In particular, it is shown that robustness of the solution explains why the solution is sparse. The analysis as well as the specific results obtained differ from standard sparsity results, providing different geometric intuition. Furthermore, it is shown that the robust optimization formulation is related to kernel density estimation, and based on this approach, a proof that Lasso is consistent is given using robustness directly. Finally, a theorem saying that sparsity and algorithmic stability contradict each other, and hence Lasso is not stable, is presented.", "source": "arxiv/ml"}
{"id": "arxiv:178", "title": "Land Cover Mapping Using Ensemble Feature Selection Methods", "text": "Ensemble classification is an emerging approach to land cover mapping whereby the final classification output is a result of a consensus of classifiers. Intuitively, an ensemble system should consist of base classifiers which are diverse i.e. classifiers whose decision boundaries err differently. In this paper ensemble feature selection is used to impose diversity in ensembles. The features of the constituent base classifiers for each ensemble were created through an exhaustive search algorithm using different separability indices. For each ensemble, the classification accuracy was derived as well as a diversity measure purported to give a measure of the inensemble diversity. The correlation between ensemble classification accuracy and diversity measure was determined to establish the interplay between the two variables. From the findings of this paper, diversity measures as currently formulated do not provide an adequate means upon which to constitute ensembles for land cover mapping.", "source": "arxiv/ml"}
{"id": "arxiv:179", "title": "A Spectral Algorithm for Learning Hidden Markov Models", "text": "Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computationally hard (under cryptographic assumptions), and practitioners typically resort to search heuristics which suffer from the usual local optima issues. We prove that under a natural separation condition (bounds on the smallest singular value of the HMM parameters), there is an efficient and provably correct algorithm for learning HMMs. The sample complexity of the algorithm does not explicitly depend on the number of distinct (discrete) observations---it implicitly depends on this quantity through spectral properties of the underlying HMM. This makes the algorithm particularly applicable to settings with a large number of observations, such as those in natural language processing where the space of observation is sometimes the words in a language. The algorithm is also simple, employing only a singular value decomposition and matrix multiplications.", "source": "arxiv/ml"}
{"id": "arxiv:180", "title": "Learning Class-Level Bayes Nets for Relational Data", "text": "Many databases store data in relational format, with different types of entities and information about links between the entities. The field of statistical-relational learning (SRL) has developed a number of new statistical models for such data. In this paper we focus on learning class-level or first-order dependencies, which model the general database statistics over attributes of linked objects and links (e.g., the percentage of A grades given in computer science classes). Class-level statistical relationships are important in themselves, and they support applications like policy making, strategic planning, and query optimization. Most current SRL methods find class-level dependencies, but their main task is to support instance-level predictions about the attributes or links of specific entities. We focus only on class-level prediction, and describe algorithms for learning class-level models that are orders of magnitude faster for this task. Our algorithms learn Bayes nets with relational structure, leveraging the efficiency of single-table nonrelational Bayes net learners. An evaluation of our methods on three data sets shows that they are computationally feasible for realistic table sizes, and that the learned structures represent the statistical information in the databases well. After learning compiles the database statistics into a Bayes net, querying these statistics via Bayes net inference is faster than with SQL queries, and does not depend on the size of the database.", "source": "arxiv/ml"}
{"id": "arxiv:181", "title": "k-means requires exponentially many iterations even in the plane", "text": "The k-means algorithm is a well-known method for partitioning n points that lie in the d-dimensional space into k clusters. Its main features are simplicity and speed in practice. Theoretically, however, the best known upper bound on its running time (i.e. O(n^{kd})) can be exponential in the number of points. Recently, Arthur and Vassilvitskii [3] showed a super-polynomial worst-case analysis, improving the best known lower bound from \\Omega(n) to 2^{\\Omega(\\sqrt{n})} with a construction in d=\\Omega(\\sqrt{n}) dimensions. In [3] they also conjectured the existence of superpolynomial lower bounds for any d >= 2. Our contribution is twofold: we prove this conjecture and we improve the lower bound, by presenting a simple construction in the plane that leads to the exponential lower bound 2^{\\Omega(n)}.", "source": "arxiv/ml"}
{"id": "arxiv:182", "title": "Approximation Algorithms for Bregman Co-clustering and Tensor Clustering", "text": "In the past few years powerful generalizations to the Euclidean k-means problem have been made, such as Bregman clustering [7], co-clustering (i.e., simultaneous clustering of rows and columns of an input matrix) [9,18], and tensor clustering [8,34]. Like k-means, these more general problems also suffer from the NP-hardness of the associated optimization. Researchers have developed approximation algorithms of varying degrees of sophistication for k-means, k-medians, and more recently also for Bregman clustering [2]. However, there seem to be no approximation algorithms for Bregman co- and tensor clustering. In this paper we derive the first (to our knowledge) guaranteed methods for these increasingly important clustering settings. Going beyond Bregman divergences, we also prove an approximation factor for tensor clustering with arbitrary separable metrics. Through extensive experiments we evaluate the characteristics of our method, and show that it also has practical impact.", "source": "arxiv/ml"}
{"id": "arxiv:183", "title": "A Novel Clustering Algorithm Based on Quantum Games", "text": "Enormous successes have been made by quantum algorithms during the last decade. In this paper, we combine the quantum game with the problem of data clustering, and then develop a quantum-game-based clustering algorithm, in which data points in a dataset are considered as players who can make decisions and implement quantum strategies in quantum games. After each round of a quantum game, each player's expected payoff is calculated. Later, he uses a link-removing-and-rewiring (LRR) function to change his neighbors and adjust the strength of links connecting to them in order to maximize his payoff. Further, algorithms are discussed and analyzed in two cases of strategies, two payoff matrixes and two LRR functions. Consequently, the simulation results have demonstrated that data points in datasets are clustered reasonably and efficiently, and the clustering algorithms have fast rates of convergence. Moreover, the comparison with other algorithms also provides an indication of the effectiveness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:184", "title": "Decision trees are PAC-learnable from most product distributions: a smoothed analysis", "text": "We consider the problem of PAC-learning decision trees, i.e., learning a decision tree over the n-dimensional hypercube from independent random labeled examples. Despite significant effort, no polynomial-time algorithm is known for learning polynomial-sized decision trees (even trees of any super-constant size), even when examples are assumed to be drawn from the uniform distribution on {0,1}^n. We give an algorithm that learns arbitrary polynomial-sized decision trees for {\\em most product distributions}. In particular, consider a random product distribution where the bias of each bit is chosen independently and uniformly from, say, [.49,.51]. Then with high probability over the parameters of the product distribution and the random examples drawn from it, the algorithm will learn any tree. More generally, in the spirit of smoothed analysis, we consider an arbitrary product distribution whose parameters are specified only up to a [-c,c] accuracy (perturbation), for an arbitrarily small positive constant c.", "source": "arxiv/ml"}
{"id": "arxiv:185", "title": "Uncovering protein interaction in abstracts and text using a novel linear model and word proximity networks", "text": "We participated in three of the protein-protein interaction subtasks of the Second BioCreative Challenge: classification of abstracts relevant for protein-protein interaction (IAS), discovery of protein pairs (IPS) and text passages characterizing protein interaction (ISS) in full text documents. We approached the abstract classification task with a novel, lightweight linear model inspired by spam-detection techniques, as well as an uncertainty-based integration scheme. We also used a Support Vector Machine and the Singular Value Decomposition on the same features for comparison purposes. Our approach to the full text subtasks (protein pair and passage identification) includes a feature expansion method based on word-proximity networks. Our approach to the abstract classification task (IAS) was among the top submissions for this task in terms of the measures of performance used in the challenge evaluation (accuracy, F-score and AUC). We also report on a web-tool we produced using our approach: the Protein Interaction Abstract Relevance Evaluator (PIARE). Our approach to the full text tasks resulted in one of the highest recall rates as well as mean reciprocal rank of correct passages. Our approach to abstract classification shows that a simple linear model, using relatively few features, is capable of generalizing and uncovering the conceptual nature of protein-protein interaction from the bibliome. Since the novel approach is based on a very lightweight linear model, it can be easily ported and applied to similar problems. In full text problems, the expansion of word features with word-proximity networks is shown to be useful, though the need for some improvements is discussed.", "source": "arxiv/ml"}
{"id": "arxiv:186", "title": "Decomposition Principles and Online Learning in Cross-Layer Optimization for Delay-Sensitive Applications", "text": "In this paper, we propose a general cross-layer optimization framework in which we explicitly consider both the heterogeneous and dynamically changing characteristics of delay-sensitive applications and the underlying time-varying network conditions. We consider both the independently decodable data units (DUs, e.g. packets) and the interdependent DUs whose dependencies are captured by a directed acyclic graph (DAG). We first formulate the cross-layer design as a non-linear constrained optimization problem by assuming complete knowledge of the application characteristics and the underlying network conditions. The constrained cross-layer optimization is decomposed into several cross-layer optimization subproblems for each DU and two master problems. The proposed decomposition method determines the necessary message exchanges between layers for achieving the optimal cross-layer solution. However, the attributes (e.g. distortion impact, delay deadline etc) of future DUs as well as the network conditions are often unknown in the considered real-time applications. The impact of current cross-layer actions on the future DUs can be characterized by a state-value function in the Markov decision process (MDP) framework. Based on the dynamic programming solution to the MDP, we develop a low-complexity cross-layer optimization algorithm using online learning for each DU transmission. This online algorithm can be implemented in real-time in order to cope with unknown source characteristics, network dynamics and resource constraints. Our numerical results demonstrate the efficiency of the proposed online algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:187", "title": "A Novel Clustering Algorithm Based on Quantum Random Walk", "text": "The enormous successes have been made by quantum algorithms during the last decade. In this paper, we combine the quantum random walk (QRW) with the problem of data clustering, and develop two clustering algorithms based on the one dimensional QRW. Then, the probability distributions on the positions induced by QRW in these algorithms are investigated, which also indicates the possibility of obtaining better results. Consequently, the experimental results have demonstrated that data points in datasets are clustered reasonably and efficiently, and the clustering algorithms are of fast rates of convergence. Moreover, the comparison with other algorithms also provides an indication of the effectiveness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:188", "title": "Convex Sparse Matrix Factorizations", "text": "We present a convex formulation of dictionary learning for sparse signal decomposition. Convexity is obtained by replacing the usual explicit upper bound on the dictionary size by a convex rank-reducing term similar to the trace norm. In particular, our formulation introduces an explicit trade-off between size and sparsity of the decomposition of rectangular matrices. Using a large set of synthetic examples, we compare the estimation abilities of the convex and non-convex approaches, showing that while the convex formulation has a single local minimum, this may lead in some cases to performance which is inferior to the local minima of the non-convex formulation.", "source": "arxiv/ml"}
{"id": "arxiv:189", "title": "Characterizing Truthful Multi-Armed Bandit Mechanisms", "text": "We consider a multi-round auction setting motivated by pay-per-click auctions for Internet advertising. In each round the auctioneer selects an advertiser and shows her ad, which is then either clicked or not. An advertiser derives value from clicks; the value of a click is her private information. Initially, neither the auctioneer nor the advertisers have any information about the likelihood of clicks on the advertisements. The auctioneer's goal is to design a (dominant strategies) truthful mechanism that (approximately) maximizes the social welfare. If the advertisers bid their true private values, our problem is equivalent to the \"multi-armed bandit problem\", and thus can be viewed as a strategic version of the latter. In particular, for both problems the quality of an algorithm can be characterized by \"regret\", the difference in social welfare between the algorithm and the benchmark which always selects the same \"best\" advertisement. We investigate how the design of multi-armed bandit algorithms is affected by the restriction that the resulting mechanism must be truthful. We find that truthful mechanisms have certain strong structural properties -- essentially, they must separate exploration from exploitation -- and they incur much higher regret than the optimal multi-armed bandit algorithms. Moreover, we provide a truthful mechanism which (essentially) matches our lower bound on regret.", "source": "arxiv/ml"}
{"id": "arxiv:190", "title": "Feature Selection By KDDA For SVM-Based MultiView Face Recognition", "text": "Applications such as face recognition that deal with high-dimensional data need a mapping technique that introduces representation of low-dimensional features with enhanced discriminatory power and a proper classifier, able to classify those complex features. Most of traditional Linear Discriminant Analysis suffer from the disadvantage that their optimality criteria are not directly related to the classification ability of the obtained feature representation. Moreover, their classification accuracy is affected by the \"small sample size\" problem which is often encountered in FR tasks. In this short paper, we combine nonlinear kernel based mapping of data called KDDA with Support Vector machine classifier to deal with both of the shortcomings in an efficient and cost effective manner. The proposed here method is compared, in terms of classification accuracy, to other commonly used FR methods on UMIST face database. Results indicate that the performance of the proposed method is overall superior to those of traditional FR approaches, such as the Eigenfaces, Fisherfaces, and D-LDA methods and traditional linear classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:191", "title": "Face Detection Using Adaboosted SVM-Based Component Classifier", "text": "Recently, Adaboost has been widely used to improve the accuracy of any given learning algorithm. In this paper we focus on designing an algorithm to employ combination of Adaboost with Support Vector Machine as weak component classifiers to be used in Face Detection Task. To obtain a set of effective SVM-weaklearner Classifier, this algorithm adaptively adjusts the kernel parameter in SVM instead of using a fixed one. Proposed combination outperforms in generalization in comparison with SVM on imbalanced classification problem. The proposed here method is compared, in terms of classification accuracy, to other commonly used Adaboost methods, such as Decision Trees and Neural Networks, on CMU+MIT face database. Results indicate that the performance of the proposed method is overall superior to previous Adaboost approaches.", "source": "arxiv/ml"}
{"id": "arxiv:192", "title": "Binary Classification Based on Potentials", "text": "We introduce a simple and computationally trivial method for binary classification based on the evaluation of potential functions. We demonstrate that despite the conceptual and computational simplicity of the method its performance can match or exceed that of standard Support Vector Machine methods.", "source": "arxiv/ml"}
{"id": "arxiv:193", "title": "Comparison of Binary Classification Based on Signed Distance Functions with Support Vector Machines", "text": "We investigate the performance of a simple signed distance function (SDF) based method by direct comparison with standard SVM packages, as well as K-nearest neighbor and RBFN methods. We present experimental results comparing the SDF approach with other classifiers on both synthetic geometric problems and five benchmark clinical microarray data sets. On both geometric problems and microarray data sets, the non-optimized SDF based classifiers perform just as well or slightly better than well-developed, standard SVM methods. These results demonstrate the potential accuracy of SDF-based methods on some types of problems.", "source": "arxiv/ml"}
{"id": "arxiv:194", "title": "Quantum Predictive Learning and Communication Complexity with Single Input", "text": "We define a new model of quantum learning that we call Predictive Quantum (PQ). This is a quantum analogue of PAC, where during the testing phase the student is only required to answer a polynomial number of testing queries. We demonstrate a relational concept class that is efficiently learnable in PQ, while in any \"reasonable\" classical model exponential amount of training data would be required. This is the first unconditional separation between quantum and classical learning. We show that our separation is the best possible in several ways; in particular, there is no analogous result for a functional class, as well as for several weaker versions of quantum learning. In order to demonstrate tightness of our separation we consider a special case of one-way communication that we call single-input mode, where Bob receives no input. Somewhat surprisingly, this setting becomes nontrivial when relational communication tasks are considered. In particular, any problem with two-sided input can be transformed into a single-input relational problem of equal classical one-way cost. We show that the situation is different in the quantum case, where the same transformation can make the communication complexity exponentially larger. This happens if and only if the original problem has exponential gap between quantum and classical one-way communication costs. We believe that these auxiliary results might be of independent interest.", "source": "arxiv/ml"}
{"id": "arxiv:195", "title": "Linearly Parameterized Bandits", "text": "We consider bandit problems involving a large (possibly infinite) collection of arms, in which the expected reward of each arm is a linear function of an $r$-dimensional random vector $\\mathbf{Z} \\in \\mathbb{R}^r$, where $r \\geq 2$. The objective is to minimize the cumulative regret and Bayes risk. When the set of arms corresponds to the unit sphere, we prove that the regret and Bayes risk is of order $\\Theta(r \\sqrt{T})$, by establishing a lower bound for an arbitrary policy, and showing that a matching upper bound is obtained through a policy that alternates between exploration and exploitation phases. The phase-based policy is also shown to be effective if the set of arms satisfies a strong convexity condition. For the case of a general set of arms, we describe a near-optimal policy whose regret and Bayes risk admit upper bounds of the form $O(r \\sqrt{T} \\log^{3/2} T)$.", "source": "arxiv/ml"}
{"id": "arxiv:196", "title": "The Offset Tree for Learning with Partial Labels", "text": "We present an algorithm, called the Offset Tree, for learning to make decisions in situations where the payoff of only one choice is observed, rather than all choices. The algorithm reduces this setting to binary classification, allowing one to reuse of any existing, fully supervised binary classification algorithm in this partial information setting. We show that the Offset Tree is an optimal reduction to binary classification. In particular, it has regret at most $(k-1)$ times the regret of the binary classifier it uses (where $k$ is the number of choices), and no reduction to binary classification can do better. This reduction is also computationally optimal, both at training and test time, requiring just $O(\\log_2 k)$ work to train on an example or make a prediction. Experiments with the Offset Tree show that it generally performs better than several alternative approaches.", "source": "arxiv/ml"}
{"id": "arxiv:197", "title": "Client-server multi-task learning from distributed datasets", "text": "A client-server architecture to simultaneously solve multiple learning tasks from distributed datasets is described. In such architecture, each client is associated with an individual learning task and the associated dataset of examples. The goal of the architecture is to perform information fusion from multiple datasets while preserving privacy of individual data. The role of the server is to collect data in real-time from the clients and codify the information in a common database. The information coded in this database can be used by all the clients to solve their individual learning task, so that each client can exploit the informative content of all the datasets without actually having access to private data of others. The proposed algorithmic framework, based on regularization theory and kernel methods, uses a suitable class of mixed effect kernels. The new method is illustrated through a simulated music recommendation system.", "source": "arxiv/ml"}
{"id": "arxiv:198", "title": "The Latent Relation Mapping Engine: Algorithm and Experiments", "text": "Many AI researchers and cognitive scientists have argued that analogy is the core of cognition. The most influential work on computational modeling of analogy-making is Structure Mapping Theory (SMT) and its implementation in the Structure Mapping Engine (SME). A limitation of SME is the requirement for complex hand-coded representations. We introduce the Latent Relation Mapping Engine (LRME), which combines ideas from SME and Latent Relational Analysis (LRA) in order to remove the requirement for hand-coded representations. LRME builds analogical mappings between lists of words, using a large corpus of raw text to automatically discover the semantic relations among the words. We evaluate LRME on a set of twenty analogical mapping problems, ten based on scientific analogies and ten based on common metaphors. LRME achieves human-level performance on the twenty problems. We compare LRME with a variety of alternative approaches and find that they are not able to reach the same level of performance.", "source": "arxiv/ml"}
{"id": "arxiv:199", "title": "Feature Markov Decision Processes", "text": "General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes (MDPs). So far it is an art performed by human designers to extract the right state representation out of the bare observations, i.e. to reduce the agent setup to the MDP framework. Before we can think of mechanizing this search for suitable MDPs, we need a formal objective criterion. The main contribution of this article is to develop such a criterion. I also integrate the various parts into one learning algorithm. Extensions to more realistic dynamic Bayesian networks are developed in a companion article.", "source": "arxiv/ml"}
{"id": "arxiv:200", "title": "Feature Dynamic Bayesian Networks", "text": "Feature Markov Decision Processes (PhiMDPs) are well-suited for learning agents in general environments. Nevertheless, unstructured (Phi)MDPs are limited to relatively simple environments. Structured MDPs like Dynamic Bayesian Networks (DBNs) are used for large-scale real-world problems. In this article I extend PhiMDP to PhiDBN. The primary contribution is to derive a cost criterion that allows to automatically extract the most relevant features from the environment, leading to the \"best\" DBN representation. I discuss all building blocks required for a complete general learning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:201", "title": "Importance Weighted Active Learning", "text": "We present a practical and statistically consistent scheme for actively learning binary classifiers under general loss functions. Our algorithm uses importance weighting to correct sampling bias, and by controlling the variance, we are able to give rigorous label complexity bounds for the learning process. Experiments on passively labeled data show that this approach reduces the label complexity required to achieve good predictive performance on many learning problems.", "source": "arxiv/ml"}
{"id": "arxiv:202", "title": "A New Clustering Algorithm Based Upon Flocking On Complex Network", "text": "We have proposed a model based upon flocking on a complex network, and then developed two clustering algorithms on the basis of it. In the algorithms, firstly a \\textit{k}-nearest neighbor (knn) graph as a weighted and directed graph is produced among all data points in a dataset each of which is regarded as an agent who can move in space, and then a time-varying complex network is created by adding long-range links for each data point. Furthermore, each data point is not only acted by its \\textit{k} nearest neighbors but also \\textit{r} long-range neighbors through fields established in space by them together, so it will take a step along the direction of the vector sum of all fields. It is more important that these long-range links provides some hidden information for each data point when it moves and at the same time accelerate its speed converging to a center. As they move in space according to the proposed model, data points that belong to the same class are located at a same position gradually, whereas those that belong to different classes are away from one another. Consequently, the experimental results have demonstrated that data points in datasets are clustered reasonably and efficiently, and the rates of convergence of clustering algorithms are fast enough. Moreover, the comparison with other algorithms also provides an indication of the effectiveness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:203", "title": "A Novel Clustering Algorithm Based Upon Games on Evolving Network", "text": "This paper introduces a model based upon games on an evolving network, and develops three clustering algorithms according to it. In the clustering algorithms, data points for clustering are regarded as players who can make decisions in games. On the network describing relationships among data points, an edge-removing-and-rewiring (ERR) function is employed to explore in a neighborhood of a data point, which removes edges connecting to neighbors with small payoffs, and creates new edges to neighbors with larger payoffs. As such, the connections among data points vary over time. During the evolution of network, some strategies are spread in the network. As a consequence, clusters are formed automatically, in which data points with the same evolutionarily stable strategy are collected as a cluster, so the number of evolutionarily stable strategies indicates the number of clusters. Moreover, the experimental results have demonstrated that data points in datasets are clustered reasonably and efficiently, and the comparison with other algorithms also provides an indication of the effectiveness of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:204", "title": "MIMO decoding based on stochastic reconstruction from multiple projections", "text": "Least squares (LS) fitting is one of the most fundamental techniques in science and engineering. It is used to estimate parameters from multiple noisy observations. In many problems the parameters are known a-priori to be bounded integer valued, or they come from a finite set of values on an arbitrary finite lattice. In this case finding the closest vector becomes NP-Hard problem. In this paper we propose a novel algorithm, the Tomographic Least Squares Decoder (TLSD), that not only solves the ILS problem, better than other sub-optimal techniques, but also is capable of providing the a-posteriori probability distribution for each element in the solution vector. The algorithm is based on reconstruction of the vector from multiple two-dimensional projections. The projections are carefully chosen to provide low computational complexity. Unlike other iterative techniques, such as the belief propagation, the proposed algorithm has ensured convergence. We also provide simulated experiments comparing the algorithm to other sub-optimal algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:205", "title": "Distributed Preemption Decisions: Probabilistic Graphical Model, Algorithm and Near-Optimality", "text": "Cooperative decision making is a vision of future network management and control. Distributed connection preemption is an important example where nodes can make intelligent decisions on allocating resources and controlling traffic flows for multi-class service networks. A challenge is that nodal decisions are spatially dependent as traffic flows trespass multiple nodes in a network. Hence the performance-complexity trade-off becomes important, i.e., how accurate decisions are versus how much information is exchanged among nodes. Connection preemption is known to be NP-complete. Centralized preemption is optimal but computationally intractable. Decentralized preemption is computationally efficient but may result in a poor performance. This work investigates distributed preemption where nodes decide whether and which flows to preempt using only local information exchange with neighbors. We develop, based on the probabilistic graphical models, a near-optimal distributed algorithm. The algorithm is used by each node to make collectively near-optimal preemption decisions. We study trade-offs between near-optimal performance and complexity that corresponds to the amount of information-exchange of the distributed algorithm. The algorithm is validated by both analysis and simulation.", "source": "arxiv/ml"}
{"id": "arxiv:206", "title": "A Theoretical Analysis of Joint Manifolds", "text": "The emergence of low-cost sensor architectures for diverse modalities has made it possible to deploy sensor arrays that capture a single event from a large number of vantage points and using multiple modalities. In many scenarios, these sensors acquire very high-dimensional data such as audio signals, images, and video. To cope with such high-dimensional data, we typically rely on low-dimensional models. Manifold models provide a particularly powerful model that captures the structure of high-dimensional data when it is governed by a low-dimensional set of parameters. However, these models do not typically take into account dependencies among multiple sensors. We thus propose a new joint manifold framework for data ensembles that exploits such dependencies. We show that simple algorithms can exploit the joint manifold structure to improve their performance on standard signal processing applications. Additionally, recent results concerning dimensionality reduction for manifolds enable us to formulate a network-scalable data compression scheme that uses random projections of the sensed data. This scheme efficiently fuses the data from all sensors through the addition of such projections, regardless of the data modalities and dimensions.", "source": "arxiv/ml"}
{"id": "arxiv:207", "title": "Joint universal lossy coding and identification of stationary mixing sources with general alphabets", "text": "We consider the problem of joint universal variable-rate lossy coding and identification for parametric classes of stationary $\\beta$-mixing sources with general (Polish) alphabets. Compression performance is measured in terms of Lagrangians, while identification performance is measured by the variational distance between the true source and the estimated source. Provided that the sources are mixing at a sufficiently fast rate and satisfy certain smoothness and Vapnik-Chervonenkis learnability conditions, it is shown that, for bounded metric distortions, there exist universal schemes for joint lossy compression and identification whose Lagrangian redundancies converge to zero as $\\sqrt{V_n \\log n /n}$ as the block length $n$ tends to infinity, where $V_n$ is the Vapnik-Chervonenkis dimension of a certain class of decision regions defined by the $n$-dimensional marginal distributions of the sources; furthermore, for each $n$, the decoder can identify $n$-dimensional marginal of the active source up to a ball of radius $O(\\sqrt{V_n\\log n/n})$ in variational distance, eventually with probability one. The results are supplemented by several examples of parametric sources satisfying the regularity conditions.", "source": "arxiv/ml"}
{"id": "arxiv:208", "title": "Achievability results for statistical learning under communication constraints", "text": "The problem of statistical learning is to construct an accurate predictor of a random variable as a function of a correlated random variable on the basis of an i.i.d. training sample from their joint distribution. Allowable predictors are constrained to lie in some specified class, and the goal is to approach asymptotically the performance of the best predictor in the class. We consider two settings in which the learning agent only has access to rate-limited descriptions of the training data, and present information-theoretic bounds on the predictor performance achievable in the presence of these communication constraints. Our proofs do not assume any separation structure between compression and learning and rely on a new class of operational criteria specifically tailored to joint design of encoders and learning algorithms in rate-constrained settings.", "source": "arxiv/ml"}
{"id": "arxiv:209", "title": "A Limit Theorem in Singular Regression Problem", "text": "In statistical problems, a set of parameterized probability distributions is used to estimate the true probability distribution. If Fisher information matrix at the true distribution is singular, then it has been left unknown what we can estimate about the true distribution from random samples. In this paper, we study a singular regression problem and prove a limit theorem which shows the relation between the singular regression problem and two birational invariants, a real log canonical threshold and a singular fluctuation. The obtained theorem has an important application to statistics, because it enables us to estimate the generalization error from the training error without any knowledge of the true probability distribution.", "source": "arxiv/ml"}
{"id": "arxiv:210", "title": "Matrix Completion from a Few Entries", "text": "Let M be a random (alpha n) x n matrix of rank r<<n, and assume that a uniformly random subset E of its entries is observed. We describe an efficient algorithm that reconstructs M from |E| = O(rn) observed entries with relative root mean square error RMSE <= C(rn/|E|)^0.5 . Further, if r=O(1), M can be reconstructed exactly from |E| = O(n log(n)) entries. These results apply beyond random matrices to general low-rank incoherent matrices. This settles (in the case of bounded rank) a question left open by Candes and Recht and improves over the guarantees for their reconstruction algorithm. The complexity of our algorithm is O(|E|r log(n)), which opens the way to its use for massive data sets. In the process of proving these statements, we obtain a generalization of a celebrated result by Friedman-Kahn-Szemeredi and Feige-Ofek on the spectrum of sparse random matrices.", "source": "arxiv/ml"}
{"id": "arxiv:211", "title": "Model-Consistent Sparse Estimation through the Bootstrap", "text": "We consider the least-square linear regression problem with regularization by the $\\ell^1$-norm, a problem usually referred to as the Lasso. In this paper, we first present a detailed asymptotic analysis of model consistency of the Lasso in low-dimensional settings. For various decays of the regularization parameter, we compute asymptotic equivalents of the probability of correct model selection. For a specific rate decay, we show that the Lasso selects all the variables that should enter the model with probability tending to one exponentially fast, while it selects all other variables with strictly positive probability. We show that this property implies that if we run the Lasso for several bootstrapped replications of a given sample, then intersecting the supports of the Lasso bootstrap estimates leads to consistent model selection. This novel variable selection procedure, referred to as the Bolasso, is extended to high-dimensional settings by a provably consistent two-step procedure.", "source": "arxiv/ml"}
{"id": "arxiv:212", "title": "On the Dual Formulation of Boosting Algorithms", "text": "We study boosting algorithms from a new perspective. We show that the Lagrange dual problems of AdaBoost, LogitBoost and soft-margin LPBoost with generalized hinge loss are all entropy maximization problems. By looking at the dual problems of these boosting algorithms, we show that the success of boosting algorithms can be understood in terms of maintaining a better margin distribution by maximizing margins and at the same time controlling the margin variance.We also theoretically prove that, approximately, AdaBoost maximizes the average margin, instead of the minimum margin. The duality formulation also enables us to develop column generation based optimization algorithms, which are totally corrective. We show that they exhibit almost identical classification results to that of standard stage-wise additive boosting algorithms but with much faster convergence rates. Therefore fewer weak classifiers are needed to build the ensemble using our proposed optimization technique.", "source": "arxiv/ml"}
{"id": "arxiv:213", "title": "Cross-situational and supervised learning in the emergence of communication", "text": "Scenarios for the emergence or bootstrap of a lexicon involve the repeated interaction between at least two agents who must reach a consensus on how to name N objects using H words. Here we consider minimal models of two types of learning algorithms: cross-situational learning, in which the individuals determine the meaning of a word by looking for something in common across all observed uses of that word, and supervised operant conditioning learning, in which there is strong feedback between individuals about the intended meaning of the words. Despite the stark differences between these learning schemes, we show that they yield the same communication accuracy in the realistic limits of large N and H, which coincides with the result of the classical occupancy problem of randomly assigning N objects to H words.", "source": "arxiv/ml"}
{"id": "arxiv:214", "title": "Practical Robust Estimators for the Imprecise Dirichlet Model", "text": "Walley's Imprecise Dirichlet Model (IDM) for categorical i.i.d. data extends the classical Dirichlet model to a set of priors. It overcomes several fundamental problems which other approaches to uncertainty suffer from. Yet, to be useful in practice, one needs efficient ways for computing the imprecise=robust sets or intervals. The main objective of this work is to derive exact, conservative, and approximate, robust and credible interval estimates under the IDM for a large class of statistical estimators, including the entropy and mutual information.", "source": "arxiv/ml"}
{"id": "arxiv:215", "title": "Fixing Convergence of Gaussian Belief Propagation", "text": "Gaussian belief propagation (GaBP) is an iterative message-passing algorithm for inference in Gaussian graphical models. It is known that when GaBP converges it converges to the correct MAP estimate of the Gaussian random vector and simple sufficient conditions for its convergence have been established. In this paper we develop a double-loop algorithm for forcing convergence of GaBP. Our method computes the correct MAP estimate even in cases where standard GaBP would not have converged. We further extend this construction to compute least-squares solutions of over-constrained linear systems. We believe that our construction has numerous applications, since the GaBP algorithm is linked to solution of linear systems of equations, which is a fundamental problem in computer science and engineering. As a case study, we discuss the linear detection problem. We show that using our new construction, we are able to force convergence of Montanari's linear detection algorithm, in cases where it would originally fail. As a consequence, we are able to increase significantly the number of users that can transmit concurrently.", "source": "arxiv/ml"}
{"id": "arxiv:216", "title": "Non-Confluent NLC Graph Grammar Inference by Compressing Disjoint Subgraphs", "text": "Grammar inference deals with determining (preferable simple) models/grammars consistent with a set of observations. There is a large body of research on grammar inference within the theory of formal languages. However, there is surprisingly little known on grammar inference for graph grammars. In this paper we take a further step in this direction and work within the framework of node label controlled (NLC) graph grammars. Specifically, we characterize, given a set of disjoint and isomorphic subgraphs of a graph $G$, whether or not there is a NLC graph grammar rule which can generate these subgraphs to obtain $G$. This generalizes previous results by assuming that the set of isomorphic subgraphs is disjoint instead of non-touching. This leads naturally to consider the more involved ``non-confluent'' graph grammar rules.", "source": "arxiv/ml"}
{"id": "arxiv:217", "title": "Tree Exploration for Bayesian RL Exploration", "text": "Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programming problem on a belief tree with an infinite number of states. The second type employs relatively simple algorithm which are shown to suffer small regret within a distribution-free framework. This paper presents a lower bound and a high probability upper bound on the optimal value function for the nodes in the Bayesian belief tree, which are analogous to similar bounds in POMDPs. The bounds are then used to create more efficient strategies for exploring the tree. The resulting algorithms are compared with the distribution-free algorithm UCB1, as well as a simpler baseline algorithm on multi-armed bandit problems.", "source": "arxiv/ml"}
{"id": "arxiv:218", "title": "Discovering general partial orders in event streams", "text": "Frequent episode discovery is a popular framework for pattern discovery in event streams. An episode is a partially ordered set of nodes with each node associated with an event type. Efficient (and separate) algorithms exist for episode discovery when the associated partial order is total (serial episode) and trivial (parallel episode). In this paper, we propose efficient algorithms for discovering frequent episodes with general partial orders. These algorithms can be easily specialized to discover serial or parallel episodes. Also, the algorithms are flexible enough to be specialized for mining in the space of certain interesting subclasses of partial orders. We point out that there is an inherent combinatorial explosion in frequent partial order mining and most importantly, frequency alone is not a sufficient measure of interestingness. We propose a new interestingness measure for general partial order episodes and a discovery method based on this measure, for filtering out uninteresting partial orders. Simulations demonstrate the effectiveness of our algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:219", "title": "Extraction de concepts sous contraintes dans des donn\\'ees d'expression de g\\`enes", "text": "In this paper, we propose a technique to extract constrained formal concepts.", "source": "arxiv/ml"}
{"id": "arxiv:220", "title": "Database Transposition for Constrained (Closed) Pattern Mining", "text": "Recently, different works proposed a new way to mine patterns in databases with pathological size. For example, experiments in genome biology usually provide databases with thousands of attributes (genes) but only tens of objects (experiments). In this case, mining the \"transposed\" database runs through a smaller search space, and the Galois connection allows to infer the closed patterns of the original database. We focus here on constrained pattern mining for those unusual databases and give a theoretical framework for database and constraint transposition. We discuss the properties of constraint transposition and look into classical constraints. We then address the problem of generating the closed patterns of the original database satisfying the constraint, starting from those mined in the \"transposed\" database. Finally, we show how to generate all the patterns satisfying the constraint from the closed ones.", "source": "arxiv/ml"}
{"id": "arxiv:221", "title": "Multi-Label Prediction via Compressed Sensing", "text": "We consider multi-label prediction problems with large output spaces under the assumption of output sparsity -- that the target (label) vectors have small support. We develop a general theory for a variant of the popular error correcting output code scheme, using ideas from compressed sensing for exploiting this sparsity. The method can be regarded as a simple reduction from multi-label regression problems to binary regression problems. We show that the number of subproblems need only be logarithmic in the total number of possible labels, making this approach radically more efficient than others. We also state and prove robustness guarantees for this method in the form of regret transform bounds (in general), and also provide a more detailed analysis for the linear prediction setting.", "source": "arxiv/ml"}
{"id": "arxiv:222", "title": "Object Classification by means of Multi-Feature Concept Learning in a Multi Expert-Agent System", "text": "Classification of some objects in classes of concepts is an essential and even breathtaking task in many applications. A solution is discussed here based on Multi-Agent systems. A kernel of some expert agents in several classes is to consult a central agent decide among the classification problem of a certain object. This kernel is moderated with the center agent, trying to manage the querying agents for any decision problem by means of a data-header like feature set. Agents have cooperation among concepts related to the classes of this classification decision-making; and may affect on each others' results on a certain query object in a multi-agent learning approach. This leads to an online feature learning via the consulting trend. The performance is discussed to be much better in comparison to some other prior trends while system's message passing overload is decreased to less agents and the expertism helps the performance and operability of system win the comparison.", "source": "arxiv/ml"}
{"id": "arxiv:223", "title": "Error-Correcting Tournaments", "text": "We present a family of pairwise tournaments reducing $k$-class classification to binary classification. These reductions are provably robust against a constant fraction of binary errors. The results improve on the PECOC construction \\cite{SECOC} with an exponential improvement in computation, from $O(k)$ to $O(\\log_2 k)$, and the removal of a square root in the regret dependence, matching the best possible computation and regret up to a constant.", "source": "arxiv/ml"}
{"id": "arxiv:224", "title": "An Exact Algorithm for the Stratification Problem with Proportional Allocation", "text": "We report a new optimal resolution for the statistical stratification problem under proportional sampling allocation among strata. Consider a finite population of N units, a random sample of n units selected from this population and a number L of strata. Thus, we have to define which units belong to each stratum so as to minimize the variance of a total estimator for one desired variable of interest in each stratum,and consequently reduce the overall variance for such quantity. In order to solve this problem, an exact algorithm based on the concept of minimal path in a graph is proposed and assessed. Computational results using real data from IBGE (Brazilian Central Statistical Office) are provided.", "source": "arxiv/ml"}
{"id": "arxiv:225", "title": "Learning rules from multisource data for cardiac monitoring", "text": "This paper formalises the concept of learning symbolic rules from multisource data in a cardiac monitoring context. Our sources, electrocardiograms and arterial blood pressure measures, describe cardiac behaviours from different viewpoints. To learn interpretable rules, we use an Inductive Logic Programming (ILP) method. We develop an original strategy to cope with the dimensionality issues caused by using this ILP technique on a rich multisource language. The results show that our method greatly improves the feasibility and the efficiency of the process while staying accurate. They also confirm the benefits of using multiple sources to improve the diagnosis of cardiac arrhythmias.", "source": "arxiv/ml"}
{"id": "arxiv:226", "title": "Domain Adaptation: Learning Bounds and Algorithms", "text": "This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by Ben-David et al. (2007), we introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss functions. We give Rademacher complexity bounds for estimating the discrepancy distance from finite samples for different loss functions. Using this distance, we derive novel generalization bounds for domain adaptation for a wide family of loss functions. We also present a series of novel adaptation bounds for large classes of regularization-based algorithms, including support vector machines and kernel ridge regression based on the empirical discrepancy. This motivates our analysis of the problem of minimizing the empirical discrepancy for various loss functions for which we also give novel algorithms. We report the results of preliminary experiments that demonstrate the benefits of our discrepancy minimization algorithms for domain adaptation.", "source": "arxiv/ml"}
{"id": "arxiv:227", "title": "Online Multi-task Learning with Hard Constraints", "text": "We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss \"tracking\" and \"bandit\" versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.", "source": "arxiv/ml"}
{"id": "arxiv:228", "title": "Uniqueness of Low-Rank Matrix Completion by Rigidity Theory", "text": "The problem of completing a low-rank matrix from a subset of its entries is often encountered in the analysis of incomplete data sets exhibiting an underlying factor model with applications in collaborative filtering, computer vision and control. Most recent work had been focused on constructing efficient algorithms for exact or approximate recovery of the missing matrix entries and proving lower bounds for the number of known entries that guarantee a successful recovery with high probability. A related problem from both the mathematical and algorithmic point of view is the distance geometry problem of realizing points in a Euclidean space from a given subset of their pairwise distances. Rigidity theory answers basic questions regarding the uniqueness of the realization satisfying a given partial set of distances. We observe that basic ideas and tools of rigidity theory can be adapted to determine uniqueness of low-rank matrix completion, where inner products play the role that distances play in rigidity theory. This observation leads to an efficient randomized algorithm for testing both local and global unique completion. Crucial to our analysis is a new matrix, which we call the completion matrix, that serves as the analogue of the rigidity matrix.", "source": "arxiv/ml"}
{"id": "arxiv:229", "title": "Prediction with expert evaluators' advice", "text": "We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner's and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner's goal is to perform better or not much worse than each expert, as evaluated by that expert, for all experts simultaneously. If the loss functions used by the experts are all proper scoring rules and all mixable, we show that the defensive forecasting algorithm enjoys the same performance guarantee as that attainable by the Aggregating Algorithm in the standard setting and known to be optimal. This result is also applied to the case of \"specialist\" (or \"sleeping\") experts. In this case, the defensive forecasting algorithm reduces to a simple modification of the Aggregating Algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:230", "title": "Multiplicative updates For Non-Negative Kernel SVM", "text": "We present multiplicative updates for solving hard and soft margin support vector machines (SVM) with non-negative kernels. They follow as a natural extension of the updates for non-negative matrix factorization. No additional param- eter setting, such as choosing learning, rate is required. Ex- periments demonstrate rapid convergence to good classifiers. We analyze the rates of asymptotic convergence of the up- dates and establish tight bounds. We test the performance on several datasets using various non-negative kernels and report equivalent generalization errors to that of a standard SVM.", "source": "arxiv/ml"}
{"id": "arxiv:231", "title": "Manipulation Robustness of Collaborative Filtering Systems", "text": "A collaborative filtering system recommends to users products that similar users like. Collaborative filtering systems influence purchase decisions, and hence have become targets of manipulation by unscrupulous vendors. We provide theoretical and empirical results demonstrating that while common nearest neighbor algorithms, which are widely used in commercial systems, can be highly susceptible to manipulation, two classes of collaborative filtering algorithms which we refer to as linear and asymptotically linear are relatively robust. These results provide guidance for the design of future collaborative filtering systems.", "source": "arxiv/ml"}
{"id": "arxiv:232", "title": "Efficient Human Computation", "text": "Collecting large labeled data sets is a laborious and expensive task, whose scaling up requires division of the labeling workload between many teachers. When the number of classes is large, miscorrespondences between the labels given by the different teachers are likely to occur, which, in the extreme case, may reach total inconsistency. In this paper we describe how globally consistent labels can be obtained, despite the absence of teacher coordination, and discuss the possible efficiency of this process in terms of human labor. We define a notion of label efficiency, measuring the ratio between the number of globally consistent labels obtained and the number of labels provided by distributed teachers. We show that the efficiency depends critically on the ratio alpha between the number of data instances seen by a single teacher, and the number of classes. We suggest several algorithms for the distributed labeling problem, and analyze their efficiency as a function of alpha. In addition, we provide an upper bound on label efficiency for the case of completely uncoordinated teachers, and show that efficiency approaches 0 as the ratio between the number of labels each teacher provides and the number of classes drops (i.e. alpha goes to 0).", "source": "arxiv/ml"}
{"id": "arxiv:233", "title": "Multiagent Learning in Large Anonymous Games", "text": "In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to find restricted classes of games where simple, efficient algorithms converge. It is shown that stage learning efficiently converges to Nash equilibria in large anonymous games if best-reply dynamics converge. Two features are identified that improve convergence. First, rather than making learning more difficult, more agents are actually beneficial in many settings. Second, providing agents with statistical information about the behavior of others can significantly reduce the number of observations needed.", "source": "arxiv/ml"}
{"id": "arxiv:234", "title": "Differential Contrastive Divergence", "text": "This paper has been retracted.", "source": "arxiv/ml"}
{"id": "arxiv:235", "title": "A parameter-free hedging algorithm", "text": "We study the problem of decision-theoretic online learning (DTOL). Motivated by practical applications, we focus on DTOL when the number of actions is very large. Previous algorithms for learning in this framework have a tunable learning rate parameter, and a barrier to using online-learning in practical applications is that it is not understood how to set this parameter optimally, particularly when the number of actions is large. In this paper, we offer a clean solution by proposing a novel and completely parameter-free algorithm for DTOL. We introduce a new notion of regret, which is more natural for applications with a large number of actions. We show that our algorithm achieves good performance with respect to this new notion of regret; in addition, it also achieves performance close to that of the best bounds achieved by previous algorithms with optimally-tuned parameters, according to previous notions of regret.", "source": "arxiv/ml"}
{"id": "arxiv:236", "title": "Tracking using explanation-based modeling", "text": "We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. However, the problem with these solutions is that they are very sensitive to model mismatches. In this paper, motivated by online learning, we introduce a new framework -- an {\\em explanatory} framework -- for tracking. We provide an efficient tracking algorithm for this framework. We provide experimental results comparing our algorithm to the Bayesian algorithm on simulated data. Our experiments show that when there are slight model mismatches, our algorithm vastly outperforms the Bayesian algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:237", "title": "On $p$-adic Classification", "text": "A $p$-adic modification of the split-LBG classification method is presented in which first clusterings and then cluster centers are computed which locally minimise an energy function. The outcome for a fixed dataset is independent of the prime number $p$ with finitely many exceptions. The methods are applied to the construction of $p$-adic classifiers in the context of learning.", "source": "arxiv/ml"}
{"id": "arxiv:238", "title": "Kalman Filtering with Intermittent Observations: Weak Convergence to a Stationary Distribution", "text": "The paper studies the asymptotic behavior of Random Algebraic Riccati Equations (RARE) arising in Kalman filtering when the arrival of the observations is described by a Bernoulli i.i.d. process. We model the RARE as an order-preserving, strongly sublinear random dynamical system (RDS). Under a sufficient condition, stochastic boundedness, and using a limit-set dichotomy result for order-preserving, strongly sublinear RDS, we establish the asymptotic properties of the RARE: the sequence of random prediction error covariance matrices converges weakly to a unique invariant distribution, whose support exhibits fractal behavior. In particular, this weak convergence holds under broad conditions and even when the observations arrival rate is below the critical probability for mean stability. We apply the weak-Feller property of the Markov process governing the RARE to characterize the support of the limiting invariant distribution as the topological closure of a countable set of points, which, in general, is not dense in the set of positive semi-definite matrices. We use the explicit characterization of the support of the invariant distribution and the almost sure ergodicity of the sample paths to easily compute the moments of the invariant distribution. A one dimensional example illustrates that the support is a fractured subset of the non-negative reals with self-similarity properties.", "source": "arxiv/ml"}
{"id": "arxiv:239", "title": "Optimistic Simulated Exploration as an Incentive for Real Exploration", "text": "Many reinforcement learning exploration techniques are overly optimistic and try to explore every state. Such exploration is impossible in environments with the unlimited number of states. I propose to use simulated exploration with an optimistic model to discover promising paths for real exploration. This reduces the needs for the real exploration.", "source": "arxiv/ml"}
{"id": "arxiv:240", "title": "Efficiently Learning a Detection Cascade with Sparse Eigenvectors", "text": "In this work, we first show that feature selection methods other than boosting can also be used for training an efficient object detector. In particular, we introduce Greedy Sparse Linear Discriminant Analysis (GSLDA) \\cite{Moghaddam2007Fast} for its conceptual simplicity and computational efficiency; and slightly better detection performance is achieved compared with \\cite{Viola2004Robust}. Moreover, we propose a new technique, termed Boosted Greedy Sparse Linear Discriminant Analysis (BGSLDA), to efficiently train a detection cascade. BGSLDA exploits the sample re-weighting property of boosting and the class-separability criterion of GSLDA.", "source": "arxiv/ml"}
{"id": "arxiv:241", "title": "A New Local Distance-Based Outlier Detection Approach for Scattered Real-World Data", "text": "Detecting outliers which are grossly different from or inconsistent with the remaining dataset is a major challenge in real-world KDD applications. Existing outlier detection methods are ineffective on scattered real-world datasets due to implicit data patterns and parameter setting issues. We define a novel \"Local Distance-based Outlier Factor\" (LDOF) to measure the {outlier-ness} of objects in scattered datasets which addresses these issues. LDOF uses the relative location of an object to its neighbours to determine the degree to which the object deviates from its neighbourhood. Properties of LDOF are theoretically analysed including LDOF's lower bound and its false-detection probability, as well as parameter settings. In order to facilitate parameter settings in real-world applications, we employ a top-n technique in our outlier detection approach, where only the objects with the highest LDOF values are regarded as outliers. Compared to conventional approaches (such as top-n KNN and top-n LOF), our method top-n LDOF is more effective at detecting outliers in scattered data. It is also easier to set parameters, since its performance is relatively stable over a large range of parameter values, as illustrated by experimental results on both real-world and synthetic datasets.", "source": "arxiv/ml"}
{"id": "arxiv:242", "title": "Optimal Policies Search for Sensor Management", "text": "This paper introduces a new approach to solve sensor management problems. Classically sensor management problems can be well formalized as Partially-Observed Markov Decision Processes (POMPD). The original approach developped here consists in deriving the optimal parameterized policy based on a stochastic gradient estimation. We assume in this work that it is possible to learn the optimal policy off-line (in simulation) using models of the environement and of the sensor(s). The learned policy can then be used to manage the sensor(s). In order to approximate the gradient in a stochastic context, we introduce a new method to approximate the gradient, based on Infinitesimal Perturbation Approximation (IPA). The effectiveness of this general framework is illustrated by the managing of an Electronically Scanned Array Radar. First simulations results are finally proposed.", "source": "arxiv/ml"}
{"id": "arxiv:243", "title": "How random are a learner's mistakes?", "text": "Given a random binary sequence $X^{(n)}$ of random variables, $X_{t},$ $t=1,2,...,n$, for instance, one that is generated by a Markov source (teacher) of order $k^{*}$ (each state represented by $k^{*}$ bits). Assume that the probability of the event $X_{t}=1$ is constant and denote it by $\\beta$. Consider a learner which is based on a parametric model, for instance a Markov model of order $k$, who trains on a sequence $x^{(m)}$ which is randomly drawn by the teacher. Test the learner's performance by giving it a sequence $x^{(n)}$ (generated by the teacher) and check its predictions on every bit of $x^{(n)}.$ An error occurs at time $t$ if the learner's prediction $Y_{t}$ differs from the true bit value $X_{t}$. Denote by $\\xi^{(n)}$ the sequence of errors where the error bit $\\xi_{t}$ at time $t$ equals 1 or 0 according to whether the event of an error occurs or not, respectively. Consider the subsequence $\\xi^{(\\nu)}$ of $\\xi^{(n)}$ which corresponds to the errors of predicting a 0, i.e., $\\xi^{(\\nu)}$ consists of the bits of $\\xi^{(n)}$ only at times $t$ such that $Y_{t}=0.$ In this paper we compute an estimate on the deviation of the frequency of 1s of $\\xi^{(\\nu)}$ from $\\beta$. The result shows that the level of randomness of $\\xi^{(\\nu)}$ decreases relative to an increase in the complexity of the learner.", "source": "arxiv/ml"}
{"id": "arxiv:244", "title": "Conditional Probability Tree Estimation Analysis and Algorithms", "text": "We consider the problem of estimating the conditional probability of a label in time $O(\\log n)$, where $n$ is the number of possible labels. We analyze a natural reduction of this problem to a set of binary regression problems organized in a tree structure, proving a regret bound that scales with the depth of the tree. Motivated by this analysis, we propose the first online algorithm which provably constructs a logarithmic depth tree on the set of labels to solve this problem. We test the algorithm empirically, showing that it works succesfully on a dataset with roughly $10^6$ labels.", "source": "arxiv/ml"}
{"id": "arxiv:245", "title": "Graph polynomials and approximation of partition functions with Loopy Belief Propagation", "text": "The Bethe approximation, or loopy belief propagation algorithm is a successful method for approximating partition functions of probabilistic models associated with a graph. Chertkov and Chernyak derived an interesting formula called Loop Series Expansion, which is an expansion of the partition function. The main term of the series is the Bethe approximation while other terms are labeled by subgraphs called generalized loops. In our recent paper, we derive the loop series expansion in form of a polynomial with coefficients positive integers, and extend the result to the expansion of marginals. In this paper, we give more clear derivation for the results and discuss the properties of the polynomial which is introduced in the paper.", "source": "arxiv/ml"}
{"id": "arxiv:246", "title": "An Exponential Lower Bound on the Complexity of Regularization Paths", "text": "For a variety of regularized optimization problems in machine learning, algorithms computing the entire solution path have been developed recently. Most of these methods are quadratic programs that are parameterized by a single parameter, as for example the Support Vector Machine (SVM). Solution path algorithms do not only compute the solution for one particular value of the regularization parameter but the entire path of solutions, making the selection of an optimal parameter much easier. It has been assumed that these piecewise linear solution paths have only linear complexity, i.e. linearly many bends. We prove that for the support vector machine this complexity can be exponential in the number of training points in the worst case. More strongly, we construct a single instance of n input points in d dimensions for an SVM such that at least \\Theta(2^{n/2}) = \\Theta(2^d) many distinct subsets of support vectors occur as the regularization parameter changes.", "source": "arxiv/ml"}
{"id": "arxiv:247", "title": "A Combinatorial Algorithm to Compute Regularization Paths", "text": "For a wide variety of regularization methods, algorithms computing the entire solution path have been developed recently. Solution path algorithms do not only compute the solution for one particular value of the regularization parameter but the entire path of solutions, making the selection of an optimal parameter much easier. Most of the currently used algorithms are not robust in the sense that they cannot deal with general or degenerate input. Here we present a new robust, generic method for parametric quadratic programming. Our algorithm directly applies to nearly all machine learning applications, where so far every application required its own different algorithm. We illustrate the usefulness of our method by applying it to a very low rank problem which could not be solved by existing path tracking methods, namely to compute part-worth values in choice based conjoint analysis, a popular technique from market research to estimate consumers preferences on a class of parameterized options.", "source": "arxiv/ml"}
{"id": "arxiv:248", "title": "Learning Multiple Belief Propagation Fixed Points for Real Time Inference", "text": "In the context of inference with expectation constraints, we propose an approach based on the \"loopy belief propagation\" algorithm LBP, as a surrogate to an exact Markov Random Field MRF modelling. A prior information composed of correlations among a large set of N variables, is encoded into a graphical model; this encoding is optimized with respect to an approximate decoding procedure LBP, which is used to infer hidden variables from an observed subset. We focus on the situation where the underlying data have many different statistical components, representing a variety of independent patterns. Considering a single parameter family of models we show how LBP may be used to encode and decode efficiently such information, without solving the NP hard inverse problem yielding the optimal MRF. Contrary to usual practice, we work in the non-convex Bethe free energy minimization framework, and manage to associate a belief propagation fixed point to each component of the underlying probabilistic mixture. The mean field limit is considered and yields an exact connection with the Hopfield model at finite temperature and steady state, when the number of mixture components is proportional to the number of variables. In addition, we provide an enhanced learning procedure, based on a straightforward multi-parameter extension of the model in conjunction with an effective continuous optimization procedure. This is performed using the stochastic search heuristic CMAES and yields a significant improvement with respect to the single parameter basic model.", "source": "arxiv/ml"}
{"id": "arxiv:249", "title": "Time manipulation technique for speeding up reinforcement learning in simulations", "text": "A technique for speeding up reinforcement learning algorithms by using time manipulation is proposed. It is applicable to failure-avoidance control problems running in a computer simulation. Turning the time of the simulation backwards on failure events is shown to speed up the learning by 260% and improve the state space exploration by 12% on the cart-pole balancing task, compared to the conventional Q-learning and Actor-Critic algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:250", "title": "A Stochastic View of Optimal Regret through Minimax Duality", "text": "We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical minimization algorithm in a stochastic process setting: it is equal to the maximum, over joint distributions of the adversary's action sequence, of the difference between a sum of minimal expected losses and the minimal empirical loss. We show that the optimal regret has a natural geometric interpretation, since it can be viewed as the gap in Jensen's inequality for a concave functional--the minimizer over the player's actions of expected loss--defined on a set of probability distributions. We use this expression to obtain upper and lower bounds on the regret of an optimal strategy for a variety of online learning problems. Our method provides upper bounds without the need to construct a learning algorithm; the lower bounds provide explicit optimal strategies for the adversary.", "source": "arxiv/ml"}
{"id": "arxiv:251", "title": "Exact Non-Parametric Bayesian Inference on Infinite Trees", "text": "Given i.i.d. data from an unknown distribution, we consider the problem of predicting future items. An adaptive way to estimate the probability density is to recursively subdivide the domain to an appropriate data-dependent granularity. A Bayesian would assign a data-independent prior probability to \"subdivide\", which leads to a prior over infinite(ly many) trees. We derive an exact, fast, and simple inference algorithm for such a prior, for the data evidence, the predictive distribution, the effective model dimension, moments, and other quantities. We prove asymptotic convergence and consistency results, and illustrate the behavior of our model on some prototypical functions.", "source": "arxiv/ml"}
{"id": "arxiv:252", "title": "Time Hopping technique for faster reinforcement learning in simulations", "text": "This preprint has been withdrawn by the author for revision", "source": "arxiv/ml"}
{"id": "arxiv:253", "title": "Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning", "text": "A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provides for Time Hopping similar abilities to what eligibility traces provide for conventional Reinforcement Learning. It propagates values from one state to all of its temporal predecessors using a state transitions graph. Experiments on a simulated biped crawling robot confirm that Eligibility Propagation accelerates the learning process more than 3 times.", "source": "arxiv/ml"}
{"id": "arxiv:254", "title": "Performing Nonlinear Blind Source Separation with Signal Invariants", "text": "Given a time series of multicomponent measurements x(t), the usual objective of nonlinear blind source separation (BSS) is to find a \"source\" time series s(t), comprised of statistically independent combinations of the measured components. In this paper, the source time series is required to have a density function in (s,ds/dt)-space that is equal to the product of density functions of individual components. This formulation of the BSS problem has a solution that is unique, up to permutations and component-wise transformations. Separability is shown to impose constraints on certain locally invariant (scalar) functions of x, which are derived from local higher-order correlations of the data's velocity dx/dt. The data are separable if and only if they satisfy these constraints, and, if the constraints are satisfied, the sources can be explicitly constructed from the data. The method is illustrated by using it to separate two speech-like sounds recorded with a single microphone.", "source": "arxiv/ml"}
{"id": "arxiv:255", "title": "Evolvability need not imply learnability", "text": "We show that Boolean functions expressible as monotone disjunctive normal forms are PAC-evolvable under a uniform distribution on the Boolean cube if the hypothesis size is allowed to remain fixed. We further show that this result is insufficient to prove the PAC-learnability of monotone Boolean functions, thereby demonstrating a counter-example to a recent claim to the contrary. We further discuss scenarios wherein evolvability and learnability will coincide as well as scenarios under which they differ. The implications of the latter case on the prospects of learning in complex hypothesis spaces is briefly examined.", "source": "arxiv/ml"}
{"id": "arxiv:256", "title": "Induction of High-level Behaviors from Problem-solving Traces using Machine Learning Tools", "text": "This paper applies machine learning techniques to student modeling. It presents a method for discovering high-level student behaviors from a very large set of low-level traces corresponding to problem-solving actions in a learning environment. Basic actions are encoded into sets of domain-dependent attribute-value patterns called cases. Then a domain-independent hierarchical clustering identifies what we call general attitudes, yielding automatic diagnosis expressed in natural language, addressed in principle to teachers. The method can be applied to individual students or to entire groups, like a class. We exhibit examples of this system applied to thousands of students' actions in the domain of algebraic transformations.", "source": "arxiv/ml"}
{"id": "arxiv:257", "title": "Stability Analysis and Learning Bounds for Transductive Regression Algorithms", "text": "This paper uses the notion of algorithmic stability to derive novel generalization bounds for several families of transductive regression algorithms, both by using convexity and closed-form solutions. Our analysis helps compare the stability of these algorithms. It also shows that a number of widely used transductive regression algorithms are in fact unstable. Finally, it reports the results of experiments with local transductive regression demonstrating the benefit of our stability bounds for model selection, for one of the algorithms, in particular for determining the radius of the local neighborhood used by the algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:258", "title": "Learning convex bodies is hard", "text": "We show that learning a convex body in $\\RR^d$, given random samples from the body, requires $2^{\\Omega(\\sqrt{d/\\eps})}$ samples. By learning a convex body we mean finding a set having at most $\\eps$ relative symmetric difference with the input body. To prove the lower bound we construct a hard to learn family of convex bodies. Our construction of this family is very simple and based on error correcting codes.", "source": "arxiv/ml"}
{"id": "arxiv:259", "title": "Online prediction of ovarian cancer", "text": "In this paper we apply computer learning methods to diagnosing ovarian cancer using the level of the standard biomarker CA125 in conjunction with information provided by mass-spectrometry. We are working with a new data set collected over a period of 7 years. Using the level of CA125 and mass-spectrometry peaks, our algorithm gives probability predictions for the disease. To estimate classification accuracy we convert probability predictions into strict predictions. Our algorithm makes fewer errors than almost any linear combination of the CA125 level and one peak's intensity (taken on the log scale). To check the power of our algorithm we use it to test the hypothesis that CA125 and the peaks do not contain useful information for the prediction of the disease at a particular time before the diagnosis. Our algorithm produces $p$-values that are better than those produced by the algorithm that has been previously applied to this data set. Our conclusion is that the proposed algorithm is more reliable for prediction on new data.", "source": "arxiv/ml"}
{"id": "arxiv:260", "title": "Recovering the state sequence of hidden Markov models using mean-field approximations", "text": "Inferring the sequence of states from observations is one of the most fundamental problems in Hidden Markov Models. In statistical physics language, this problem is equivalent to computing the marginals of a one-dimensional model with a random external field. While this task can be accomplished through transfer matrix methods, it becomes quickly intractable when the underlying state space is large. This paper develops several low-complexity approximate algorithms to address this inference problem when the state space becomes large. The new algorithms are based on various mean-field approximations of the transfer matrix. Their performances are studied in detail on a simple realistic model for DNA pyrosequencing.", "source": "arxiv/ml"}
{"id": "arxiv:261", "title": "On Fodor on Darwin on Evolution", "text": "Jerry Fodor argues that Darwin was wrong about \"natural selection\" because (1) it is only a tautology rather than a scientific law that can support counterfactuals (\"If X had happened, Y would have happened\") and because (2) only minds can select. Hence Darwin's analogy with \"artificial selection\" by animal breeders was misleading and evolutionary explanation is nothing but post-hoc historical narrative. I argue that Darwin was right on all counts.", "source": "arxiv/ml"}
{"id": "arxiv:262", "title": "Boosting through Optimization of Margin Distributions", "text": "Boosting has attracted much research attention in the past decade. The success of boosting algorithms may be interpreted in terms of the margin theory. Recently it has been shown that generalization error of classifiers can be obtained by explicitly taking the margin distribution of the training data into account. Most of the current boosting algorithms in practice usually optimizes a convex loss function and do not make use of the margin distribution. In this work we design a new boosting algorithm, termed margin-distribution boosting (MDBoost), which directly maximizes the average margin and minimizes the margin variance simultaneously. This way the margin distribution is optimized. A totally-corrective optimization algorithm based on column generation is proposed to implement MDBoost. Experiments on UCI datasets show that MDBoost outperforms AdaBoost and LPBoost in most cases.", "source": "arxiv/ml"}
{"id": "arxiv:263", "title": "Inferring Dynamic Bayesian Networks using Frequent Episode Mining", "text": "Motivation: Several different threads of research have been proposed for modeling and mining temporal data. On the one hand, approaches such as dynamic Bayesian networks (DBNs) provide a formal probabilistic basis to model relationships between time-indexed random variables but these models are intractable to learn in the general case. On the other, algorithms such as frequent episode mining are scalable to large datasets but do not exhibit the rigorous probabilistic interpretations that are the mainstay of the graphical models literature. Results: We present a unification of these two seemingly diverse threads of research, by demonstrating how dynamic (discrete) Bayesian networks can be inferred from the results of frequent episode mining. This helps bridge the modeling emphasis of the former with the counting emphasis of the latter. First, we show how, under reasonable assumptions on data characteristics and on influences of random variables, the optimal DBN structure can be computed using a greedy, local, algorithm. Next, we connect the optimality of the DBN structure with the notion of fixed-delay episodes and their counts of distinct occurrences. Finally, to demonstrate the practical feasibility of our approach, we focus on a specific (but broadly applicable) class of networks, called excitatory networks, and show how the search for the optimal DBN structure can be conducted using just information from frequent episodes. Application on datasets gathered from mathematical models of spiking neurons as well as real neuroscience datasets are presented. Availability: Algorithmic implementations, simulator codebases, and datasets are available from our website at http://neural-code.cs.vt.edu/dbn", "source": "arxiv/ml"}
{"id": "arxiv:264", "title": "Why Global Performance is a Poor Metric for Verifying Convergence of Multi-agent Learning", "text": "Experimental verification has been the method of choice for verifying the stability of a multi-agent reinforcement learning (MARL) algorithm as the number of agents grows and theoretical analysis becomes prohibitively complex. For cooperative agents, where the ultimate goal is to optimize some global metric, the stability is usually verified by observing the evolution of the global performance metric over time. If the global metric improves and eventually stabilizes, it is considered a reasonable verification of the system's stability. The main contribution of this note is establishing the need for better experimental frameworks and measures to assess the stability of large-scale adaptive cooperative systems. We show an experimental case study where the stability of the global performance metric can be rather deceiving, hiding an underlying instability in the system that later leads to a significant drop in performance. We then propose an alternative metric that relies on agents' local policies and show, experimentally, that our proposed metric is more effective (than the traditional global performance metric) in exposing the instability of MARL algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:265", "title": "A Methodology for Learning Players' Styles from Game Records", "text": "We describe a preliminary investigation into learning a Chess player's style from game records. The method is based on attempting to learn features of a player's individual evaluation function using the method of temporal differences, with the aid of a conventional Chess engine architecture. Some encouraging results were obtained in learning the styles of two recent Chess world champions, and we report on our attempt to use the learnt styles to discriminate between the players from game records by trying to detect who was playing white and who was playing black. We also discuss some limitations of our approach and propose possible directions for future research. The method we have presented may also be applicable to other strategic games, and may even be generalisable to other domains where sequences of agents' actions are recorded.", "source": "arxiv/ml"}
{"id": "arxiv:266", "title": "Exponential Family Graph Matching and Ranking", "text": "We present a method for learning max-weight matching predictors in bipartite graphs. The method consists of performing maximum a posteriori estimation in exponential families with sufficient statistics that encode permutations and data features. Although inference is in general hard, we show that for one very relevant application - web page ranking - exact inference is efficient. For general model instances, an appropriate sampler is readily available. Contrary to existing max-margin matching models, our approach is statistically consistent and, in addition, experiments with increasing sample sizes indicate superior improvement over such models. We apply the method to graph matching in computer vision as well as to a standard benchmark dataset for learning web page ranking, in which we obtain state-of-the-art results, in particular improving on max-margin variants. The drawback of this method with respect to max-margin alternatives is its runtime for large graphs, which is comparatively high.", "source": "arxiv/ml"}
{"id": "arxiv:267", "title": "Efficient Construction of Neighborhood Graphs by the Multiple Sorting Method", "text": "Neighborhood graphs are gaining popularity as a concise data representation in machine learning. However, naive graph construction by pairwise distance calculation takes $O(n^2)$ runtime for $n$ data points and this is prohibitively slow for millions of data points. For strings of equal length, the multiple sorting method (Uno, 2008) can construct an $\\epsilon$-neighbor graph in $O(n+m)$ time, where $m$ is the number of $\\epsilon$-neighbor pairs in the data. To introduce this remarkably efficient algorithm to continuous domains such as images, signals and texts, we employ a random projection method to convert vectors to strings. Theoretical results are presented to elucidate the trade-off between approximation quality and computation time. Empirical results show the efficiency of our method in comparison to fast nearest neighbor alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:268", "title": "Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs - Extended Version", "text": "In this paper we propose an algorithm for polynomial-time reinforcement learning in factored Markov decision processes (FMDPs). The factored optimistic initial model (FOIM) algorithm, maintains an empirical model of the FMDP in a conventional way, and always follows a greedy policy with respect to its model. The only trick of the algorithm is that the model is initialized optimistically. We prove that with suitable initialization (i) FOIM converges to the fixed point of approximate value iteration (AVI); (ii) the number of steps when the agent makes non-near-optimal decisions (with respect to the solution of AVI) is polynomial in all relevant quantities; (iii) the per-step costs of the algorithm are also polynomial. To our best knowledge, FOIM is the first algorithm with these properties. This extended version contains the rigorous proofs of the main theorem. A version of this paper appeared in ICML'09.", "source": "arxiv/ml"}
{"id": "arxiv:269", "title": "Introduction to Machine Learning: Class Notes 67577", "text": "Introduction to Machine learning covering Statistical Inference (Bayes, EM, ML/MaxEnt duality), algebraic and spectral methods (PCA, LDA, CCA, Clustering), and PAC learning (the Formal model, VC dimension, Double Sampling theorem).", "source": "arxiv/ml"}
{"id": "arxiv:270", "title": "Considerations upon the Machine Learning Technologies", "text": "Artificial intelligence offers superior techniques and methods by which problems from diverse domains may find an optimal solution. The Machine Learning technologies refer to the domain of artificial intelligence aiming to develop the techniques allowing the computers to \"learn\". Some systems based on Machine Learning technologies tend to eliminate the necessity of the human intelligence while the others adopt a man-machine collaborative approach.", "source": "arxiv/ml"}
{"id": "arxiv:271", "title": "Limits of Learning about a Categorical Latent Variable under Prior Near-Ignorance", "text": "In this paper, we consider the coherent theory of (epistemic) uncertainty of Walley, in which beliefs are represented through sets of probability distributions, and we focus on the problem of modeling prior ignorance about a categorical random variable. In this setting, it is a known result that a state of prior ignorance is not compatible with learning. To overcome this problem, another state of beliefs, called \\emph{near-ignorance}, has been proposed. Near-ignorance resembles ignorance very closely, by satisfying some principles that can arguably be regarded as necessary in a state of ignorance, and allows learning to take place. What this paper does, is to provide new and substantial evidence that also near-ignorance cannot be really regarded as a way out of the problem of starting statistical inference in conditions of very weak beliefs. The key to this result is focusing on a setting characterized by a variable of interest that is \\emph{latent}. We argue that such a setting is by far the most common case in practice, and we provide, for the case of categorical latent variables (and general \\emph{manifest} variables) a condition that, if satisfied, prevents learning to take place under prior near-ignorance. This condition is shown to be easily satisfied even in the most common statistical problems. We regard these results as a strong form of evidence against the possibility to adopt a condition of prior near-ignorance in real statistical problems.", "source": "arxiv/ml"}
{"id": "arxiv:272", "title": "Temporal data mining for root-cause analysis of machine faults in automotive assembly lines", "text": "Engine assembly is a complex and heavily automated distributed-control process, with large amounts of faults data logged everyday. We describe an application of temporal data mining for analyzing fault logs in an engine assembly plant. Frequent episode discovery framework is a model-free method that can be used to deduce (temporal) correlations among events from the logs in an efficient manner. In addition to being theoretically elegant and computationally efficient, frequent episodes are also easy to interpret in the form actionable recommendations. Incorporation of domain-specific information is critical to successful application of the method for analyzing fault logs in the manufacturing domain. We show how domain-specific knowledge can be incorporated using heuristic rules that act as pre-filters and post-filters to frequent episode discovery. The system described here is currently being used in one of the engine assembly plants of General Motors and is planned for adaptation in other plants. To the best of our knowledge, this paper presents the first real, large-scale application of temporal data mining in the manufacturing domain. We believe that the ideas presented in this paper can help practitioners engineer tools for analysis in other similar or related application domains as well.", "source": "arxiv/ml"}
{"id": "arxiv:273", "title": "Continuous Strategy Replicator Dynamics for Multi--Agent Learning", "text": "The problem of multi-agent learning and adaptation has attracted a great deal of attention in recent years. It has been suggested that the dynamics of multi agent learning can be studied using replicator equations from population biology. Most existing studies so far have been limited to discrete strategy spaces with a small number of available actions. In many cases, however, the choices available to agents are better characterized by continuous spectra. This paper suggests a generalization of the replicator framework that allows to study the adaptive dynamics of Q-learning agents with continuous strategy spaces. Instead of probability vectors, agents strategies are now characterized by probability measures over continuous variables. As a result, the ordinary differential equations for the discrete case are replaced by a system of coupled integral--differential replicator equations that describe the mutual evolution of individual agent strategies. We derive a set of functional equations describing the steady state of the replicator dynamics, examine their solutions for several two-player games, and confirm our analytical results using simulations.", "source": "arxiv/ml"}
{"id": "arxiv:274", "title": "Dictionary Identification - Sparse Matrix-Factorisation via $\\ell_1$-Minimisation", "text": "This article treats the problem of learning a dictionary providing sparse representations for a given signal class, via $\\ell_1$-minimisation. The problem can also be seen as factorising a $\\ddim \\times \\nsig$ matrix $Y=(y_1 >... y_\\nsig), y_n\\in \\R^\\ddim$ of training signals into a $\\ddim \\times \\natoms$ dictionary matrix $\\dico$ and a $\\natoms \\times \\nsig$ coefficient matrix $\\X=(x_1... x_\\nsig), x_n \\in \\R^\\natoms$, which is sparse. The exact question studied here is when a dictionary coefficient pair $(\\dico,\\X)$ can be recovered as local minimum of a (nonconvex) $\\ell_1$-criterion with input $Y=\\dico \\X$. First, for general dictionaries and coefficient matrices, algebraic conditions ensuring local identifiability are derived, which are then specialised to the case when the dictionary is a basis. Finally, assuming a random Bernoulli-Gaussian sparse model on the coefficient matrix, it is shown that sufficiently incoherent bases are locally identifiable with high probability. The perhaps surprising result is that the typically sufficient number of training samples $\\nsig$ grows up to a logarithmic factor only linearly with the signal dimension, i.e. $\\nsig \\approx C \\natoms \\log \\natoms$, in contrast to previous approaches requiring combinatorially many samples.", "source": "arxiv/ml"}
{"id": "arxiv:275", "title": "Fast and Near-Optimal Matrix Completion via Randomized Basis Pursuit", "text": "Motivated by the philosophy and phenomenal success of compressed sensing, the problem of reconstructing a matrix from a sampling of its entries has attracted much attention recently. Such a problem can be viewed as an information-theoretic variant of the well-studied matrix completion problem, and the main objective is to design an efficient algorithm that can reconstruct a matrix by inspecting only a small number of its entries. Although this is an impossible task in general, Cand\\`es and co-authors have recently shown that under a so-called incoherence assumption, a rank $r$ $n\\times n$ matrix can be reconstructed using semidefinite programming (SDP) after one inspects $O(nr\\log^6n)$ of its entries. In this paper we propose an alternative approach that is much more efficient and can reconstruct a larger class of matrices by inspecting a significantly smaller number of the entries. Specifically, we first introduce a class of so-called stable matrices and show that it includes all those that satisfy the incoherence assumption. Then, we propose a randomized basis pursuit (RBP) algorithm and show that it can reconstruct a stable rank $r$ $n\\times n$ matrix after inspecting $O(nr\\log n)$ of its entries. Our sampling bound is only a logarithmic factor away from the information-theoretic limit and is essentially optimal. Moreover, the runtime of the RBP algorithm is bounded by $O(nr^2\\log n+n^2r)$, which compares very favorably with the $\\Omega(n^4r^2\\log^{12}n)$ runtime of the SDP-based algorithm. Perhaps more importantly, our algorithm will provide an exact reconstruction of the input matrix in polynomial time. By contrast, the SDP-based algorithm can only provide an approximate one in polynomial time.", "source": "arxiv/ml"}
{"id": "arxiv:276", "title": "Experience-driven formation of parts-based representations in a model of layered visual memory", "text": "Growing neuropsychological and neurophysiological evidence suggests that the visual cortex uses parts-based representations to encode, store and retrieve relevant objects. In such a scheme, objects are represented as a set of spatially distributed local features, or parts, arranged in stereotypical fashion. To encode the local appearance and to represent the relations between the constituent parts, there has to be an appropriate memory structure formed by previous experience with visual objects. Here, we propose a model how a hierarchical memory structure supporting efficient storage and rapid recall of parts-based representations can be established by an experience-driven process of self-organization. The process is based on the collaboration of slow bidirectional synaptic plasticity and homeostatic unit activity regulation, both running at the top of fast activity dynamics with winner-take-all character modulated by an oscillatory rhythm. These neural mechanisms lay down the basis for cooperation and competition between the distributed units and their synaptic connections. Choosing human face recognition as a test task, we show that, under the condition of open-ended, unsupervised incremental learning, the system is able to form memory traces for individual faces in a parts-based fashion. On a lower memory layer the synaptic structure is developed to represent local facial features and their interrelations, while the identities of different persons are captured explicitly on a higher layer. An additional property of the resulting representations is the sparseness of both the activity during the recall and the synaptic patterns comprising the memory traces.", "source": "arxiv/ml"}
{"id": "arxiv:277", "title": "Combining Supervised and Unsupervised Learning for GIS Classification", "text": "This paper presents a new hybrid learning algorithm for unsupervised classification tasks. We combined Fuzzy c-means learning algorithm and a supervised version of Minimerror to develop a hybrid incremental strategy allowing unsupervised classifications. We applied this new approach to a real-world database in order to know if the information contained in unlabeled features of a Geographic Information System (GIS), allows to well classify it. Finally, we compared our results to a classical supervised classification obtained by a multilayer perceptron.", "source": "arxiv/ml"}
{"id": "arxiv:278", "title": "Information-theoretic limits of selecting binary graphical models in high dimensions", "text": "The problem of graphical model selection is to correctly estimate the graph structure of a Markov random field given samples from the underlying distribution. We analyze the information-theoretic limitations of the problem of graph selection for binary Markov random fields under high-dimensional scaling, in which the graph size $p$ and the number of edges $k$, and/or the maximal node degree $d$ are allowed to increase to infinity as a function of the sample size $n$. For pairwise binary Markov random fields, we derive both necessary and sufficient conditions for correct graph selection over the class $\\mathcal{G}_{p,k}$ of graphs on $p$ vertices with at most $k$ edges, and over the class $\\mathcal{G}_{p,d}$ of graphs on $p$ vertices with maximum degree at most $d$. For the class $\\mathcal{G}_{p, k}$, we establish the existence of constants $c$ and $c'$ such that if $\\numobs < c k \\log p$, any method has error probability at least 1/2 uniformly over the family, and we demonstrate a graph decoder that succeeds with high probability uniformly over the family for sample sizes $\\numobs > c' k^2 \\log p$. Similarly, for the class $\\mathcal{G}_{p,d}$, we exhibit constants $c$ and $c'$ such that for $n < c d^2 \\log p$, any method fails with probability at least 1/2, and we demonstrate a graph decoder that succeeds with high probability for $n > c' d^3 \\log p$.", "source": "arxiv/ml"}
{"id": "arxiv:279", "title": "Average-Case Active Learning with Costs", "text": "We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have different costs. Moreover, queries may have more than two possible responses and the distribution over hypotheses may be non uniform. Specific applications include active learning with label costs, active learning for multiclass and partial label queries, and batch mode active learning. We also discuss an approximate version of interest when there are very many queries.", "source": "arxiv/ml"}
{"id": "arxiv:280", "title": "Information Distance in Multiples", "text": "Information distance is a parameter-free similarity measure based on compression, used in pattern recognition, data mining, phylogeny, clustering, and classification. The notion of information distance is extended from pairs to multiples (finite lists). We study maximal overlap, metricity, universality, minimal overlap, additivity, and normalized information distance in multiples. We use the theoretical notion of Kolmogorov complexity which for practical purposes is approximated by the length of the compressed version of the file involved, using a real-world compression program. {\\em Index Terms}-- Information distance, multiples, pattern recognition, data mining, similarity, Kolmogorov complexity", "source": "arxiv/ml"}
{"id": "arxiv:281", "title": "Learning Nonlinear Dynamic Models", "text": "We present a novel approach for learning nonlinear dynamic models, which leads to a new set of tools capable of solving problems that are otherwise difficult. We provide theory showing this new approach is consistent for models with long range structure, and apply the approach to motion capture and high-dimensional video data, yielding results superior to standard alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:282", "title": "Finding Anomalous Periodic Time Series: An Application to Catalogs of Periodic Variable Stars", "text": "Catalogs of periodic variable stars contain large numbers of periodic light-curves (photometric time series data from the astrophysics domain). Separating anomalous objects from well-known classes is an important step towards the discovery of new classes of astronomical objects. Most anomaly detection methods for time series data assume either a single continuous time series or a set of time series whose periods are aligned. Light-curve data precludes the use of these methods as the periods of any given pair of light-curves may be out of sync. One may use an existing anomaly detection method if, prior to similarity calculation, one performs the costly act of aligning two light-curves, an operation that scales poorly to massive data sets. This paper presents PCAD, an unsupervised anomaly detection method for large sets of unsynchronized periodic time-series data, that outputs a ranked list of both global and local anomalies. It calculates its anomaly score for each light-curve in relation to a set of centroids produced by a modified k-means clustering algorithm. Our method is able to scale to large data sets through the use of sampling. We validate our method on both light-curve data and other time series data sets. We demonstrate its effectiveness at finding known anomalies, and discuss the effect of sample size and number of centroids on our results. We compare our method to naive solutions and existing time series anomaly detection methods for unphased data, and show that PCAD's reported anomalies are comparable to or better than all other methods. Finally, astrophysicists on our team have verified that PCAD finds true anomalies that might be indicative of novel astrophysical phenomena.", "source": "arxiv/ml"}
{"id": "arxiv:283", "title": "Quantum Annealing for Clustering", "text": "This paper studies quantum annealing (QA) for clustering, which can be seen as an extension of simulated annealing (SA). We derive a QA algorithm for clustering and propose an annealing schedule, which is crucial in practice. Experiments show the proposed QA algorithm finds better clustering assignments than SA. Furthermore, QA is as easy as SA to implement.", "source": "arxiv/ml"}
{"id": "arxiv:284", "title": "Quantum Annealing for Variational Bayes Inference", "text": "This paper presents studies on a deterministic annealing algorithm based on quantum annealing for variational Bayes (QAVB) inference, which can be seen as an extension of the simulated annealing for variational Bayes (SAVB) inference. QAVB is as easy as SAVB to implement. Experiments revealed QAVB finds a better local optimum than SAVB in terms of the variational free energy in latent Dirichlet allocation (LDA).", "source": "arxiv/ml"}
{"id": "arxiv:285", "title": "Coevolutionary Genetic Algorithms for Establishing Nash Equilibrium in Symmetric Cournot Games", "text": "We use co-evolutionary genetic algorithms to model the players' learning process in several Cournot models, and evaluate them in terms of their convergence to the Nash Equilibrium. The \"social-learning\" versions of the two co-evolutionary algorithms we introduce, establish Nash Equilibrium in those models, in contrast to the \"individual learning\" versions which, as we see here, do not imply the convergence of the players' strategies to the Nash outcome. When players use \"canonical co-evolutionary genetic algorithms\" as learning algorithms, the process of the game is an ergodic Markov Chain, and therefore we analyze simulation results using both the relevant methodology and more general statistical tests, to find that in the \"social\" case, states leading to NE play are highly frequent at the stationary distribution of the chain, in contrast to the \"individual learning\" case, when NE is not reached at all in our simulations; to find that the expected Hamming distance of the states at the limiting distribution from the \"NE state\" is significantly smaller in the \"social\" than in the \"individual learning case\"; to estimate the expected time that the \"social\" algorithms need to get to the \"NE state\" and verify their robustness and finally to show that a large fraction of the games played are indeed at the Nash Equilibrium.", "source": "arxiv/ml"}
{"id": "arxiv:286", "title": "Transfer Learning Using Feature Selection", "text": "We present three related ways of using Transfer Learning to improve feature selection. The three methods address different problems, and hence share different kinds of information between tasks or feature classes, but all three are based on the information theoretic Minimum Description Length (MDL) principle and share the same underlying Bayesian interpretation. The first method, MIC, applies when predictive models are to be built simultaneously for multiple tasks (``simultaneous transfer'') that share the same set of features. MIC allows each feature to be added to none, some, or all of the task models and is most beneficial for selecting a small set of predictive features from a large pool of features, as is common in genomic and biological datasets. Our second method, TPC (Three Part Coding), uses a similar methodology for the case when the features can be divided into feature classes. Our third method, Transfer-TPC, addresses the ``sequential transfer'' problem in which the task to which we want to transfer knowledge may not be known in advance and may have different amounts of data than the other tasks. Transfer-TPC is most beneficial when we want to transfer knowledge between tasks which have unequal amounts of labeled data, for example the data for disambiguating the senses of different verbs. We demonstrate the effectiveness of these approaches with experimental results on real world data pertaining to genomics and to Word Sense Disambiguation (WSD).", "source": "arxiv/ml"}
{"id": "arxiv:287", "title": "A Minimum Description Length Approach to Multitask Feature Selection", "text": "Many regression problems involve not one but several response variables (y's). Often the responses are suspected to share a common underlying structure, in which case it may be advantageous to share information across them; this is known as multitask learning. As a special case, we can use multiple responses to better identify shared predictive features -- a project we might call multitask feature selection. This thesis is organized as follows. Section 1 introduces feature selection for regression, focusing on ell_0 regularization methods and their interpretation within a Minimum Description Length (MDL) framework. Section 2 proposes a novel extension of MDL feature selection to the multitask setting. The approach, called the \"Multiple Inclusion Criterion\" (MIC), is designed to borrow information across regression tasks by more easily selecting features that are associated with multiple responses. We show in experiments on synthetic and real biological data sets that MIC can reduce prediction error in settings where features are at least partially shared across responses. Section 3 surveys hypothesis testing by regression with a single response, focusing on the parallel between the standard Bonferroni correction and an MDL approach. Mirroring the ideas in Section 2, Section 4 proposes a novel MIC approach to hypothesis testing with multiple responses and shows that on synthetic data with significant sharing of features across responses, MIC sometimes outperforms standard FDR-controlling methods in terms of finding true positives for a given level of false positives. Section 5 concludes.", "source": "arxiv/ml"}
{"id": "arxiv:288", "title": "Equations of States in Statistical Learning for a Nonparametrizable and Regular Case", "text": "Many learning machines that have hierarchical structure or hidden variables are now being used in information science, artificial intelligence, and bioinformatics. However, several learning machines used in such fields are not regular but singular statistical models, hence their generalization performance is still left unknown. To overcome these problems, in the previous papers, we proved new equations in statistical learning, by which we can estimate the Bayes generalization loss from the Bayes training loss and the functional variance, on the condition that the true distribution is a singularity contained in a learning machine. In this paper, we prove that the same equations hold even if a true distribution is not contained in a parametric model. Also we prove that, the proposed equations in a regular case are asymptotically equivalent to the Takeuchi information criterion. Therefore, the proposed equations are always applicable without any condition on the unknown true distribution.", "source": "arxiv/ml"}
{"id": "arxiv:289", "title": "An optimal linear separator for the Sonar Signals Classification task", "text": "The problem of classifying sonar signals from rocks and mines first studied by Gorman and Sejnowski has become a benchmark against which many learning algorithms have been tested. We show that both the training set and the test set of this benchmark are linearly separable, although with different hyperplanes. Moreover, the complete set of learning and test patterns together, is also linearly separable. We give the weights that separate these sets, which may be used to compare results found by other algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:290", "title": "Using Genetic Algorithms for Texts Classification Problems", "text": "The avalanche quantity of the information developed by mankind has led to concept of automation of knowledge extraction - Data Mining ([1]). This direction is connected with a wide spectrum of problems - from recognition of the fuzzy set to creation of search machines. Important component of Data Mining is processing of the text information. Such problems lean on concept of classification and clustering ([2]). Classification consists in definition of an accessory of some element (text) to one of in advance created classes. Clustering means splitting a set of elements (texts) on clusters which quantity are defined by localization of elements of the given set in vicinities of these some natural centers of these clusters. Realization of a problem of classification initially should lean on the given postulates, basic of which - the aprioristic information on primary set of texts and a measure of affinity of elements and classes.", "source": "arxiv/ml"}
{"id": "arxiv:291", "title": "Fast Weak Learner Based on Genetic Algorithm", "text": "An approach to the acceleration of parametric weak classifier boosting is proposed. Weak classifier is called parametric if it has fixed number of parameters and, so, can be represented as a point into multidimensional space. Genetic algorithm is used instead of exhaustive search to learn parameters of such classifier. Proposed approach also takes cases when effective algorithm for learning some of the classifier parameters exists into account. Experiments confirm that such an approach can dramatically decrease classifier training time while keeping both training and test errors small.", "source": "arxiv/ml"}
{"id": "arxiv:292", "title": "Feature Reinforcement Learning: Part I: Unstructured MDPs", "text": "General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small finite state Markov decision processes (MDPs). Up to now, extracting the right state representations out of bare observations, that is, reducing the general agent setup to the MDP framework, is an art that involves significant effort by designers. The primary goal of this work is to automate the reduction process and thereby significantly expand the scope of many existing reinforcement learning algorithms and the agents that employ them. Before we can think of mechanizing this search for suitable MDPs, we need a formal objective criterion. The main contribution of this article is to develop such a criterion. I also integrate the various parts into one learning algorithm. Extensions to more realistic dynamic Bayesian networks are developed in Part II. The role of POMDPs is also considered there.", "source": "arxiv/ml"}
{"id": "arxiv:293", "title": "Large-Margin kNN Classification Using a Deep Encoder Network", "text": "KNN is one of the most popular classification methods, but it often fails to work well with inappropriate choice of distance metric or due to the presence of numerous class-irrelevant features. Linear feature transformation methods have been widely applied to extract class-relevant information to improve kNN classification, which is very limited in many applications. Kernels have been used to learn powerful non-linear feature transformations, but these methods fail to scale to large datasets. In this paper, we present a scalable non-linear feature mapping method based on a deep neural network pretrained with restricted boltzmann machines for improving kNN classification in a large-margin framework, which we call DNet-kNN. DNet-kNN can be used for both classification and for supervised dimensionality reduction. The experimental results on two benchmark handwritten digit datasets show that DNet-kNN has much better performance than large-margin kNN using a linear mapping and kNN based on a deep autoencoder pretrained with retricted boltzmann machines.", "source": "arxiv/ml"}
{"id": "arxiv:294", "title": "Matrix Completion from Noisy Entries", "text": "Given a matrix M of low-rank, we consider the problem of reconstructing it from noisy observations of a small, random subset of its entries. The problem arises in a variety of applications, from collaborative filtering (the `Netflix problem') to structure-from-motion and positioning. We study a low complexity algorithm introduced by Keshavan et al.(2009), based on a combination of spectral techniques and manifold optimization, that we call here OptSpace. We prove performance guarantees that are order-optimal in a number of circumstances.", "source": "arxiv/ml"}
{"id": "arxiv:295", "title": "Bayesian History Reconstruction of Complex Human Gene Clusters on a Phylogeny", "text": "Clusters of genes that have evolved by repeated segmental duplication present difficult challenges throughout genomic analysis, from sequence assembly to functional analysis. Improved understanding of these clusters is of utmost importance, since they have been shown to be the source of evolutionary innovation, and have been linked to multiple diseases, including HIV and a variety of cancers. Previously, Zhang et al. (2008) developed an algorithm for reconstructing parsimonious evolutionary histories of such gene clusters, using only human genomic sequence data. In this paper, we propose a probabilistic model for the evolution of gene clusters on a phylogeny, and an MCMC algorithm for reconstruction of duplication histories from genomic sequences in multiple species. Several projects are underway to obtain high quality BAC-based assemblies of duplicated clusters in multiple species, and we anticipate that our method will be useful in analyzing these valuable new data sets.", "source": "arxiv/ml"}
{"id": "arxiv:296", "title": "Entropy Message Passing", "text": "The paper proposes a new message passing algorithm for cycle-free factor graphs. The proposed \"entropy message passing\" (EMP) algorithm may be viewed as sum-product message passing over the entropy semiring, which has previously appeared in automata theory. The primary use of EMP is to compute the entropy of a model. However, EMP can also be used to compute expressions that appear in expectation maximization and in gradient descent algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:297", "title": "Bayesian Forecasting of WWW Traffic on the Time Varying Poisson Model", "text": "Traffic forecasting from past observed traffic data with small calculation complexity is one of important problems for planning of servers and networks. Focusing on World Wide Web (WWW) traffic as fundamental investigation, this paper would deal with Bayesian forecasting of network traffic on the time varying Poisson model from a viewpoint from statistical decision theory. Under this model, we would show that the estimated forecasting value is obtained by simple arithmetic calculation and expresses real WWW traffic well from both theoretical and empirical points of view.", "source": "arxiv/ml"}
{"id": "arxiv:298", "title": "Bayesian two-sample tests", "text": "In this paper, we present two classes of Bayesian approaches to the two-sample problem. Our first class of methods extends the Bayesian t-test to include all parametric models in the exponential family and their conjugate priors. Our second class of methods uses Dirichlet process mixtures (DPM) of such conjugate-exponential distributions as flexible nonparametric priors over the unknown distributions.", "source": "arxiv/ml"}
{"id": "arxiv:299", "title": "Rough Set Model for Discovering Hybrid Association Rules", "text": "In this paper, the mining of hybrid association rules with rough set approach is investigated as the algorithm RSHAR.The RSHAR algorithm is constituted of two steps mainly. At first, to join the participant tables into a general table to generate the rules which is expressing the relationship between two or more domains that belong to several different tables in a database. Then we apply the mapping code on selected dimension, which can be added directly into the information system as one certain attribute. To find the association rules, frequent itemsets are generated in second step where candidate itemsets are generated through equivalence classes and also transforming the mapping code in to real dimensions. The searching method for candidate itemset is similar to apriori algorithm. The analysis of the performance of algorithm has been carried out.", "source": "arxiv/ml"}
{"id": "arxiv:300", "title": "Learning with Spectral Kernels and Heavy-Tailed Data", "text": "Two ubiquitous aspects of large-scale data analysis are that the data often have heavy-tailed properties and that diffusion-based or spectral-based methods are often used to identify and extract structure of interest. Perhaps surprisingly, popular distribution-independent methods such as those based on the VC dimension fail to provide nontrivial results for even simple learning problems such as binary classification in these two settings. In this paper, we develop distribution-dependent learning methods that can be used to provide dimension-independent sample complexity bounds for the binary classification problem in these two popular settings. In particular, we provide bounds on the sample complexity of maximum margin classifiers when the magnitude of the entries in the feature vector decays according to a power law and also when learning is performed with the so-called Diffusion Maps kernel. Both of these results rely on bounding the annealed entropy of gap-tolerant classifiers in a Hilbert space. We provide such a bound, and we demonstrate that our proof technique generalizes to the case when the margin is measured with respect to more general Banach space norms. The latter result is of potential interest in cases where modeling the relationship between data elements as a dot product in a Hilbert space is too restrictive.", "source": "arxiv/ml"}
{"id": "arxiv:301", "title": "On landmark selection and sampling in high-dimensional data analysis", "text": "In recent years, the spectral analysis of appropriately defined kernel matrices has emerged as a principled way to extract the low-dimensional structure often prevalent in high-dimensional data. Here we provide an introduction to spectral methods for linear and nonlinear dimension reduction, emphasizing ways to overcome the computational limitations currently faced by practitioners with massive datasets. In particular, a data subsampling or landmark selection process is often employed to construct a kernel based on partial information, followed by an approximate spectral analysis termed the Nystrom extension. We provide a quantitative framework to analyse this procedure, and use it to demonstrate algorithmic performance bounds on a range of practical approaches designed to optimize the landmark selection process. We compare the practical implications of these bounds by way of real-world examples drawn from the field of computer vision, whereby low-dimensional manifold structure is shown to emerge from high-dimensional video data streams.", "source": "arxiv/ml"}
{"id": "arxiv:302", "title": "Acquiring Knowledge for Evaluation of Teachers Performance in Higher Education using a Questionnaire", "text": "In this paper, we present the step by step knowledge acquisition process by choosing a structured method through using a questionnaire as a knowledge acquisition tool. Here we want to depict the problem domain as, how to evaluate teachers performance in higher education through the use of expert system technology. The problem is how to acquire the specific knowledge for a selected problem efficiently and effectively from human experts and encode it in the suitable computer format. Acquiring knowledge from human experts in the process of expert systems development is one of the most common problems cited till yet. This questionnaire was sent to 87 domain experts within all public and private universities in Pakistani. Among them 25 domain experts sent their valuable opinions. Most of the domain experts were highly qualified, well experienced and highly responsible persons. The whole questionnaire was divided into 15 main groups of factors, which were further divided into 99 individual questions. These facts were analyzed further to give a final shape to the questionnaire. This knowledge acquisition technique may be used as a learning tool for further research work.", "source": "arxiv/ml"}
{"id": "arxiv:303", "title": "Minimum Probability Flow Learning", "text": "Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable normalization factor or sampling from the equilibrium distribution of the model. This is achieved by establishing dynamics that would transform the observed data distribution into the model distribution, and then setting as the objective the minimization of the KL divergence between the data distribution and the distribution produced by running the dynamics for an infinitesimal time. Score matching, minimum velocity learning, and certain forms of contrastive divergence are shown to be special cases of this learning technique. We demonstrate parameter estimation in Ising models, deep belief networks and an independent component analysis model of natural scenes. In the Ising model case, current state of the art techniques are outperformed by at least an order of magnitude in learning time, with lower error in recovered coupling parameters.", "source": "arxiv/ml"}
{"id": "arxiv:304", "title": "Statistical Analysis of Privacy and Anonymity Guarantees in Randomized Security Protocol Implementations", "text": "Security protocols often use randomization to achieve probabilistic non-determinism. This non-determinism, in turn, is used in obfuscating the dependence of observable values on secret data. Since the correctness of security protocols is very important, formal analysis of security protocols has been widely studied in literature. Randomized security protocols have also been analyzed using formal techniques such as process-calculi and probabilistic model checking. In this paper, we consider the problem of validating implementations of randomized protocols. Unlike previous approaches which treat the protocol as a white-box, our approach tries to verify an implementation provided as a black box. Our goal is to infer the secrecy guarantees provided by a security protocol through statistical techniques. We learn the probabilistic dependency of the observable outputs on secret inputs using Bayesian network. This is then used to approximate the leakage of secret. In order to evaluate the accuracy of our statistical approach, we compare our technique with the probabilistic model checking technique on two examples: crowds protocol and dining crypotgrapher's protocol.", "source": "arxiv/ml"}
{"id": "arxiv:305", "title": "Unsupervised Search-based Structured Prediction", "text": "We describe an adaptation and application of a search-based structured prediction algorithm \"Searn\" to unsupervised learning problems. We show that it is possible to reduce unsupervised learning to supervised learning and demonstrate a high-quality unsupervised shift-reduce parsing model. We additionally show a close connection between unsupervised Searn and expectation maximization. Finally, we demonstrate the efficacy of a semi-supervised extension. The key idea that enables this is an application of the predict-self idea for unsupervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:306", "title": "Online Reinforcement Learning for Dynamic Multimedia Systems", "text": "In our previous work, we proposed a systematic cross-layer framework for dynamic multimedia systems, which allows each layer to make autonomous and foresighted decisions that maximize the system's long-term performance, while meeting the application's real-time delay constraints. The proposed solution solved the cross-layer optimization offline, under the assumption that the multimedia system's probabilistic dynamics were known a priori. In practice, however, these dynamics are unknown a priori and therefore must be learned online. In this paper, we address this problem by allowing the multimedia system layers to learn, through repeated interactions with each other, to autonomously optimize the system's long-term performance at run-time. We propose two reinforcement learning algorithms for optimizing the system under different design constraints: the first algorithm solves the cross-layer optimization in a centralized manner, and the second solves it in a decentralized manner. We analyze both algorithms in terms of their required computation, memory, and inter-layer communication overheads. After noting that the proposed reinforcement learning algorithms learn too slowly, we introduce a complementary accelerated learning algorithm that exploits partial knowledge about the system's dynamics in order to dramatically improve the system's performance. In our experiments, we demonstrate that decentralized learning can perform as well as centralized learning, while enabling the layers to act autonomously. Additionally, we show that existing application-independent reinforcement learning algorithms, and existing myopic learning algorithms deployed in multimedia systems, perform significantly worse than our proposed application-aware and foresighted learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:307", "title": "A new model of artificial neuron: cyberneuron and its use", "text": "This article describes a new type of artificial neuron, called the authors \"cyberneuron\". Unlike classical models of artificial neurons, this type of neuron used table substitution instead of the operation of multiplication of input values for the weights. This allowed to significantly increase the information capacity of a single neuron, but also greatly simplify the process of learning. Considered an example of the use of \"cyberneuron\" with the task of detecting computer viruses.", "source": "arxiv/ml"}
{"id": "arxiv:308", "title": "Random DFAs are Efficiently PAC Learnable", "text": "This paper has been withdrawn due to an error found by Dana Angluin and Lev Reyzin.", "source": "arxiv/ml"}
{"id": "arxiv:309", "title": "Open Problems in Universal Induction & Intelligence", "text": "Specialized intelligent systems can be found everywhere: finger print, handwriting, speech, and face recognition, spam filtering, chess and other game programs, robots, et al. This decade the first presumably complete mathematical theory of artificial intelligence based on universal induction-prediction-decision-action has been proposed. This information-theoretic approach solidifies the foundations of inductive inference and artificial intelligence. Getting the foundations right usually marks a significant progress and maturing of a field. The theory provides a gold standard and guidance for researchers working on intelligent algorithms. The roots of universal induction have been laid exactly half-a-century ago and the roots of universal intelligence exactly one decade ago. So it is timely to take stock of what has been achieved and what remains to be done. Since there are already good recent surveys, I describe the state-of-the-art only in passing and refer the reader to the literature. This article concentrates on the open problems in universal induction and its extension to universal intelligence.", "source": "arxiv/ml"}
{"id": "arxiv:310", "title": "Bayesian Multitask Learning with Latent Hierarchies", "text": "We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previously proposed multitask learning models and performs well on three distinct real-world data sets.", "source": "arxiv/ml"}
{"id": "arxiv:311", "title": "Cross-Task Knowledge-Constrained Self Training", "text": "We present an algorithmic framework for learning multiple related tasks. Our framework exploits a form of prior knowledge that relates the output spaces of these tasks. We present PAC learning results that analyze the conditions under which such learning is possible. We present results on learning a shallow parser and named-entity recognition system that exploits our framework, showing consistent improvements over baseline methods.", "source": "arxiv/ml"}
{"id": "arxiv:312", "title": "Search-based Structured Prediction", "text": "We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Searn is a meta-algorithm that transforms these complex problems into simple classification problems to which any binary classifier may be applied. Unlike current algorithms for structured learning that require decomposition of both the loss function and the feature functions over the predicted structure, Searn is able to learn prediction functions for any loss function and any class of features. Moreover, Searn comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies good performance on the structured prediction problem.", "source": "arxiv/ml"}
{"id": "arxiv:313", "title": "A Bayesian Model for Supervised Clustering with the Dirichlet Process Prior", "text": "We develop a Bayesian framework for tackling the supervised clustering problem, the generic problem encountered in tasks such as reference matching, coreference resolution, identity uncertainty and record linkage. Our clustering model is based on the Dirichlet process prior, which enables us to define distributions over the countably infinite sets that naturally arise in this problem. We add supervision to our model by positing the existence of a set of unobserved random variables (we call these \"reference types\") that are generic across all clusters. Inference in our framework, which requires integrating over infinitely many parameters, is solved using Markov chain Monte Carlo techniques. We present algorithms for both conjugate and non-conjugate priors. We present a simple--but general--parameterization of our model based on a Gaussian assumption. We evaluate this model on one artificial task and three real-world tasks, comparing it against both unsupervised and state-of-the-art supervised algorithms. Our results show that our model is able to outperform other models across a variety of tasks and performance metrics.", "source": "arxiv/ml"}
{"id": "arxiv:314", "title": "Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction", "text": "Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be performed exactly. Unfortunately, in many complex problems, it is rare that exact search or parameter estimation is tractable. Instead of learning exact models and searching via heuristic means, we embrace this difficulty and treat the structured output problem in terms of approximate search. We present a framework for learning as search optimization, and two parameter updates with convergence theorems and bounds. Empirical evidence shows that our integrated approach to learning and decoding can outperform exact models at smaller computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:315", "title": "Learning Gaussian Mixtures with Arbitrary Separation", "text": "In this paper we present a method for learning the parameters of a mixture of $k$ identical spherical Gaussians in $n$-dimensional space with an arbitrarily small separation between the components. Our algorithm is polynomial in all parameters other than $k$. The algorithm is based on an appropriate grid search over the space of parameters. The theoretical analysis of the algorithm hinges on a reduction of the problem to 1 dimension and showing that two 1-dimensional mixtures whose densities are close in the $L^2$ norm must have similar means and mixing coefficients. To produce such a lower bound for the $L^2$ norm in terms of the distances between the corresponding means, we analyze the behavior of the Fourier transform of a mixture of Gaussians in 1 dimension around the origin, which turns out to be closely related to the properties of the Vandermonde matrix obtained from the component means. Analysis of this matrix together with basic function approximation results allows us to provide a lower bound for the norm of the mixture in the Fourier domain. In recent years much research has been aimed at understanding the computational aspects of learning parameters of Gaussians mixture distributions in high dimension. To the best of our knowledge all existing work on learning parameters of Gaussian mixtures assumes minimum separation between components of the mixture which is an increasing function of either the dimension of the space $n$ or the number of components $k$. In our paper we prove the first result showing that parameters of a $n$-dimensional Gaussian mixture model with arbitrarily small component separation can be learned in time polynomial in $n$.", "source": "arxiv/ml"}
{"id": "arxiv:316", "title": "Privacy constraints in regularized convex optimization", "text": "This paper is withdrawn due to some errors, which are corrected in arXiv:0912.0071v4 [cs.LG].", "source": "arxiv/ml"}
{"id": "arxiv:317", "title": "Fast search for Dirichlet process mixture models", "text": "Dirichlet process (DP) mixture models provide a flexible Bayesian framework for density estimation. Unfortunately, their flexibility comes at a cost: inference in DP mixture models is computationally expensive, even when conjugate distributions are used. In the common case when one seeks only a maximum a posteriori assignment of data points to clusters, we show that search algorithms provide a practical alternative to expensive MCMC and variational techniques. When a true posterior sample is desired, the solution found by search can serve as a good initializer for MCMC. Experimental results show that using these techniques is it possible to apply DP mixture models to very large data sets.", "source": "arxiv/ml"}
{"id": "arxiv:318", "title": "Bayesian Query-Focused Summarization", "text": "We present BayeSum (for ``Bayesian summarization''), a model for sentence extraction in query-focused summarization. BayeSum leverages the common case in which multiple documents are relevant to a single query. Using these documents as reinforcement for query terms, BayeSum is not afflicted by the paucity of information in short queries. We show that approximate inference in BayeSum is possible on large data sets and results in a state-of-the-art summarization system. Furthermore, we show how BayeSum can be understood as a justified query expansion technique in the language modeling for IR framework.", "source": "arxiv/ml"}
{"id": "arxiv:319", "title": "Frustratingly Easy Domain Adaptation", "text": "We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough ``target'' data to do slightly better than just using only ``source'' data. Our approach is incredibly simple, easy to implement as a preprocessing step (10 lines of Perl!) and outperforms state-of-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multi-domain adaptation problem, where one has data from a variety of different domains.", "source": "arxiv/ml"}
{"id": "arxiv:320", "title": "Learning Equilibria in Games by Stochastic Distributed Algorithms", "text": "We consider a class of fully stochastic and fully distributed algorithms, that we prove to learn equilibria in games. Indeed, we consider a family of stochastic distributed dynamics that we prove to converge weakly (in the sense of weak convergence for probabilistic processes) towards their mean-field limit, i.e an ordinary differential equation (ODE) in the general case. We focus then on a class of stochastic dynamics where this ODE turns out to be related to multipopulation replicator dynamics. Using facts known about convergence of this ODE, we discuss the convergence of the initial stochastic dynamics: For general games, there might be non-convergence, but when convergence of the ODE holds, considered stochastic algorithms converge towards Nash equilibria. For games admitting Lyapunov functions, that we call Lyapunov games, the stochastic dynamics converge. We prove that any ordinal potential game, and hence any potential game is a Lyapunov game, with a multiaffine Lyapunov function. For Lyapunov games with a multiaffine Lyapunov function, we prove that this Lyapunov function is a super-martingale over the stochastic dynamics. This leads a way to provide bounds on their time of convergence by martingale arguments. This applies in particular for many classes of games that have been considered in literature, including several load balancing game scenarios and congestion games.", "source": "arxiv/ml"}
{"id": "arxiv:321", "title": "An Augmented Lagrangian Approach for Sparse Principal Component Analysis", "text": "Principal component analysis (PCA) is a widely used technique for data analysis and dimension reduction with numerous applications in science and engineering. However, the standard PCA suffers from the fact that the principal components (PCs) are usually linear combinations of all the original variables, and it is thus often difficult to interpret the PCs. To alleviate this drawback, various sparse PCA approaches were proposed in literature [15, 6, 17, 28, 8, 25, 18, 7, 16]. Despite success in achieving sparsity, some important properties enjoyed by the standard PCA are lost in these methods such as uncorrelation of PCs and orthogonality of loading vectors. Also, the total explained variance that they attempt to maximize can be too optimistic. In this paper we propose a new formulation for sparse PCA, aiming at finding sparse and nearly uncorrelated PCs with orthogonal loading vectors while explaining as much of the total variance as possible. We also develop a novel augmented Lagrangian method for solving a class of nonsmooth constrained optimization problems, which is well suited for our formulation of sparse PCA. We show that it converges to a feasible point, and moreover under some regularity assumptions, it converges to a stationary point. Additionally, we propose two nonmonotone gradient methods for solving the augmented Lagrangian subproblems, and establish their global and local convergence. Finally, we compare our sparse PCA approach with several existing methods on synthetic, random, and real data, respectively. The computational results demonstrate that the sparse PCs produced by our approach substantially outperform those by other methods in terms of total explained variance, correlation of PCs, and orthogonality of loading vectors.", "source": "arxiv/ml"}
{"id": "arxiv:322", "title": "Network-aware Adaptation with Real-Time Channel Statistics for Wireless LAN Multimedia Transmissions in the Digital Home", "text": "This paper suggests the use of intelligent network-aware processing agents in wireless local area network drivers to generate metrics for bandwidth estimation based on real-time channel statistics to enable wireless multimedia application adaptation. Various configurations in the wireless digital home are studied and the experimental results with performance variations are presented.", "source": "arxiv/ml"}
{"id": "arxiv:323", "title": "Neural Modeling and Control of Diesel Engine with Pollution Constraints", "text": "The paper describes a neural approach for modelling and control of a turbocharged Diesel engine. A neural model, whose structure is mainly based on some physical equations describing the engine behaviour, is built for the rotation speed and the exhaust gas opacity. The model is composed of three interconnected neural submodels, each of them constituting a nonlinear multi-input single-output error model. The structural identification and the parameter estimation from data gathered on a real engine are described. The neural direct model is then used to determine a neural controller of the engine, in a specialized training scheme minimising a multivariable criterion. Simulations show the effect of the pollution constraint weighting on a trajectory tracking of the engine speed. Neural networks, which are flexible and parsimonious nonlinear black-box models, with universal approximation capabilities, can accurately describe or control complex nonlinear systems, with little a priori theoretical knowledge. The presented work extends optimal neuro-control to the multivariable case and shows the flexibility of neural optimisers. Considering the preliminary results, it appears that neural networks can be used as embedded models for engine control, to satisfy the more and more restricting pollutant emission legislation. Particularly, they are able to model nonlinear dynamics and outperform during transients the control schemes based on static mappings.", "source": "arxiv/ml"}
{"id": "arxiv:324", "title": "Contextual Bandits with Similarity Information", "text": "In a multi-armed bandit (MAB) problem, an online algorithm makes a sequence of choices. In each round it chooses from a time-invariant set of alternatives and receives the payoff associated with this alternative. While the case of small strategy sets is by now well-understood, a lot of recent work has focused on MAB problems with exponentially or infinitely large strategy sets, where one needs to assume extra structure in order to make the problem tractable. In particular, recent literature considered information on similarity between arms. We consider similarity information in the setting of \"contextual bandits\", a natural extension of the basic MAB problem where before each round an algorithm is given the \"context\" -- a hint about the payoffs in this round. Contextual bandits are directly motivated by placing advertisements on webpages, one of the crucial problems in sponsored search. A particularly simple way to represent similarity information in the contextual bandit setting is via a \"similarity distance\" between the context-arm pairs which gives an upper bound on the difference between the respective expected payoffs. Prior work on contextual bandits with similarity uses \"uniform\" partitions of the similarity space, which is potentially wasteful. We design more efficient algorithms that are based on adaptive partitions adjusted to \"popular\" context and \"high-payoff\" arms.", "source": "arxiv/ml"}
{"id": "arxiv:325", "title": "Online Learning for Matrix Factorization and Sparse Coding", "text": "Sparse coding--that is, modelling data vectors as sparse linear combinations of basis elements--is widely used in machine learning, neuroscience, signal processing, and statistics. This paper focuses on the large-scale matrix factorization problem that consists of learning the basis set, adapting it to specific data. Variations of this problem include dictionary learning in signal processing, non-negative matrix factorization and sparse principal component analysis. In this paper, we propose to address these tasks with a new online optimization algorithm, based on stochastic approximations, which scales up gracefully to large datasets with millions of training samples, and extends naturally to various matrix factorization formulations, making it suitable for a wide range of learning problems. A proof of convergence is presented, along with experiments with natural images and genomic data demonstrating that it leads to state-of-the-art performance in terms of speed and optimization for both small and large datasets.", "source": "arxiv/ml"}
{"id": "arxiv:326", "title": "Regret Bounds for Opportunistic Channel Access", "text": "We consider the task of opportunistic channel access in a primary system composed of independent Gilbert-Elliot channels where the secondary (or opportunistic) user does not dispose of a priori information regarding the statistical characteristics of the system. It is shown that this problem may be cast into the framework of model-based learning in a specific class of Partially Observed Markov Decision Processes (POMDPs) for which we introduce an algorithm aimed at striking an optimal tradeoff between the exploration (or estimation) and exploitation requirements. We provide finite horizon regret bounds for this algorithm as well as a numerical evaluation of its performance in the single channel model as well as in the case of stochastically identical channels.", "source": "arxiv/ml"}
{"id": "arxiv:327", "title": "The Infinite Hierarchical Factor Regression Model", "text": "We propose a nonparametric Bayesian factor regression model that accounts for uncertainty in the number of factors, and the relationship between factors. To accomplish this, we propose a sparse variant of the Indian Buffet Process and couple this with a hierarchical model over factors, based on Kingman's coalescent. We apply this model to two problems (factor analysis and factor regression) in gene-expression data analysis.", "source": "arxiv/ml"}
{"id": "arxiv:328", "title": "Streamed Learning: One-Pass SVMs", "text": "We present a streaming model for large-scale classification (in the context of $\\ell_2$-SVM) by leveraging connections between learning and computational geometry. The streaming model imposes the constraint that only a single pass over the data is allowed. The $\\ell_2$-SVM is known to have an equivalent formulation in terms of the minimum enclosing ball (MEB) problem, and an efficient algorithm based on the idea of \\emph{core sets} exists (Core Vector Machine, CVM). CVM learns a $(1+\\varepsilon)$-approximate MEB for a set of points and yields an approximate solution to corresponding SVM instance. However CVM works in batch mode requiring multiple passes over the data. This paper presents a single-pass SVM which is based on the minimum enclosing ball of streaming data. We show that the MEB updates for the streaming case can be easily adapted to learn the SVM weight vector in a way similar to using online stochastic gradient updates. Our algorithm performs polylogarithmic computation at each example, and requires very small and constant storage. Experimental results show that, even in such restrictive settings, we can learn efficiently in just one pass and get accuracies comparable to other state-of-the-art SVM solvers (batch and online). We also give an analysis of the algorithm, and discuss some open issues and possible extensions.", "source": "arxiv/ml"}
{"id": "arxiv:329", "title": "Online Learning of Assignments that Maximize Submodular Functions", "text": "Which ads should we display in sponsored search in order to maximize our revenue? How should we dynamically rank information sources to maximize value of information? These applications exhibit strong diminishing returns: Selection of redundant ads and information sources decreases their marginal utility. We show that these and other problems can be formalized as repeatedly selecting an assignment of items to positions to maximize a sequence of monotone submodular functions that arrive one by one. We present an efficient algorithm for this general problem and analyze it in the no-regret model. Our algorithm possesses strong theoretical guarantees, such as a performance ratio that converges to the optimal constant of 1-1/e. We empirically evaluate our algorithm on two real-world online optimization problems on the web: ad allocation with submodular utilities, and dynamically ranking blogs to detect information cascades.", "source": "arxiv/ml"}
{"id": "arxiv:330", "title": "Clustering for Improved Learning in Maze Traversal Problem", "text": "The maze traversal problem (finding the shortest distance to the goal from any position in a maze) has been an interesting challenge in computational intelligence. Recent work has shown that the cellular simultaneous recurrent neural network (CSRN) can solve this problem for simple mazes. This thesis focuses on exploiting relevant information about the maze to improve learning and decrease the training time for the CSRN to solve mazes. Appropriate variables are identified to create useful clusters using relevant information. The CSRN was next modified to allow for an additional external input. With this additional input, several methods were tested and results show that clustering the mazes improves the overall learning of the traversal problem for the CSRN.", "source": "arxiv/ml"}
{"id": "arxiv:331", "title": "An Application of Bayesian classification to Interval Encoded Temporal mining with prioritized items", "text": "In real life, media information has time attributes either implicitly or explicitly known as temporal data. This paper investigates the usefulness of applying Bayesian classification to an interval encoded temporal database with prioritized items. The proposed method performs temporal mining by encoding the database with weighted items which prioritizes the items according to their importance from the user perspective. Naive Bayesian classification helps in making the resulting temporal rules more effective. The proposed priority based temporal mining (PBTM) method added with classification aids in solving problems in a well informed and systematic manner. The experimental results are obtained from the complaints database of the telecommunications system, which shows the feasibility of this method of classification based temporal mining.", "source": "arxiv/ml"}
{"id": "arxiv:332", "title": "Approximating the Permanent with Belief Propagation", "text": "This work describes a method of approximating matrix permanents efficiently using belief propagation. We formulate a probability distribution whose partition function is exactly the permanent, then use Bethe free energy to approximate this partition function. After deriving some speedups to standard belief propagation, the resulting algorithm requires $(n^2)$ time per iteration. Finally, we demonstrate the advantages of using this approximation.", "source": "arxiv/ml"}
{"id": "arxiv:333", "title": "Rate Constrained Random Access over a Fading Channel", "text": "In this paper, we consider uplink transmissions involving multiple users communicating with a base station over a fading channel. We assume that the base station does not coordinate the transmissions of the users and hence the users employ random access communication. The situation is modeled as a non-cooperative repeated game with incomplete information. Each user attempts to minimize its long term power consumption subject to a minimum rate requirement. We propose a two timescale stochastic gradient algorithm (TTSGA) for tuning the users' transmission probabilities. The algorithm includes a 'waterfilling threshold update mechanism' that ensures that the rate constraints are satisfied. We prove that under the algorithm, the users' transmission probabilities converge to a Nash equilibrium. Moreover, we also prove that the rate constraints are satisfied; this is also demonstrated using simulation studies.", "source": "arxiv/ml"}
{"id": "arxiv:334", "title": "Uncovering delayed patterns in noisy and irregularly sampled time series: an astronomy application", "text": "We study the problem of estimating the time delay between two signals representing delayed, irregularly sampled and noisy versions of the same underlying pattern. We propose and demonstrate an evolutionary algorithm for the (hyper)parameter estimation of a kernel-based technique in the context of an astronomical problem, namely estimating the time delay between two gravitationally lensed signals from a distant quasar. Mixed types (integer and real) are used to represent variables within the evolutionary algorithm. We test the algorithm on several artificial data sets, and also on real astronomical observations of quasar Q0957+561. By carrying out a statistical analysis of the results we present a detailed comparison of our method with the most popular methods for time delay estimation in astrophysics. Our method yields more accurate and more stable time delay estimates: for Q0957+561, we obtain 419.6 days for the time delay between images A and B. Our methodology can be readily applied to current state-of-the-art optical monitoring data in astronomy, but can also be applied in other disciplines involving similar time series data.", "source": "arxiv/ml"}
{"id": "arxiv:335", "title": "ABC-LogitBoost for Multi-class Classification", "text": "We develop abc-logitboost, based on the prior work on abc-boost and robust logitboost. Our extensive experiments on a variety of datasets demonstrate the considerable improvement of abc-logitboost over logitboost and abc-mart.", "source": "arxiv/ml"}
{"id": "arxiv:336", "title": "Rare-Allele Detection Using Compressed Se(que)nsing", "text": "Detection of rare variants by resequencing is important for the identification of individuals carrying disease variants. Rapid sequencing by new technologies enables low-cost resequencing of target regions, although it is still prohibitive to test more than a few individuals. In order to improve cost trade-offs, it has recently been suggested to apply pooling designs which enable the detection of carriers of rare alleles in groups of individuals. However, this was shown to hold only for a relatively low number of individuals in a pool, and requires the design of pooling schemes for particular cases. We propose a novel pooling design, based on a compressed sensing approach, which is both general, simple and efficient. We model the experimental procedure and show via computer simulations that it enables the recovery of rare allele carriers out of larger groups than were possible before, especially in situations where high coverage is obtained for each individual. Our approach can also be combined with barcoding techniques to enhance performance and provide a feasible solution based on current resequencing costs. For example, when targeting a small enough genomic region (~100 base-pairs) and using only ~10 sequencing lanes and ~10 distinct barcodes, one can recover the identity of 4 rare allele carriers out of a population of over 4000 individuals.", "source": "arxiv/ml"}
{"id": "arxiv:337", "title": "Advances in Feature Selection with Mutual Information", "text": "The selection of features that are relevant for a prediction or classification problem is an important problem in many domains involving high-dimensional data. Selecting features helps fighting the curse of dimensionality, improving the performances of prediction or classification methods, and interpreting the application. In a nonlinear context, the mutual information is widely used as relevance criterion for features and sets of features. Nevertheless, it suffers from at least three major limitations: mutual information estimators depend on smoothing parameters, there is no theoretically justified stopping criterion in the feature selection greedy procedure, and the estimation itself suffers from the curse of dimensionality. This chapter shows how to deal with these problems. The two first ones are addressed by using resampling techniques that provide a statistical basis to select the estimator parameters and to stop the search procedure. The third one is addressed by modifying the mutual information criterion into a measure of how features are complementary (and not only informative) for the problem at hand.", "source": "arxiv/ml"}
{"id": "arxiv:338", "title": "Median topographic maps for biomedical data sets", "text": "Median clustering extends popular neural data analysis methods such as the self-organizing map or neural gas to general data structures given by a dissimilarity matrix only. This offers flexible and robust global data inspection methods which are particularly suited for a variety of data as occurs in biomedical domains. In this chapter, we give an overview about median clustering and its properties and extensions, with a particular focus on efficient implementations adapted to large scale data analysis.", "source": "arxiv/ml"}
{"id": "arxiv:339", "title": "Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization EM training and Viterbi training", "text": "Background: Hidden Markov models are widely employed by numerous bioinformatics programs used today. Applications range widely from comparative gene prediction to time-series analyses of micro-array data. The parameters of the underlying models need to be adjusted for specific data sets, for example the genome of a particular species, in order to maximize the prediction accuracy. Computationally efficient algorithms for parameter training are thus key to maximizing the usability of a wide range of bioinformatics applications. Results: We introduce two computationally efficient training algorithms, one for Viterbi training and one for stochastic expectation maximization (EM) training, which render the memory requirements independent of the sequence length. Unlike the existing algorithms for Viterbi and stochastic EM training which require a two-step procedure, our two new algorithms require only one step and scan the input sequence in only one direction. We also implement these two new algorithms and the already published linear-memory algorithm for EM training into the hidden Markov model compiler HMM-Converter and examine their respective practical merits for three small example models. Conclusions: Bioinformatics applications employing hidden Markov models can use the two algorithms in order to make Viterbi training and stochastic EM training more computationally efficient. Using these algorithms, parameter training can thus be attempted for more complex models and longer training sequences. The two new algorithms have the added advantage of being easier to implement than the corresponding default algorithms for Viterbi training and stochastic EM training.", "source": "arxiv/ml"}
{"id": "arxiv:340", "title": "A Monte Carlo AIXI Approximation", "text": "This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents. Previously, it has been unclear whether the theory of AIXI could motivate the design of practical algorithms. We answer this hitherto open question in the affirmative, by providing the first computationally feasible approximation to the AIXI agent. To develop our approximation, we introduce a new Monte-Carlo Tree Search algorithm along with an agent-specific extension to the Context Tree Weighting algorithm. Empirically, we present a set of encouraging results on a variety of stochastic and partially observable domains. We conclude by proposing a number of directions for future research.", "source": "arxiv/ml"}
{"id": "arxiv:341", "title": "High-Dimensional Non-Linear Variable Selection through Hierarchical Kernel Learning", "text": "We consider the problem of high-dimensional non-linear variable selection for supervised learning. Our approach is based on performing linear selection among exponentially many appropriately defined positive definite kernels that characterize non-linear interactions between the original variables. To select efficiently from these many kernels, we use the natural hierarchical structure of the problem to extend the multiple kernel learning framework to kernels that can be embedded in a directed acyclic graph; we show that it is then possible to perform kernel selection through a graph-adapted sparsity-inducing norm, in polynomial time in the number of selected kernels. Moreover, we study the consistency of variable selection in high-dimensional settings, showing that under certain assumptions, our regularization framework allows a number of irrelevant variables which is exponential in the number of observations. Our simulations on synthetic datasets and datasets from the UCI repository show state-of-the-art predictive performance for non-linear regression problems.", "source": "arxiv/ml"}
{"id": "arxiv:342", "title": "New Approximation Algorithms for Minimum Enclosing Convex Shapes", "text": "Given $n$ points in a $d$ dimensional Euclidean space, the Minimum Enclosing Ball (MEB) problem is to find the ball with the smallest radius which contains all $n$ points. We give a $O(nd\\Qcal/\\sqrt{\\epsilon})$ approximation algorithm for producing an enclosing ball whose radius is at most $\\epsilon$ away from the optimum (where $\\Qcal$ is an upper bound on the norm of the points). This improves existing results using \\emph{coresets}, which yield a $O(nd/\\epsilon)$ greedy algorithm. Finding the Minimum Enclosing Convex Polytope (MECP) is a related problem wherein a convex polytope of a fixed shape is given and the aim is to find the smallest magnification of the polytope which encloses the given points. For this problem we present a $O(mnd\\Qcal/\\epsilon)$ approximation algorithm, where $m$ is the number of faces of the polytope. Our algorithms borrow heavily from convex duality and recently developed techniques in non-smooth optimization, and are in contrast with existing methods which rely on geometric arguments. In particular, we specialize the excessive gap framework of \\citet{Nesterov05a} to obtain our results.", "source": "arxiv/ml"}
{"id": "arxiv:343", "title": "Efficient Learning of Sparse Conditional Random Fields for Supervised Sequence Labelling", "text": "Conditional Random Fields (CRFs) constitute a popular and efficient approach for supervised sequence labelling. CRFs can cope with large description spaces and can integrate some form of structural dependency between labels. In this contribution, we address the issue of efficient feature selection for CRFs based on imposing sparsity through an L1 penalty. We first show how sparsity of the parameter set can be exploited to significantly speed up training and labelling. We then introduce coordinate descent parameter update schemes for CRFs with L1 regularization. We finally provide some empirical comparisons of the proposed approach with state-of-the-art CRF training strategies. In particular, it is shown that the proposed approach is able to take profit of the sparsity to speed up processing and hence potentially handle larger dimensional models.", "source": "arxiv/ml"}
{"id": "arxiv:344", "title": "Lower Bounds for BMRM and Faster Rates for Training SVMs", "text": "Regularized risk minimization with the binary hinge loss and its variants lies at the heart of many machine learning problems. Bundle methods for regularized risk minimization (BMRM) and the closely related SVMStruct are considered the best general purpose solvers to tackle this problem. It was recently shown that BMRM requires $O(1/\\epsilon)$ iterations to converge to an $\\epsilon$ accurate solution. In the first part of the paper we use the Hadamard matrix to construct a regularized risk minimization problem and show that these rates cannot be improved. We then show how one can exploit the structure of the objective function to devise an algorithm for the binary hinge loss which converges to an $\\epsilon$ accurate solution in $O(1/\\sqrt{\\epsilon})$ iterations.", "source": "arxiv/ml"}
{"id": "arxiv:345", "title": "Sailing the Information Ocean with Awareness of Currents: Discovery and Application of Source Dependence", "text": "The Web has enabled the availability of a huge amount of useful information, but has also eased the ability to spread false information and rumors across multiple sources, making it hard to distinguish between what is true and what is not. Recent examples include the premature Steve Jobs obituary, the second bankruptcy of United airlines, the creation of Black Holes by the operation of the Large Hadron Collider, etc. Since it is important to permit the expression of dissenting and conflicting opinions, it would be a fallacy to try to ensure that the Web provides only consistent information. However, to help in separating the wheat from the chaff, it is essential to be able to determine dependence between sources. Given the huge number of data sources and the vast volume of conflicting data available on the Web, doing so in a scalable manner is extremely challenging and has not been addressed by existing work yet. In this paper, we present a set of research problems and propose some preliminary solutions on the issues involved in discovering dependence between sources. We also discuss how this knowledge can benefit a variety of technologies, such as data integration and Web 2.0, that help users manage and access the totality of the available information from various sources.", "source": "arxiv/ml"}
{"id": "arxiv:346", "title": "Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $\\beta$-Mixing Processes", "text": "Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for margin classifiers: there have been recent contributions showing how practical these bounds can be either to perform model selection (Ambroladze et al., 2007) or even to directly guide the learning of linear classifiers (Germain et al., 2009). However, there are many practical situations where the training data show some dependencies and where the traditional IID assumption does not hold. Stating generalization bounds for such frameworks is therefore of the utmost interest, both from theoretical and practical standpoints. In this work, we propose the first - to the best of our knowledge - Pac-Bayes generalization bounds for classifiers trained on data exhibiting interdependencies. The approach undertaken to establish our results is based on the decomposition of a so-called dependency graph that encodes the dependencies within the data, in sets of independent data, thanks to graph fractional covers. Our bounds are very general, since being able to find an upper bound on the fractional chromatic number of the dependency graph is sufficient to get new Pac-Bayes bounds for specific settings. We show how our results can be used to derive bounds for ranking statistics (such as Auc) and classifiers trained on data distributed according to a stationary {\\ss}-mixing process. In the way, we show how our approach seemlessly allows us to deal with U-processes. As a side note, we also provide a Pac-Bayes generalization bound for classifiers learned on data from stationary $\\varphi$-mixing distributions.", "source": "arxiv/ml"}
{"id": "arxiv:347", "title": "Approximate Nearest Neighbor Search through Comparisons", "text": "This paper addresses the problem of finding the nearest neighbor (or one of the R-nearest neighbors) of a query object q in a database of n objects. In contrast with most existing approaches, we can only access the ``hidden'' space in which the objects live through a similarity oracle. The oracle, given two reference objects and a query object, returns the reference object closest to the query object. The oracle attempts to model the behavior of human users, capable of making statements about similarity, but not of assigning meaningful numerical values to distances between objects.", "source": "arxiv/ml"}
{"id": "arxiv:348", "title": "Universal and Composite Hypothesis Testing via Mismatched Divergence", "text": "For the universal hypothesis testing problem, where the goal is to decide between the known null hypothesis distribution and some other unknown distribution, Hoeffding proposed a universal test in the nineteen sixties. Hoeffding's universal test statistic can be written in terms of Kullback-Leibler (K-L) divergence between the empirical distribution of the observations and the null hypothesis distribution. In this paper a modification of Hoeffding's test is considered based on a relaxation of the K-L divergence test statistic, referred to as the mismatched divergence. The resulting mismatched test is shown to be a generalized likelihood-ratio test (GLRT) for the case where the alternate distribution lies in a parametric family of the distributions characterized by a finite dimensional parameter, i.e., it is a solution to the corresponding composite hypothesis testing problem. For certain choices of the alternate distribution, it is shown that both the Hoeffding test and the mismatched test have the same asymptotic performance in terms of error exponents. A consequence of this result is that the GLRT is optimal in differentiating a particular distribution from others in an exponential family. It is also shown that the mismatched test has a significant advantage over the Hoeffding test in terms of finite sample size performance. This advantage is due to the difference in the asymptotic variances of the two test statistics under the null hypothesis. In particular, the variance of the K-L divergence grows linearly with the alphabet size, making the test impractical for applications involving large alphabet distributions. The variance of the mismatched divergence on the other hand grows linearly with the dimension of the parameter space, and can hence be controlled through a prudent choice of the function class defining the mismatched divergence.", "source": "arxiv/ml"}
{"id": "arxiv:349", "title": "Distribution-Specific Agnostic Boosting", "text": "We consider the problem of boosting the accuracy of weak learning algorithms in the agnostic learning framework of Haussler (1992) and Kearns et al. (1992). Known algorithms for this problem (Ben-David et al., 2001; Gavinsky, 2002; Kalai et al., 2008) follow the same strategy as boosting algorithms in the PAC model: the weak learner is executed on the same target function but over different distributions on the domain. We demonstrate boosting algorithms for the agnostic learning framework that only modify the distribution on the labels of the points (or, equivalently, modify the target function). This allows boosting a distribution-specific weak agnostic learner to a strong agnostic learner with respect to the same distribution. When applied to the weak agnostic parity learning algorithm of Goldreich and Levin (1989) our algorithm yields a simple PAC learning algorithm for DNF and an agnostic learning algorithm for decision trees over the uniform distribution using membership queries. These results substantially simplify Jackson's famous DNF learning algorithm (1994) and the recent result of Gopalan et al. (2008). We also strengthen the connection to hard-core set constructions discovered by Klivans and Servedio (1999) by demonstrating that hard-core set constructions that achieve the optimal hard-core set size (given by Holenstein (2005) and Barak et al. (2009)) imply distribution-specific agnostic boosting algorithms. Conversely, our boosting algorithm gives a simple hard-core set construction with an (almost) optimal hard-core set size.", "source": "arxiv/ml"}
{"id": "arxiv:350", "title": "A Convergent Online Single Time Scale Actor Critic Algorithm", "text": "Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their generality, good convergence properties, and possible biological relevance. In this paper, we introduce an online temporal difference based actor-critic algorithm which is proved to converge to a neighborhood of a local maximum of the average reward. Linear function approximation is used by the critic in order estimate the value function, and the temporal difference signal, which is passed from the critic to the actor. The main distinguishing feature of the present convergence proof is that both the actor and the critic operate on a similar time scale, while in most current convergence proofs they are required to have very different time scales in order to converge. Moreover, the same temporal difference signal is used to update the parameters of both the actor and the critic. A limitation of the proposed approach, compared to results available for two time scale convergence, is that convergence is guaranteed only to a neighborhood of an optimal value, rather to an optimal value itself. The single time scale and identical temporal difference signal used by the actor and the critic, may provide a step towards constructing more biologically realistic models of reinforcement learning in the brain.", "source": "arxiv/ml"}
{"id": "arxiv:351", "title": "Median K-flats for hybrid linear modeling with many outliers", "text": "We describe the Median K-Flats (MKF) algorithm, a simple online method for hybrid linear modeling, i.e., for approximating data by a mixture of flats. This algorithm simultaneously partitions the data into clusters while finding their corresponding best approximating l1 d-flats, so that the cumulative l1 error is minimized. The current implementation restricts d-flats to be d-dimensional linear subspaces. It requires a negligible amount of storage, and its complexity, when modeling data consisting of N points in D-dimensional Euclidean space with K d-dimensional linear subspaces, is of order O(n K d D+n d^2 D), where n is the number of iterations required for convergence (empirically on the order of 10^4). Since it is an online algorithm, data can be supplied to it incrementally and it can incrementally produce the corresponding output. The performance of the algorithm is carefully evaluated using synthetic and real data.", "source": "arxiv/ml"}
{"id": "arxiv:352", "title": "Exploiting Unlabeled Data to Enhance Ensemble Diversity", "text": "Ensemble learning aims to improve generalization ability by using multiple base learners. It is well-known that to construct a good ensemble, the base learners should be accurate as well as diverse. In this paper, unlabeled data is exploited to facilitate ensemble learning by helping augment the diversity among the base learners. Specifically, a semi-supervised ensemble method named UDEED is proposed. Unlike existing semi-supervised ensemble methods where error-prone pseudo-labels are estimated for unlabeled data to enlarge the labeled data to improve accuracy, UDEED works by maximizing accuracies of base learners on labeled data while maximizing diversity among them on unlabeled data. Experiments show that UDEED can effectively utilize unlabeled data for ensemble learning and is highly competitive to well-established semi-supervised ensemble methods.", "source": "arxiv/ml"}
{"id": "arxiv:353", "title": "Extension of Path Probability Method to Approximate Inference over Time", "text": "There has been a tremendous growth in publicly available digital video footage over the past decade. This has necessitated the development of new techniques in computer vision geared towards efficient analysis, storage and retrieval of such data. Many mid-level computer vision tasks such as segmentation, object detection, tracking, etc. involve an inference problem based on the video data available. Video data has a high degree of spatial and temporal coherence. The property must be intelligently leveraged in order to obtain better results. Graphical models, such as Markov Random Fields, have emerged as a powerful tool for such inference problems. They are naturally suited for expressing the spatial dependencies present in video data, It is however, not clear, how to extend the existing techniques for the problem of inference over time. This thesis explores the Path Probability Method, a variational technique in statistical mechanics, in the context of graphical models and approximate inference problems. It extends the method to a general framework for problems involving inference in time, resulting in an algorithm, \\emph{DynBP}. We explore the relation of the algorithm with existing techniques, and find the algorithm competitive with existing approaches. The main contribution of this thesis are the extended GBP algorithm, the extension of Path Probability Methods to the DynBP algorithm and the relationship between them. We have also explored some applications in computer vision involving temporal evolution with promising results.", "source": "arxiv/ml"}
{"id": "arxiv:354", "title": "Randomized Algorithms for Large scale SVMs", "text": "We propose a randomized algorithm for training Support vector machines(SVMs) on large datasets. By using ideas from Random projections we show that the combinatorial dimension of SVMs is $O({log} n)$ with high probability. This estimate of combinatorial dimension is used to derive an iterative algorithm, called RandSVM, which at each step calls an existing solver to train SVMs on a randomly chosen subset of size $O({log} n)$. The algorithm has probabilistic guarantees and is capable of training SVMs with Kernels for both classification and regression problems. Experiments done on synthetic and real life data sets demonstrate that the algorithm scales up existing SVM learners, without loss of accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:355", "title": "Discrete MDL Predicts in Total Variation", "text": "The Minimum Description Length (MDL) principle selects the model that has the shortest code for data plus model. We show that for a countable class of models, MDL predictions are close to the true distribution in a strong sense. The result is completely general. No independence, ergodicity, stationarity, identifiability, or other assumption on the model class need to be made. More formally, we show that for any countable class of models, the distributions selected by MDL (or MAP) asymptotically predict (merge with) the true measure in the class in total variation distance. Implications for non-i.i.d. domains like time-series forecasting, discriminative learning, and reinforcement learning are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:356", "title": "Scalable Inference for Latent Dirichlet Allocation", "text": "We investigate the problem of learning a topic model - the well-known Latent Dirichlet Allocation - in a distributed manner, using a cluster of C processors and dividing the corpus to be learned equally among them. We propose a simple approximated method that can be tuned, trading speed for accuracy according to the task at hand. Our approach is asynchronous, and therefore suitable for clusters of heterogenous machines.", "source": "arxiv/ml"}
{"id": "arxiv:357", "title": "Eignets for function approximation on manifolds", "text": "Let $\\XX$ be a compact, smooth, connected, Riemannian manifold without boundary, $G:\\XX\\times\\XX\\to \\RR$ be a kernel. Analogous to a radial basis function network, an eignet is an expression of the form $\\sum_{j=1}^M a_jG(\\circ,y_j)$, where $a_j\\in\\RR$, $y_j\\in\\XX$, $1\\le j\\le M$. We describe a deterministic, universal algorithm for constructing an eignet for approximating functions in $L^p(\\mu;\\XX)$ for a general class of measures $\\mu$ and kernels $G$. Our algorithm yields linear operators. Using the minimal separation amongst the centers $y_j$ as the cost of approximation, we give modulus of smoothness estimates for the degree of approximation by our eignets, and show by means of a converse theorem that these are the best possible for every \\emph{individual function}. We also give estimates on the coefficients $a_j$ in terms of the norm of the eignet. Finally, we demonstrate that if any sequence of eignets satisfies the optimal estimates for the degree of approximation of a smooth function, measured in terms of the minimal separation, then the derivatives of the eignets also approximate the corresponding derivatives of the target function in an optimal manner.", "source": "arxiv/ml"}
{"id": "arxiv:358", "title": "Bounding the Sensitivity of Polynomial Threshold Functions", "text": "We give the first non-trivial upper bounds on the average sensitivity and noise sensitivity of polynomial threshold functions. More specifically, for a Boolean function f on n variables equal to the sign of a real, multivariate polynomial of total degree d we prove 1) The average sensitivity of f is at most O(n^{1-1/(4d+6)}) (we also give a combinatorial proof of the bound O(n^{1-1/2^d}). 2) The noise sensitivity of f with noise rate \\delta is at most O(\\delta^{1/(4d+6)}). Previously, only bounds for the linear case were known. Along the way we show new structural theorems about random restrictions of polynomial threshold functions obtained via hypercontractivity. These structural results may be of independent interest as they provide a generic template for transforming problems related to polynomial threshold functions defined on the Boolean hypercube to polynomial threshold functions defined in Gaussian space.", "source": "arxiv/ml"}
{"id": "arxiv:359", "title": "Guaranteed Rank Minimization via Singular Value Projection", "text": "Minimizing the rank of a matrix subject to affine constraints is a fundamental problem with many important applications in machine learning and statistics. In this paper we propose a simple and fast algorithm SVP (Singular Value Projection) for rank minimization with affine constraints (ARMP) and show that SVP recovers the minimum rank solution for affine constraints that satisfy the \"restricted isometry property\" and show robustness of our method to noise. Our results improve upon a recent breakthrough by Recht, Fazel and Parillo (RFP07) and Lee and Bresler (LB09) in three significant ways: 1) our method (SVP) is significantly simpler to analyze and easier to implement, 2) we give recovery guarantees under strictly weaker isometry assumptions 3) we give geometric convergence guarantees for SVP even in presense of noise and, as demonstrated empirically, SVP is significantly faster on real-world and synthetic problems. In addition, we address the practically important problem of low-rank matrix completion (MCP), which can be seen as a special case of ARMP. We empirically demonstrate that our algorithm recovers low-rank incoherent matrices from an almost optimal number of uniformly sampled entries. We make partial progress towards proving exact recovery and provide some intuition for the strong performance of SVP applied to matrix completion by showing a more restricted isometry property. Our algorithm outperforms existing methods, such as those of \\cite{RFP07,CR08,CT09,CCS08,KOM09,LB09}, for ARMP and the matrix-completion problem by an order of magnitude and is also significantly more robust to noise.", "source": "arxiv/ml"}
{"id": "arxiv:360", "title": "Finding Associations and Computing Similarity via Biased Pair Sampling", "text": "This version is ***superseded*** by a full version that can be found at http://www.itu.dk/people/pagh/papers/mining-jour.pdf, which contains stronger theoretical results and fixes a mistake in the reporting of experiments. Abstract: Sampling-based methods have previously been proposed for the problem of finding interesting associations in data, even for low-support items. While these methods do not guarantee precise results, they can be vastly more efficient than approaches that rely on exact counting. However, for many similarity measures no such methods have been known. In this paper we show how a wide variety of measures can be supported by a simple biased sampling method. The method also extends to find high-confidence association rules. We demonstrate theoretically that our method is superior to exact methods when the threshold for \"interesting similarity/confidence\" is above the average pairwise similarity/confidence, and the average support is not too low. Our method is particularly good when transactions contain many items. We confirm in experiments on standard association mining benchmarks that this gives a significant speedup on real data sets (sometimes much larger than the theoretical guarantees). Reductions in computation time of over an order of magnitude, and significant savings in space, are observed.", "source": "arxiv/ml"}
{"id": "arxiv:361", "title": "Compressed Blind De-convolution", "text": "Suppose the signal x is realized by driving a k-sparse signal u through an arbitrary unknown stable discrete-linear time invariant system H. These types of processes arise naturally in Reflection Seismology. In this paper we are interested in several problems: (a) Blind-Deconvolution: Can we recover both the filter $H$ and the sparse signal $u$ from noisy measurements? (b) Compressive Sensing: Is x compressible in the conventional sense of compressed sensing? Namely, can x, u and H be reconstructed from a sparse set of measurements. We develop novel L1 minimization methods to solve both cases and establish sufficient conditions for exact recovery for the case when the unknown system H is auto-regressive (i.e. all pole) of a known order. In the compressed sensing/sampling setting it turns out that both H and x can be reconstructed from O(k log(n)) measurements under certain technical conditions on the support structure of u. Our main idea is to pass x through a linear time invariant system G and collect O(k log(n)) sequential measurements. The filter G is chosen suitably, namely, its associated Toeplitz matrix satisfies the RIP property. We develop a novel LP optimization algorithm and show that both the unknown filter H and the sparse input u can be reliably estimated.", "source": "arxiv/ml"}
{"id": "arxiv:362", "title": "Post-Processing of Discovered Association Rules Using Ontologies", "text": "In Data Mining, the usefulness of association rules is strongly limited by the huge amount of delivered rules. In this paper we propose a new approach to prune and filter discovered rules. Using Domain Ontologies, we strengthen the integration of user knowledge in the post-processing task. Furthermore, an interactive and iterative framework is designed to assist the user along the analyzing task. On the one hand, we represent user domain knowledge using a Domain Ontology over database. On the other hand, a novel technique is suggested to prune and to filter discovered rules. The proposed framework was applied successfully over the client database provided by Nantes Habitat.", "source": "arxiv/ml"}
{"id": "arxiv:363", "title": "Statistical Decision Making for Authentication and Intrusion Detection", "text": "User authentication and intrusion detection differ from standard classification problems in that while we have data generated from legitimate users, impostor or intrusion data is scarce or non-existent. We review existing techniques for dealing with this problem and propose a novel alternative based on a principled statistical decision-making view point. We examine the technique on a toy problem and validate it on complex real-world data from an RFID based access control system. The results indicate that it can significantly outperform the classical world model approach. The method could be more generally useful in other decision-making scenarios where there is a lack of adversary data.", "source": "arxiv/ml"}
{"id": "arxiv:364", "title": "Regularization Techniques for Learning with Matrices", "text": "There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge). This work describes and analyzes a systematic method for constructing such matrix-based, regularization methods. In particular, we focus on how the underlying statistical properties of a given problem can help us decide which regularization function is appropriate. Our methodology is based on the known duality fact: that a function is strongly convex with respect to some norm if and only if its conjugate function is strongly smooth with respect to the dual norm. This result has already been found to be a key component in deriving and analyzing several learning algorithms. We demonstrate the potential of this framework by deriving novel generalization and regret bounds for multi-task learning, multi-class learning, and kernel learning.", "source": "arxiv/ml"}
{"id": "arxiv:365", "title": "Variable sigma Gaussian processes: An expectation propagation perspective", "text": "Gaussian processes (GPs) provide a probabilistic nonparametric representation of functions in regression, classification, and other problems. Unfortunately, exact learning with GPs is intractable for large datasets. A variety of approximate GP methods have been proposed that essentially map the large dataset into a small set of basis points. The most advanced of these, the variable-sigma GP (VSGP) (Walder et al., 2008), allows each basis point to have its own length scale. However, VSGP was only derived for regression. We describe how VSGP can be applied to classification and other problems, by deriving it as an expectation propagation algorithm. In this view, sparse GP approximations correspond to a KL-projection of the true posterior onto a compact exponential family of GPs. VSGP constitutes one such family, and we show how to enlarge this family to get additional accuracy. In particular, we show that endowing each basis point with its own full covariance matrix provides a significant increase in approximation power.", "source": "arxiv/ml"}
{"id": "arxiv:366", "title": "Prediction of Zoonosis Incidence in Human using Seasonal Auto Regressive Integrated Moving Average (SARIMA)", "text": "Zoonosis refers to the transmission of infectious diseases from animal to human. The increasing number of zoonosis incidence makes the great losses to lives, including humans and animals, and also the impact in social economic. It motivates development of a system that can predict the future number of zoonosis occurrences in human. This paper analyses and presents the use of Seasonal Autoregressive Integrated Moving Average (SARIMA) method for developing a forecasting model that able to support and provide prediction number of zoonosis human incidence. The dataset for model development was collected on a time series data of human tuberculosis occurrences in United States which comprises of fourteen years of monthly data obtained from a study published by Centers for Disease Control and Prevention (CDC). Several trial models of SARIMA were compared to obtain the most appropriate model. Then, diagnostic tests were used to determine model validity. The result showed that the SARIMA(9,0,14)(12,1,24)12 is the fittest model. While in the measure of accuracy, the selected model achieved 0.062 of Theils U value. It implied that the model was highly accurate and a close fit. It was also indicated the capability of final model to closely represent and made prediction based on the tuberculosis historical dataset.", "source": "arxiv/ml"}
{"id": "arxiv:367", "title": "Reduced-Rank Hidden Markov Models", "text": "We introduce the Reduced-Rank Hidden Markov Model (RR-HMM), a generalization of HMMs that can model smooth state evolution as in Linear Dynamical Systems (LDSs) as well as non-log-concave predictive distributions as in continuous-observation HMMs. RR-HMMs assume an m-dimensional latent state and n discrete observations, with a transition matrix of rank k <= m. This implies the dynamics evolve in a k-dimensional subspace, while the shape of the set of predictive distributions is determined by m. Latent state belief is represented with a k-dimensional state vector and inference is carried out entirely in R^k, making RR-HMMs as computationally efficient as k-state HMMs yet more expressive. To learn RR-HMMs, we relax the assumptions of a recently proposed spectral learning algorithm for HMMs (Hsu, Kakade and Zhang 2009) and apply it to learn k-dimensional observable representations of rank-k RR-HMMs. The algorithm is consistent and free of local optima, and we extend its performance guarantees to cover the RR-HMM case. We show how this algorithm can be used in conjunction with a kernel density estimator to efficiently model high-dimensional multivariate continuous data. We also relax the assumption that single observations are sufficient to disambiguate state, and extend the algorithm accordingly. Experiments on synthetic data and a toy video, as well as on a difficult robot vision modeling problem, yield accurate models that compare favorably with standard alternatives in simulation quality and prediction capability.", "source": "arxiv/ml"}
{"id": "arxiv:368", "title": "Low-rank Matrix Completion with Noisy Observations: a Quantitative Comparison", "text": "We consider a problem of significant practical importance, namely, the reconstruction of a low-rank data matrix from a small subset of its entries. This problem appears in many areas such as collaborative filtering, computer vision and wireless sensor networks. In this paper, we focus on the matrix completion problem in the case when the observed samples are corrupted by noise. We compare the performance of three state-of-the-art matrix completion algorithms (OptSpace, ADMiRA and FPCA) on a single simulation platform and present numerical results. We show that in practice these efficient algorithms can be used to reconstruct real data matrices, as well as randomly generated matrices, accurately.", "source": "arxiv/ml"}
{"id": "arxiv:369", "title": "Adaboost with \"Keypoint Presence Features\" for Real-Time Vehicle Visual Detection", "text": "We present promising results for real-time vehicle visual detection, obtained with adaBoost using new original ?keypoints presence features?. These weak-classifiers produce a boolean response based on presence or absence in the tested image of a ?keypoint? (~ a SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as ?wheel? or ?side skirt?) and thus have a ?semantic? meaning.", "source": "arxiv/ml"}
{"id": "arxiv:370", "title": "Introducing New AdaBoost Features for Real-Time Vehicle Detection", "text": "This paper shows how to improve the real-time object detection in complex robotics applications, by exploring new visual features as AdaBoost weak classifiers. These new features are symmetric Haar filters (enforcing global horizontal and vertical symmetry) and N-connexity control points. Experimental evaluation on a car database show that the latter appear to provide the best results for the vehicle-detection problem.", "source": "arxiv/ml"}
{"id": "arxiv:371", "title": "Visual object categorization with new keypoint-based adaBoost features", "text": "We present promising results for visual object categorization, obtained with adaBoost using new original ?keypoints-based features?. These weak-classifiers produce a boolean response based on presence or absence in the tested image of a ?keypoint? (a kind of SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Preliminary tests on a small subset of a pedestrians database also gives promising 97% recall with 92 % precision, which shows the generality of our new family of features. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as ?wheel? or ?side skirt? in the case of lateral-cars) and thus have a ?semantic? meaning. We also made a first test on video for detecting vehicles from adaBoostselected keypoints filtered in real-time from all detected keypoints.", "source": "arxiv/ml"}
{"id": "arxiv:372", "title": "Local and global approaches of affinity propagation clustering for large scale data", "text": "Recently a new clustering algorithm called 'affinity propagation' (AP) has been proposed, which efficiently clustered sparsely related data by passing messages between data points. However, we want to cluster large scale data where the similarities are not sparse in many cases. This paper presents two variants of AP for grouping large scale data with a dense similarity matrix. The local approach is partition affinity propagation (PAP) and the global method is landmark affinity propagation (LAP). PAP passes messages in the subsets of data first and then merges them as the number of initial step of iterations; it can effectively reduce the number of iterations of clustering. LAP passes messages between the landmark data points first and then clusters non-landmark data points; it is a large global approximation method to speed up clustering. Experiments are conducted on many datasets, such as random data points, manifold subspaces, images of faces and Chinese calligraphy, and the results demonstrate that the two approaches are feasible and practicable.", "source": "arxiv/ml"}
{"id": "arxiv:373", "title": "Strategies for online inference of model-based clustering in large and growing networks", "text": "In this paper we adapt online estimation strategies to perform model-based clustering on large networks. Our work focuses on two algorithms, the first based on the SAEM algorithm, and the second on variational methods. These two strategies are compared with existing approaches on simulated and real data. We use the method to decipher the connexion structure of the political websphere during the US political campaign in 2008. We show that our online EM-based algorithms offer a good trade-off between precision and speed, when estimating parameters for mixture distributions in the context of random graphs.", "source": "arxiv/ml"}
{"id": "arxiv:374", "title": "Distributed Learning in Multi-Armed Bandit with Multiple Players", "text": "We formulate and study a decentralized multi-armed bandit (MAB) problem. There are M distributed players competing for N independent arms. Each arm, when played, offers i.i.d. reward according to a distribution with an unknown parameter. At each time, each player chooses one arm to play without exchanging observations or any information with other players. Players choosing the same arm collide, and, depending on the collision model, either no one receives reward or the colliding players share the reward in an arbitrary way. We show that the minimum system regret of the decentralized MAB grows with time at the same logarithmic order as in the centralized counterpart where players act collectively as a single entity by exchanging observations and making decisions jointly. A decentralized policy is constructed to achieve this optimal order while ensuring fairness among players and without assuming any pre-agreement or information exchange among players. Based on a Time Division Fair Sharing (TDFS) of the M best arms, the proposed policy is constructed and its order optimality is proven under a general reward model. Furthermore, the basic structure of the TDFS policy can be used with any order-optimal single-player policy to achieve order optimality in the decentralized setting. We also establish a lower bound on the system regret growth rate for a general class of decentralized polices, to which the proposed policy belongs. This problem finds potential applications in cognitive radio networks, multi-channel communication systems, multi-agent systems, web search and advertising, and social networks.", "source": "arxiv/ml"}
{"id": "arxiv:375", "title": "Repeated Auctions with Learning for Spectrum Access in Cognitive Radio Networks", "text": "In this paper, spectrum access in cognitive radio networks is modeled as a repeated auction game subject to monitoring and entry costs. For secondary users, sensing costs are incurred as the result of primary users' activity. Furthermore, each secondary user pays the cost of transmissions upon successful bidding for a channel. Knowledge regarding other secondary users' activity is limited due to the distributed nature of the network. The resulting formulation is thus a dynamic game with incomplete information. In this paper, an efficient bidding learning algorithm is proposed based on the outcome of past transactions. As demonstrated through extensive simulations, the proposed distributed scheme outperforms a myopic one-stage algorithm, and can achieve a good balance between efficiency and fairness.", "source": "arxiv/ml"}
{"id": "arxiv:376", "title": "Positive Semidefinite Metric Learning with Boosting", "text": "The learning of appropriate distance metrics is a critical problem in image classification and retrieval. In this work, we propose a boosting-based technique, termed \\BoostMetric, for learning a Mahalanobis distance metric. One of the primary difficulties in learning such a metric is to ensure that the Mahalanobis matrix remains positive semidefinite. Semidefinite programming is sometimes used to enforce this constraint, but does not scale well. \\BoostMetric is instead based on a key observation that any positive semidefinite matrix can be decomposed into a linear positive combination of trace-one rank-one matrices. \\BoostMetric thus uses rank-one positive semidefinite matrices as weak learners within an efficient and scalable boosting-based learning process. The resulting method is easy to implement, does not require tuning, and can accommodate various types of constraints. Experiments on various datasets show that the proposed algorithm compares favorably to those state-of-the-art methods in terms of classification accuracy and running time.", "source": "arxiv/ml"}
{"id": "arxiv:377", "title": "Effectiveness and Limitations of Statistical Spam Filters", "text": "In this paper we discuss the techniques involved in the design of the famous statistical spam filters that include Naive Bayes, Term Frequency-Inverse Document Frequency, K-Nearest Neighbor, Support Vector Machine, and Bayes Additive Regression Tree. We compare these techniques with each other in terms of accuracy, recall, precision, etc. Further, we discuss the effectiveness and limitations of statistical filters in filtering out various types of spam from legitimate e-mails.", "source": "arxiv/ml"}
{"id": "arxiv:378", "title": "On Learning Finite-State Quantum Sources", "text": "We examine the complexity of learning the distributions produced by finite-state quantum sources. We show how prior techniques for learning hidden Markov models can be adapted to the quantum generator model to find that the analogous state of affairs holds: information-theoretically, a polynomial number of samples suffice to approximately identify the distribution, but computationally, the problem is as hard as learning parities with noise, a notorious open question in computational learning theory.", "source": "arxiv/ml"}
{"id": "arxiv:379", "title": "Self-concordant analysis for logistic regression", "text": "Most of the non-asymptotic theoretical work in regression is carried out for the square loss, where estimators can be obtained through closed-form expressions. In this paper, we use and extend tools from the convex optimization literature, namely self-concordant functions, to provide simple extensions of theoretical results for the square loss to the logistic loss. We apply the extension techniques to logistic regression with regularization by the $\\ell_2$-norm and regularization by the $\\ell_1$-norm, showing that new results for binary classification through logistic regression can be easily derived from corresponding results for least-squares regression.", "source": "arxiv/ml"}
{"id": "arxiv:380", "title": "Competing with Gaussian linear experts", "text": "We study the problem of online regression. We prove a theoretical bound on the square loss of Ridge Regression. We do not make any assumptions about input vectors or outcomes. We also show that Bayesian Ridge Regression can be thought of as an online algorithm competing with all the Gaussian linear experts.", "source": "arxiv/ml"}
{"id": "arxiv:381", "title": "A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion", "text": "We consider the problem of reconstructing a low-rank matrix from a small subset of its entries. In this paper, we describe the implementation of an efficient algorithm called OptSpace, based on singular value decomposition followed by local manifold optimization, for solving the low-rank matrix completion problem. It has been shown that if the number of revealed entries is large enough, the output of singular value decomposition gives a good estimate for the original matrix, so that local optimization reconstructs the correct matrix with high probability. We present numerical results which show that this algorithm can reconstruct the low rank matrix exactly from a very small subset of its entries. We further study the robustness of the algorithm with respect to noise, and its performance on actual collaborative filtering datasets.", "source": "arxiv/ml"}
{"id": "arxiv:382", "title": "The Cyborg Astrobiologist: Testing a Novelty-Detection Algorithm on Two Mobile Exploration Systems at Rivas Vaciamadrid in Spain and at the Mars Desert Research Station in Utah", "text": "(ABRIDGED) In previous work, two platforms have been developed for testing computer-vision algorithms for robotic planetary exploration (McGuire et al. 2004b,2005; Bartolo et al. 2007). The wearable-computer platform has been tested at geological and astrobiological field sites in Spain (Rivas Vaciamadrid and Riba de Santiuste), and the phone-camera has been tested at a geological field site in Malta. In this work, we (i) apply a Hopfield neural-network algorithm for novelty detection based upon color, (ii) integrate a field-capable digital microscope on the wearable computer platform, (iii) test this novelty detection with the digital microscope at Rivas Vaciamadrid, (iv) develop a Bluetooth communication mode for the phone-camera platform, in order to allow access to a mobile processing computer at the field sites, and (v) test the novelty detection on the Bluetooth-enabled phone-camera connected to a netbook computer at the Mars Desert Research Station in Utah. This systems engineering and field testing have together allowed us to develop a real-time computer-vision system that is capable, for example, of identifying lichens as novel within a series of images acquired in semi-arid desert environments. We acquired sequences of images of geologic outcrops in Utah and Spain consisting of various rock types and colors to test this algorithm. The algorithm robustly recognized previously-observed units by their color, while requiring only a single image or a few images to learn colors as familiar, demonstrating its fast learning capability.", "source": "arxiv/ml"}
{"id": "arxiv:383", "title": "Anomaly Detection with Score functions based on Nearest Neighbor Graphs", "text": "We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on score functions derived from nearest neighbor graphs on $n$-point nominal data. Anomalies are declared whenever the score of a test sample falls below $\\alpha$, which is supposed to be the desired false alarm level. The resulting anomaly detector is shown to be asymptotically optimal in that it is uniformly most powerful for the specified false alarm level, $\\alpha$, for the case when the anomaly density is a mixture of the nominal and a known density. Our algorithm is computationally efficient, being linear in dimension and quadratic in data size. It does not require choosing complicated tuning parameters or function approximation classes and it can adapt to local structure such as local change in dimensionality. We demonstrate the algorithm on both artificial and real data sets in high dimensional feature spaces.", "source": "arxiv/ml"}
{"id": "arxiv:384", "title": "Which graphical models are difficult to learn?", "text": "We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-complexity algorithms systematically fail when the Markov random field develops long-range correlations. More precisely, this phenomenon appears to be related to the Ising model phase transition (although it does not coincide with it).", "source": "arxiv/ml"}
{"id": "arxiv:385", "title": "Metric and Kernel Learning using a Linear Transformation", "text": "Metric and kernel learning are important in several machine learning applications. However, most existing metric learning algorithms are limited to learning metrics over low-dimensional data, while existing kernel learning algorithms are often limited to the transductive setting and do not generalize to new data points. In this paper, we study metric learning as a problem of learning a linear transformation of the input data. We show that for high-dimensional data, a particular framework for learning a linear transformation of the data based on the LogDet divergence can be efficiently kernelized to learn a metric (or equivalently, a kernel function) over an arbitrarily high dimensional space. We further demonstrate that a wide class of convex loss functions for learning linear transformations can similarly be kernelized, thereby considerably expanding the potential applications of metric learning. We demonstrate our learning approach by applying it to large-scale real world problems in computer vision and text mining.", "source": "arxiv/ml"}
{"id": "arxiv:386", "title": "Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity", "text": "The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions, such as when there is some sparsity pattern of the optimal parameter. This work characterizes a certain strong convexity property of general exponential families, which allow their generalization ability to be quantified. In particular, we show how this property can be used to analyze generic exponential families under L_1 regularization.", "source": "arxiv/ml"}
{"id": "arxiv:387", "title": "A Mirroring Theorem and its Application to a New Method of Unsupervised Hierarchical Pattern Classification", "text": "In this paper, we prove a crucial theorem called Mirroring Theorem which affirms that given a collection of samples with enough information in it such that it can be classified into classes and subclasses then (i) There exists a mapping which classifies and subclassifies these samples (ii) There exists a hierarchical classifier which can be constructed by using Mirroring Neural Networks (MNNs) in combination with a clustering algorithm that can approximate this mapping. Thus, the proof of the Mirroring theorem provides a theoretical basis for the existence and a practical feasibility of constructing hierarchical classifiers, given the maps. Our proposed Mirroring Theorem can also be considered as an extension to Kolmogrovs theorem in providing a realistic solution for unsupervised classification. The techniques we develop, are general in nature and have led to the construction of learning machines which are (i) tree like in structure, (ii) modular (iii) with each module running on a common algorithm (tandem algorithm) and (iv) selfsupervised. We have actually built the architecture, developed the tandem algorithm of such a hierarchical classifier and demonstrated it on an example problem.", "source": "arxiv/ml"}
{"id": "arxiv:388", "title": "Feature-Weighted Linear Stacking", "text": "Ensemble methods, such as stacking, are designed to boost predictive accuracy by blending the predictions of multiple machine learning models. Recent work has shown that the use of meta-features, additional inputs describing each example in a dataset, can boost the performance of ensemble methods, but the greatest reported gains have come from nonlinear procedures requiring significant tuning and training time. Here, we present a linear technique, Feature-Weighted Linear Stacking (FWLS), that incorporates meta-features for improved accuracy while retaining the well-known virtues of linear regression regarding speed, stability, and interpretability. FWLS combines model predictions linearly using coefficients that are themselves linear functions of meta-features. This technique was a key facet of the solution of the second place team in the recently concluded Netflix Prize competition. Significant increases in accuracy over standard linear stacking are demonstrated on the Netflix Prize collaborative filtering dataset.", "source": "arxiv/ml"}
{"id": "arxiv:389", "title": "Strange Bedfellows: Quantum Mechanics and Data Mining", "text": "Last year, in 2008, I gave a talk titled {\\it Quantum Calisthenics}. This year I am going to tell you about how the work I described then has spun off into a most unlikely direction. What I am going to talk about is how one maps the problem of finding clusters in a given data set into a problem in quantum mechanics. I will then use the tricks I described to let quantum evolution lets the clusters come together on their own.", "source": "arxiv/ml"}
{"id": "arxiv:390", "title": "Novel Intrusion Detection using Probabilistic Neural Network and Adaptive Boosting", "text": "This article applies Machine Learning techniques to solve Intrusion Detection problems within computer networks. Due to complex and dynamic nature of computer networks and hacking techniques, detecting malicious activities remains a challenging task for security experts, that is, currently available defense systems suffer from low detection capability and high number of false alarms. To overcome such performance limitations, we propose a novel Machine Learning algorithm, namely Boosted Subspace Probabilistic Neural Network (BSPNN), which integrates an adaptive boosting technique and a semi parametric neural network to obtain good tradeoff between accuracy and generality. As the result, learning bias and generalization variance can be significantly minimized. Substantial experiments on KDD 99 intrusion benchmark indicate that our model outperforms other state of the art learning algorithms, with significantly improved detection accuracy, minimal false alarms and relatively small computational complexity.", "source": "arxiv/ml"}
{"id": "arxiv:391", "title": "Bayes estimators for phylogenetic reconstruction", "text": "Tree reconstruction methods are often judged by their accuracy, measured by how close they get to the true tree. Yet most reconstruction methods like ML do not explicitly maximize this accuracy. To address this problem, we propose a Bayesian solution. Given tree samples, we propose finding the tree estimate which is closest on average to the samples. This ``median'' tree is known as the Bayes estimator (BE). The BE literally maximizes posterior expected accuracy, measured in terms of closeness (distance) to the true tree. We discuss a unified framework of BE trees, focusing especially on tree distances which are expressible as squared euclidean distances. Notable examples include Robinson--Foulds distance, quartet distance, and squared path difference. Using simulated data, we show Bayes estimators can be efficiently computed in practice by hill climbing. We also show that Bayes estimators achieve higher accuracy, compared to maximum likelihood and neighbor joining.", "source": "arxiv/ml"}
{"id": "arxiv:392", "title": "Sharp Dichotomies for Regret Minimization in Metric Spaces", "text": "The Lipschitz multi-armed bandit (MAB) problem generalizes the classical multi-armed bandit problem by assuming one is given side information consisting of a priori upper bounds on the difference in expected payoff between certain pairs of strategies. Classical results of (Lai and Robbins 1985) and (Auer et al. 2002) imply a logarithmic regret bound for the Lipschitz MAB problem on finite metric spaces. Recent results on continuum-armed bandit problems and their generalizations imply lower bounds of $\\sqrt{t}$, or stronger, for many infinite metric spaces such as the unit interval. Is this dichotomy universal? We prove that the answer is yes: for every metric space, the optimal regret of a Lipschitz MAB algorithm is either bounded above by any $f\\in \\omega(\\log t)$, or bounded below by any $g\\in o(\\sqrt{t})$. Perhaps surprisingly, this dichotomy does not coincide with the distinction between finite and infinite metric spaces; instead it depends on whether the completion of the metric space is compact and countable. Our proof connects upper and lower bound techniques in online learning with classical topological notions such as perfect sets and the Cantor-Bendixson theorem. Among many other results, we show a similar dichotomy for the \"full-feedback\" (a.k.a., \"best-expert\") version.", "source": "arxiv/ml"}
{"id": "arxiv:393", "title": "Machine Learning: When and Where the Horses Went Astray?", "text": "Machine Learning is usually defined as a subfield of AI, which is busy with information extraction from raw data sets. Despite of its common acceptance and widespread recognition, this definition is wrong and groundless. Meaningful information does not belong to the data that bear it. It belongs to the observers of the data and it is a shared agreement and a convention among them. Therefore, this private information cannot be extracted from the data by any means. Therefore, all further attempts of Machine Learning apologists to justify their funny business are inappropriate.", "source": "arxiv/ml"}
{"id": "arxiv:394", "title": "Belief Propagation and Loop Calculus for the Permanent of a Non-Negative Matrix", "text": "We consider computation of permanent of a positive $(N\\times N)$ non-negative matrix, $P=(P_i^j|i,j=1,\\cdots,N)$, or equivalently the problem of weighted counting of the perfect matchings over the complete bipartite graph $K_{N,N}$. The problem is known to be of likely exponential complexity. Stated as the partition function $Z$ of a graphical model, the problem allows exact Loop Calculus representation [Chertkov, Chernyak '06] in terms of an interior minimum of the Bethe Free Energy functional over non-integer doubly stochastic matrix of marginal beliefs, $\\beta=(\\beta_i^j|i,j=1,\\cdots,N)$, also correspondent to a fixed point of the iterative message-passing algorithm of the Belief Propagation (BP) type. Our main result is an explicit expression of the exact partition function (permanent) in terms of the matrix of BP marginals, $\\beta$, as $Z=\\mbox{Perm}(P)=Z_{BP} \\mbox{Perm}(\\beta_i^j(1-\\beta_i^j))/\\prod_{i,j}(1-\\beta_i^j)$, where $Z_{BP}$ is the BP expression for the permanent stated explicitly in terms if $\\beta$. We give two derivations of the formula, a direct one based on the Bethe Free Energy and an alternative one combining the Ihara graph-$\\zeta$ function and the Loop Calculus approaches. Assuming that the matrix $\\beta$ of the Belief Propagation marginals is calculated, we provide two lower bounds and one upper-bound to estimate the multiplicative term. Two complementary lower bounds are based on the Gurvits-van der Waerden theorem and on a relation between the modified permanent and determinant respectively.", "source": "arxiv/ml"}
{"id": "arxiv:395", "title": "Analytical Determination of Fractal Structure in Stochastic Time Series", "text": "Current methods for determining whether a time series exhibits fractal structure (FS) rely on subjective assessments on estimators of the Hurst exponent (H). Here, I introduce the Bayesian Assessment of Scaling, an analytical framework for drawing objective and accurate inferences on the FS of time series. The technique exploits the scaling property of the diffusion associated to a time series. The resulting criterion is simple to compute and represents an accurate characterization of the evidence supporting different hypotheses on the scaling regime of a time series. Additionally, a closed-form Maximum Likelihood estimator of H is derived from the criterion, and this estimator outperforms the best available estimators.", "source": "arxiv/ml"}
{"id": "arxiv:396", "title": "Sequential anomaly detection in the presence of noise and limited feedback", "text": "This paper describes a methodology for detecting anomalies from sequentially observed and potentially noisy data. The proposed approach consists of two main elements: (1) {\\em filtering}, or assigning a belief or likelihood to each successive measurement based upon our ability to predict it from previous noisy observations, and (2) {\\em hedging}, or flagging potential anomalies by comparing the current belief against a time-varying and data-adaptive threshold. The threshold is adjusted based on the available feedback from an end user. Our algorithms, which combine universal prediction with recent work on online convex programming, do not require computing posterior distributions given all current observations and involve simple primal-dual parameter updates. At the heart of the proposed approach lie exponential-family models which can be used in a wide variety of contexts and applications, and which yield methods that achieve sublinear per-round regret against both static and slowly varying product distributions with marginals drawn from the same exponential family. Moreover, the regret against static distributions coincides with the minimax value of the corresponding online strongly convex game. We also prove bounds on the number of mistakes made during the hedging step relative to the best offline choice of the threshold with access to all estimated beliefs and feedback signals. We validate the theory on synthetic data drawn from a time-varying distribution over binary vectors of high dimensionality, as well as on the Enron email dataset.", "source": "arxiv/ml"}
{"id": "arxiv:397", "title": "A Dynamic Near-Optimal Algorithm for Online Linear Programming", "text": "A natural optimization model that formulates many online resource allocation and revenue management problems is the online linear program (LP) in which the constraint matrix is revealed column by column along with the corresponding objective coefficient. In such a model, a decision variable has to be set each time a column is revealed without observing the future inputs and the goal is to maximize the overall objective function. In this paper, we provide a near-optimal algorithm for this general class of online problems under the assumption of random order of arrival and some mild conditions on the size of the LP right-hand-side input. Specifically, our learning-based algorithm works by dynamically updating a threshold price vector at geometric time intervals, where the dual prices learned from the revealed columns in the previous period are used to determine the sequential decisions in the current period. Due to the feature of dynamic learning, the competitiveness of our algorithm improves over the past study of the same problem. We also present a worst-case example showing that the performance of our algorithm is near-optimal.", "source": "arxiv/ml"}
{"id": "arxiv:398", "title": "Understanding the Principles of Recursive Neural networks: A Generative Approach to Tackle Model Complexity", "text": "Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not only for being extremely complex information processing models, but also because of a computational expensive learning phase. The most popular training method for these models is back-propagation through the structure. This algorithm has been revealed not to be the most appropriate for structured processing due to problems of convergence, while more sophisticated training methods enhance the speed of convergence at the expense of increasing significantly the computational cost. In this paper, we firstly perform an analysis of the underlying principles behind these models aimed at understanding their computational power. Secondly, we propose an approximate second order stochastic learning algorithm. The proposed algorithm dynamically adapts the learning rate throughout the training phase of the network without incurring excessively expensive computational effort. The algorithm operates in both on-line and batch modes. Furthermore, the resulting learning scheme is robust against the vanishing gradients problem. The advantages of the proposed algorithm are demonstrated with a real-world application example.", "source": "arxiv/ml"}
{"id": "arxiv:399", "title": "Keystroke Dynamics Authentication For Collaborative Systems", "text": "We present in this paper a study on the ability and the benefits of using a keystroke dynamics authentication method for collaborative systems. Authentication is a challenging issue in order to guarantee the security of use of collaborative systems during the access control step. Many solutions exist in the state of the art such as the use of one time passwords or smart-cards. We focus in this paper on biometric based solutions that do not necessitate any additional sensor. Keystroke dynamics is an interesting solution as it uses only the keyboard and is invisible for users. Many methods have been published in this field. We make a comparative study of many of them considering the operational constraints of use for collaborative systems.", "source": "arxiv/ml"}
{"id": "arxiv:400", "title": "A Geometric Approach to Sample Compression", "text": "The Sample Compression Conjecture of Littlestone & Warmuth has remained unsolved for over two decades. This paper presents a systematic geometric investigation of the compression of finite maximum concept classes. Simple arrangements of hyperplanes in Hyperbolic space, and Piecewise-Linear hyperplane arrangements, are shown to represent maximum classes, generalizing the corresponding Euclidean result. A main result is that PL arrangements can be swept by a moving hyperplane to unlabeled d-compress any finite maximum class, forming a peeling scheme as conjectured by Kuzmin & Warmuth. A corollary is that some d-maximal classes cannot be embedded into any maximum class of VC dimension d+k, for any constant k. The construction of the PL sweeping involves Pachner moves on the one-inclusion graph, corresponding to moves of a hyperplane across the intersection of d other hyperplanes. This extends the well known Pachner moves for triangulations to cubical complexes.", "source": "arxiv/ml"}
{"id": "arxiv:401", "title": "Likelihood-based semi-supervised model selection with applications to speech processing", "text": "In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some other means. In the context of speech processing systems and other large-scale practical applications, however, such labeled development data are typically costly and difficult to obtain. This article proposes an alternative semi-supervised framework for likelihood-based model selection that leverages unlabeled data by using trained classifiers representing each model to automatically generate putative labels. The errors that result from this automatic labeling are shown to be amenable to results from robust statistics, which in turn provide for minimax-optimal censored likelihood ratio tests that recover the nonparametric sign test as a limiting case. This approach is then validated experimentally using a state-of-the-art automatic speech recognition system to select between candidate word pronunciations using unlabeled speech data that only potentially contain instances of the words under test. Results provide supporting evidence for the utility of this approach, and suggest that it may also find use in other applications of machine learning.", "source": "arxiv/ml"}
{"id": "arxiv:402", "title": "Super-Linear Convergence of Dual Augmented-Lagrangian Algorithm for Sparsity Regularized Estimation", "text": "We analyze the convergence behaviour of a recently proposed algorithm for regularized estimation called Dual Augmented Lagrangian (DAL). Our analysis is based on a new interpretation of DAL as a proximal minimization algorithm. We theoretically show under some conditions that DAL converges super-linearly in a non-asymptotic and global sense. Due to a special modelling of sparse estimation problems in the context of machine learning, the assumptions we make are milder and more natural than those made in conventional analysis of augmented Lagrangian algorithms. In addition, the new interpretation enables us to generalize DAL to wide varieties of sparse estimation problems. We experimentally confirm our analysis in a large scale $\\ell_1$-regularized logistic regression problem and extensively compare the efficiency of DAL algorithm to previously proposed algorithms on both synthetic and benchmark datasets.", "source": "arxiv/ml"}
{"id": "arxiv:403", "title": "Towards Industrialized Conception and Production of Serious Games", "text": "Serious Games (SGs) have experienced a tremendous outburst these last years. Video game companies have been producing fun, user-friendly SGs, but their educational value has yet to be proven. Meanwhile, cognition research scientist have been developing SGs in such a way as to guarantee an educational gain, but the fun and attractive characteristics featured often would not meet the public's expectations. The ideal SG must combine these two aspects while still being economically viable. In this article, we propose a production chain model to efficiently conceive and produce SGs that are certified for their educational gain and fun qualities. Each step of this chain will be described along with the human actors, the tools and the documents that intervene.", "source": "arxiv/ml"}
{"id": "arxiv:404", "title": "Statistical exponential families: A digest with flash cards", "text": "This document describes concisely the ubiquitous class of exponential family distributions met in statistics. The first part recalls definitions and summarizes main properties and duality with Bregman divergences (all proofs are skipped). The second part lists decompositions and related formula of common exponential family distributions. We recall the Fisher-Rao-Riemannian geometries and the dual affine connection information geometries of statistical manifolds. It is intended to maintain and update this document and catalog by adding new distribution items.", "source": "arxiv/ml"}
{"id": "arxiv:405", "title": "A Bayesian Rule for Adaptive Control based on Causal Interventions", "text": "Explaining adaptive behavior is a central problem in artificial intelligence research. Here we formalize adaptive agents as mixture distributions over sequences of inputs and outputs (I/O). Each distribution of the mixture constitutes a `possible world', but the agent does not know which of the possible worlds it is actually facing. The problem is to adapt the I/O stream in a way that is compatible with the true world. A natural measure of adaptation can be obtained by the Kullback-Leibler (KL) divergence between the I/O distribution of the true world and the I/O distribution expected by the agent that is uncertain about possible worlds. In the case of pure input streams, the Bayesian mixture provides a well-known solution for this problem. We show, however, that in the case of I/O streams this solution breaks down, because outputs are issued by the agent itself and require a different probabilistic syntax as provided by intervention calculus. Based on this calculus, we obtain a Bayesian control rule that allows modeling adaptive behavior with mixture distributions over I/O streams. This rule might allow for a novel approach to adaptive control based on a minimum KL-principle.", "source": "arxiv/ml"}
{"id": "arxiv:406", "title": "Maximin affinity learning of image segmentation", "text": "Images can be segmented by first using a classifier to predict an affinity graph that reflects the degree to which image pixels must be grouped together and then partitioning the graph to yield a segmentation. Machine learning has been applied to the affinity classifier to produce affinity graphs that are good in the sense of minimizing edge misclassification rates. However, this error measure is only indirectly related to the quality of segmentations produced by ultimately partitioning the affinity graph. We present the first machine learning algorithm for training a classifier to produce affinity graphs that are good in the sense of producing segmentations that directly minimize the Rand index, a well known segmentation performance measure. The Rand index measures segmentation performance by quantifying the classification of the connectivity of image pixel pairs after segmentation. By using the simple graph partitioning algorithm of finding the connected components of the thresholded affinity graph, we are able to train an affinity classifier to directly minimize the Rand index of segmentations resulting from the graph partitioning. Our learning algorithm corresponds to the learning of maximin affinities between image pixel pairs, which are predictive of the pixel-pair connectivity.", "source": "arxiv/ml"}
{"id": "arxiv:407", "title": "Hierarchies in Dictionary Definition Space", "text": "A dictionary defines words in terms of other words. Definitions can tell you the meanings of words you don't know, but only if you know the meanings of the defining words. How many words do you need to know (and which ones) in order to be able to learn all the rest from definitions? We reduced dictionaries to their \"grounding kernels\" (GKs), about 10% of the dictionary, from which all the other words could be defined. The GK words turned out to have psycholinguistic correlates: they were learned at an earlier age and more concrete than the rest of the dictionary. But one can compress still more: the GK turns out to have internal structure, with a strongly connected \"kernel core\" (KC) and a surrounding layer, from which a hierarchy of definitional distances can be derived, all the way out to the periphery of the full dictionary. These definitional distances, too, are correlated with psycholinguistic variables (age of acquisition, concreteness, imageability, oral and written frequency) and hence perhaps with the \"mental lexicon\" in each of our heads.", "source": "arxiv/ml"}
{"id": "arxiv:408", "title": "Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning", "text": "Several recent studies in privacy-preserving learning have considered the trade-off between utility or risk and the level of differential privacy guaranteed by mechanisms for statistical query processing. In this paper we study this trade-off in private Support Vector Machine (SVM) learning. We present two efficient mechanisms, one for the case of finite-dimensional feature mappings and one for potentially infinite-dimensional feature mappings with translation-invariant kernels. For the case of translation-invariant kernels, the proposed mechanism minimizes regularized empirical risk in a random Reproducing Kernel Hilbert Space whose kernel uniformly approximates the desired kernel with high probability. This technique, borrowed from large-scale learning, allows the mechanism to respond with a finite encoding of the classifier, even when the function class is of infinite VC dimension. Differential privacy is established using a proof technique from algorithmic stability. Utility--the mechanism's response function is pointwise epsilon-close to non-private SVM with probability 1-delta--is proven by appealing to the smoothness of regularized empirical risk minimization with respect to small perturbations to the feature mapping. We conclude with a lower bound on the optimal differential privacy of the SVM. This negative result states that for any delta, no mechanism can be simultaneously (epsilon,delta)-useful and beta-differentially private for small epsilon and small beta.", "source": "arxiv/ml"}
{"id": "arxiv:409", "title": "Differentially Private Empirical Risk Minimization", "text": "Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the $\\epsilon$-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance.", "source": "arxiv/ml"}
{"id": "arxiv:410", "title": "Learning Mixtures of Gaussians using the k-means Algorithm", "text": "One of the most popular algorithms for clustering in Euclidean space is the $k$-means algorithm; $k$-means is difficult to analyze mathematically, and few theoretical guarantees are known about it, particularly when the data is {\\em well-clustered}. In this paper, we attempt to fill this gap in the literature by analyzing the behavior of $k$-means on well-clustered data. In particular, we study the case when each cluster is distributed as a different Gaussian -- or, in other words, when the input comes from a mixture of Gaussians. We analyze three aspects of the $k$-means algorithm under this assumption. First, we show that when the input comes from a mixture of two spherical Gaussians, a variant of the 2-means algorithm successfully isolates the subspace containing the means of the mixture components. Second, we show an exact expression for the convergence of our variant of the 2-means algorithm, when the input is a very large number of samples from a mixture of spherical Gaussians. Our analysis does not require any lower bound on the separation between the mixture components. Finally, we study the sample requirement of $k$-means; for a mixture of 2 spherical Gaussians, we show an upper bound on the number of samples required by a variant of 2-means to get close to the true solution. The sample requirement grows with increasing dimensionality of the data, and decreasing separation between the means of the Gaussians. To match our upper bound, we show an information-theoretic lower bound on any algorithm that learns mixtures of two spherical Gaussians; our lower bound indicates that in the case when the overlap between the probability masses of the two distributions is small, the sample requirement of $k$-means is {\\em near-optimal}.", "source": "arxiv/ml"}
{"id": "arxiv:411", "title": "Isometric Multi-Manifolds Learning", "text": "Isometric feature mapping (Isomap) is a promising manifold learning method. However, Isomap fails to work on data which distribute on clusters in a single manifold or manifolds. Many works have been done on extending Isomap to multi-manifolds learning. In this paper, we first proposed a new multi-manifolds learning algorithm (M-Isomap) with help of a general procedure. The new algorithm preserves intra-manifold geodesics and multiple inter-manifolds edges precisely. Compared with previous methods, this algorithm can isometrically learn data distributed on several manifolds. Secondly, the original multi-cluster manifold learning algorithm first proposed in \\cite{DCIsomap} and called D-C Isomap has been revised so that the revised D-C Isomap can learn multi-manifolds data. Finally, the features and effectiveness of the proposed multi-manifolds learning algorithms are demonstrated and compared through experiments.", "source": "arxiv/ml"}
{"id": "arxiv:412", "title": "Training a Large Scale Classifier with the Quantum Adiabatic Algorithm", "text": "In a previous publication we proposed discrete global optimization as a method to train a strong binary classifier constructed as a thresholded sum over weak classifiers. Our motivation was to cast the training of a classifier into a format amenable to solution by the quantum adiabatic algorithm. Applying adiabatic quantum computing (AQC) promises to yield solutions that are superior to those which can be achieved with classical heuristic solvers. Interestingly we found that by using heuristic solvers to obtain approximate solutions we could already gain an advantage over the standard method AdaBoost. In this communication we generalize the baseline method to large scale classifier training. By large scale we mean that either the cardinality of the dictionary of candidate weak classifiers or the number of weak learners used in the strong classifier exceed the number of variables that can be handled effectively in a single global optimization. For such situations we propose an iterative and piecewise approach in which a subset of weak classifiers is selected in each iteration via global optimization. The strong classifier is then constructed by concatenating the subsets of weak classifiers. We show in numerical studies that the generalized method again successfully competes with AdaBoost. We also provide theoretical arguments as to why the proposed optimization method, which does not only minimize the empirical loss but also adds L0-norm regularization, is superior to versions of boosting that only minimize the empirical loss. By conducting a Quantum Monte Carlo simulation we gather evidence that the quantum adiabatic algorithm is able to handle a generic training problem efficiently.", "source": "arxiv/ml"}
{"id": "arxiv:413", "title": "Designing Kernel Scheme for Classifiers Fusion", "text": "In this paper, we propose a special fusion method for combining ensembles of base classifiers utilizing new neural networks in order to improve overall efficiency of classification. While ensembles are designed such that each classifier is trained independently while the decision fusion is performed as a final procedure, in this method, we would be interested in making the fusion process more adaptive and efficient. This new combiner, called Neural Network Kernel Least Mean Square1, attempts to fuse outputs of the ensembles of classifiers. The proposed Neural Network has some special properties such as Kernel abilities,Least Mean Square features, easy learning over variants of patterns and traditional neuron capabilities. Neural Network Kernel Least Mean Square is a special neuron which is trained with Kernel Least Mean Square properties. This new neuron is used as a classifiers combiner to fuse outputs of base neural network classifiers. Performance of this method is analyzed and compared with other fusion methods. The analysis represents higher performance of our new method as opposed to others.", "source": "arxiv/ml"}
{"id": "arxiv:414", "title": "Biogeography based Satellite Image Classification", "text": "Biogeography is the study of the geographical distribution of biological organisms. The mindset of the engineer is that we can learn from nature. Biogeography Based Optimization is a burgeoning nature inspired technique to find the optimal solution of the problem. Satellite image classification is an important task because it is the only way we can know about the land cover map of inaccessible areas. Though satellite images have been classified in past by using various techniques, the researchers are always finding alternative strategies for satellite image classification so that they may be prepared to select the most appropriate technique for the feature extraction task in hand. This paper is focused on classification of the satellite image of a particular land cover using the theory of Biogeography based Optimization. The original BBO algorithm does not have the inbuilt property of clustering which is required during image classification. Hence modifications have been proposed to the original algorithm and the modified algorithm is used to classify the satellite image of a given region. The results indicate that highly accurate land cover features can be extracted effectively when the proposed algorithm is used.", "source": "arxiv/ml"}
{"id": "arxiv:415", "title": "An ensemble approach for feature selection of Cyber Attack Dataset", "text": "Feature selection is an indispensable preprocessing step when mining huge datasets that can significantly improve the overall system performance. Therefore in this paper we focus on a hybrid approach of feature selection. This method falls into two phases. The filter phase select the features with highest information gain and guides the initialization of search process for wrapper phase whose output the final feature subset. The final feature subsets are passed through the Knearest neighbor classifier for classification of attacks. The effectiveness of this algorithm is demonstrated on DARPA KDDCUP99 cyber attack dataset.", "source": "arxiv/ml"}
{"id": "arxiv:416", "title": "How to Explain Individual Classification Decisions", "text": "After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the question what is the most likely label of a given unseen data point. However, most methods will provide no answer why the model predicted the particular label for a single instance and what features were most influential for that particular instance. The only method that is currently able to provide such explanations are decision trees. This paper proposes a procedure which (based on a set of assumptions) allows to explain the decisions of any classification method.", "source": "arxiv/ml"}
{"id": "arxiv:417", "title": "A Learning-Based Approach to Reactive Security", "text": "Despite the conventional wisdom that proactive security is superior to reactive security, we show that reactive security can be competitive with proactive security as long as the reactive defender learns from past attacks instead of myopically overreacting to the last attack. Our game-theoretic model follows common practice in the security literature by making worst-case assumptions about the attacker: we grant the attacker complete knowledge of the defender's strategy and do not require the attacker to act rationally. In this model, we bound the competitive ratio between a reactive defense algorithm (which is inspired by online learning theory) and the best fixed proactive defense. Additionally, we show that, unlike proactive defenses, this reactive strategy is robust to a lack of information about the attacker's incentives and knowledge.", "source": "arxiv/ml"}
{"id": "arxiv:418", "title": "Delay-Optimal Power and Subcarrier Allocation for OFDMA Systems via Stochastic Approximation", "text": "In this paper, we consider delay-optimal power and subcarrier allocation design for OFDMA systems with $N_F$ subcarriers, $K$ mobiles and one base station. There are $K$ queues at the base station for the downlink traffic to the $K$ mobiles with heterogeneous packet arrivals and delay requirements. We shall model the problem as a $K$-dimensional infinite horizon average reward Markov Decision Problem (MDP) where the control actions are assumed to be a function of the instantaneous Channel State Information (CSI) as well as the joint Queue State Information (QSI). This problem is challenging because it corresponds to a stochastic Network Utility Maximization (NUM) problem where general solution is still unknown. We propose an {\\em online stochastic value iteration} solution using {\\em stochastic approximation}. The proposed power control algorithm, which is a function of both the CSI and the QSI, takes the form of multi-level water-filling. We prove that under two mild conditions in Theorem 1 (One is the stepsize condition. The other is the condition on accessibility of the Markov Chain, which can be easily satisfied in most of the cases we are interested.), the proposed solution converges to the optimal solution almost surely (with probability 1) and the proposed framework offers a possible solution to the general stochastic NUM problem. By exploiting the birth-death structure of the queue dynamics, we obtain a reduced complexity decomposed solution with linear $\\mathcal{O}(KN_F)$ complexity and $\\mathcal{O}(K)$ memory requirement.", "source": "arxiv/ml"}
{"id": "arxiv:419", "title": "Association Rule Pruning based on Interestingness Measures with Clustering", "text": "Association rule mining plays vital part in knowledge mining. The difficult task is discovering knowledge or useful rules from the large number of rules generated for reduced support. For pruning or grouping rules, several techniques are used such as rule structure cover methods, informative cover methods, rule clustering, etc. Another way of selecting association rules is based on interestingness measures such as support, confidence, correlation, and so on. In this paper, we study how rule clusters of the pattern Xi - Y are distributed over different interestingness measures.", "source": "arxiv/ml"}
{"id": "arxiv:420", "title": "Gesture Recognition with a Focus on Important Actions by Using a Path Searching Method in Weighted Graph", "text": "This paper proposes a method of gesture recognition with a focus on important actions for distinguishing similar gestures. The method generates a partial action sequence by using optical flow images, expresses the sequence in the eigenspace, and checks the feature vector sequence by applying an optimum path-searching method of weighted graph to focus the important actions. Also presented are the results of an experiment on the recognition of similar sign language words.", "source": "arxiv/ml"}
{"id": "arxiv:421", "title": "Synthesis of supervised classification algorithm using intelligent and statistical tools", "text": "A fundamental task in detecting foreground objects in both static and dynamic scenes is to take the best choice of color system representation and the efficient technique for background modeling. We propose in this paper a non-parametric algorithm dedicated to segment and to detect objects in color images issued from a football sports meeting. Indeed segmentation by pixel concern many applications and revealed how the method is robust to detect objects, even in presence of strong shadows and highlights. In the other hand to refine their playing strategy such as in football, handball, volley ball, Rugby..., the coach need to have a maximum of technical-tactics information about the on-going of the game and the players. We propose in this paper a range of algorithms allowing the resolution of many problems appearing in the automated process of team identification, where each player is affected to his corresponding team relying on visual data. The developed system was tested on a match of the Tunisian national competition. This work is prominent for many next computer vision studies as it's detailed in this study.", "source": "arxiv/ml"}
{"id": "arxiv:422", "title": "Early Detection of Breast Cancer using SVM Classifier Technique", "text": "This paper presents a tumor detection algorithm from mammogram. The proposed system focuses on the solution of two problems. One is how to detect tumors as suspicious regions with a very weak contrast to their background and another is how to extract features which categorize tumors. The tumor detection method follows the scheme of (a) mammogram enhancement. (b) The segmentation of the tumor area. (c) The extraction of features from the segmented tumor area. (d) The use of SVM classifier. The enhancement can be defined as conversion of the image quality to a better and more understandable level. The mammogram enhancement procedure includes filtering, top hat operation, DWT. Then the contrast stretching is used to increase the contrast of the image. The segmentation of mammogram images has been playing an important role to improve the detection and diagnosis of breast cancer. The most common segmentation method used is thresholding. The features are extracted from the segmented breast area. Next stage include, which classifies the regions using the SVM classifier. The method was tested on 75 mammographic images, from the mini-MIAS database. The methodology achieved a sensitivity of 88.75%.", "source": "arxiv/ml"}
{"id": "arxiv:423", "title": "Closing the Learning-Planning Loop with Predictive State Representations", "text": "A central problem in artificial intelligence is that of planning to maximize future reward under uncertainty in a partially observable environment. In this paper we propose and demonstrate a novel algorithm which accurately learns a model of such an environment directly from sequences of action-observation pairs. We then close the loop from observations to actions by planning in the learned model and recovering a policy which is near-optimal in the original environment. Specifically, we present an efficient and statistically consistent spectral algorithm for learning the parameters of a Predictive State Representation (PSR). We demonstrate the algorithm by learning a model of a simulated high-dimensional, vision-based mobile robot planning task, and then perform approximate point-based planning in the learned PSR. Analysis of our results shows that the algorithm learns a state space which efficiently captures the essential features of the environment. This representation allows accurate prediction with a small number of parameters, and enables successful and efficient planning.", "source": "arxiv/ml"}
{"id": "arxiv:424", "title": "The Gaussian Surface Area and Noise Sensitivity of Degree-$d$ Polynomials", "text": "We provide asymptotically sharp bounds for the Gaussian surface area and the Gaussian noise sensitivity of polynomial threshold functions. In particular we show that if $f$ is a degree-$d$ polynomial threshold function, then its Gaussian sensitivity at noise rate $\\epsilon$ is less than some quantity asymptotic to $\\frac{d\\sqrt{2\\epsilon}}{\\pi}$ and the Gaussian surface area is at most $\\frac{d}{\\sqrt{2\\pi}}$. Furthermore these bounds are asymptotically tight as $\\epsilon\\to 0$ and $f$ the threshold function of a product of $d$ distinct homogeneous linear functions.", "source": "arxiv/ml"}
{"id": "arxiv:425", "title": "Intrusion Detection In Mobile Ad Hoc Networks Using GA Based Feature Selection", "text": "Mobile ad hoc networking (MANET) has become an exciting and important technology in recent years because of the rapid proliferation of wireless devices. MANETs are highly vulnerable to attacks due to the open medium, dynamically changing network topology and lack of centralized monitoring point. It is important to search new architecture and mechanisms to protect the wireless networks and mobile computing application. IDS analyze the network activities by means of audit data and use patterns of well-known attacks or normal profile to detect potential attacks. There are two methods to analyze: misuse detection and anomaly detection. Misuse detection is not effective against unknown attacks and therefore, anomaly detection method is used. In this approach, the audit data is collected from each mobile node after simulating the attack and compared with the normal behavior of the system. If there is any deviation from normal behavior then the event is considered as an attack. Some of the features of collected audit data may be redundant or contribute little to the detection process. So it is essential to select the important features to increase the detection rate. This paper focuses on implementing two feature selection methods namely, markov blanket discovery and genetic algorithm. In genetic algorithm, bayesian network is constructed over the collected features and fitness function is calculated. Based on the fitness value the features are selected. Markov blanket discovery also uses bayesian network and the features are selected depending on the minimum description length. During the evaluation phase, the performances of both approaches are compared based on detection rate and false alarm rate.", "source": "arxiv/ml"}
{"id": "arxiv:426", "title": "Performance Analysis of AIM-K-means & K-means in Quality Cluster Generation", "text": "Among all the partition based clustering algorithms K-means is the most popular and well known method. It generally shows impressive results even in considerably large data sets. The computational complexity of K-means does not suffer from the size of the data set. The main disadvantage faced in performing this clustering is that the selection of initial means. If the user does not have adequate knowledge about the data set, it may lead to erroneous results. The algorithm Automatic Initialization of Means (AIM), which is an extension to K-means, has been proposed to overcome the problem of initial mean generation. In this paper an attempt has been made to compare the performance of the algorithms through implementation", "source": "arxiv/ml"}
{"id": "arxiv:427", "title": "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design", "text": "Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design. Moreover, by bounding the latter in terms of operator spectra, we obtain explicit sublinear regret bounds for many commonly used covariance functions. In some important cases, our bounds have surprisingly weak dependence on the dimensionality. In our experiments on real sensor data, GP-UCB compares favorably with other heuristical GP optimization approaches.", "source": "arxiv/ml"}
{"id": "arxiv:428", "title": "Learning to Predict Combinatorial Structures", "text": "The major challenge in designing a discriminative learning algorithm for predicting structured data is to address the computational issues arising from the exponential size of the output space. Existing algorithms make different assumptions to ensure efficient, polynomial time estimation of model parameters. For several combinatorial structures, including cycles, partially ordered sets, permutations and other graph classes, these assumptions do not hold. In this thesis, we address the problem of designing learning algorithms for predicting combinatorial structures by introducing two new assumptions: (i) The first assumption is that a particular counting problem can be solved efficiently. The consequence is a generalisation of the classical ridge regression for structured prediction. (ii) The second assumption is that a particular sampling problem can be solved efficiently. The consequence is a new technique for designing and analysing probabilistic structured prediction models. These results can be applied to solve several complex learning problems including but not limited to multi-label classification, multi-category hierarchical classification, and label ranking.", "source": "arxiv/ml"}
{"id": "arxiv:429", "title": "On Finding Predictors for Arbitrary Families of Processes", "text": "The problem is sequence prediction in the following setting. A sequence $x_1,...,x_n,...$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\\mu$. After observing each outcome, it is required to give the conditional probabilities of the next observation. The measure $\\mu$ belongs to an arbitrary but known class $C$ of stochastic process measures. We are interested in predictors $\\rho$ whose conditional probabilities converge (in some sense) to the \"true\" $\\mu$-conditional probabilities if any $\\mu\\in C$ is chosen to generate the sequence. The contribution of this work is in characterizing the families $C$ for which such predictors exist, and in providing a specific and simple form in which to look for a solution. We show that if any predictor works, then there exists a Bayesian predictor, whose prior is discrete, and which works too. We also find several sufficient and necessary conditions for the existence of a predictor, in terms of topological characterizations of the family $C$, as well as in terms of local behaviour of the measures in $C$, which in some cases lead to procedures for constructing such predictors. It should be emphasized that the framework is completely general: the stochastic processes considered are not required to be i.i.d., stationary, or to belong to any parametric or countable family.", "source": "arxiv/ml"}
{"id": "arxiv:430", "title": "An Invariance Principle for Polytopes", "text": "Let X be randomly chosen from {-1,1}^n, and let Y be randomly chosen from the standard spherical Gaussian on R^n. For any (possibly unbounded) polytope P formed by the intersection of k halfspaces, we prove that |Pr [X belongs to P] - Pr [Y belongs to P]| < log^{8/5}k * Delta, where Delta is a parameter that is small for polytopes formed by the intersection of \"regular\" halfspaces (i.e., halfspaces with low influence). The novelty of our invariance principle is the polylogarithmic dependence on k. Previously, only bounds that were at least linear in k were known. We give two important applications of our main result: (1) A polylogarithmic in k bound on the Boolean noise sensitivity of intersections of k \"regular\" halfspaces (previous work gave bounds linear in k). (2) A pseudorandom generator (PRG) with seed length O((log n)*poly(log k,1/delta)) that delta-fools all polytopes with k faces with respect to the Gaussian distribution. We also obtain PRGs with similar parameters that fool polytopes formed by intersection of regular halfspaces over the hypercube. Using our PRG constructions, we obtain the first deterministic quasi-polynomial time algorithms for approximately counting the number of solutions to a broad class of integer programs, including dense covering problems and contingency tables.", "source": "arxiv/ml"}
{"id": "arxiv:431", "title": "Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning", "text": "There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most problems of interest, the optimal solution involves planning in an infinitely large tree. However, it is possible to obtain stochastic lower and upper bounds on the value of each tree node. This enables us to use stochastic branch and bound algorithms to search the tree efficiently. This paper proposes two such algorithms and examines their complexity in this setting.", "source": "arxiv/ml"}
{"id": "arxiv:432", "title": "Ranking relations using analogies in biological and information networks", "text": "Analogical reasoning depends fundamentally on the ability to learn and generalize about relations between objects. We develop an approach to relational learning which, given a set of pairs of objects $\\mathbf{S}=\\{A^{(1)}:B^{(1)},A^{(2)}:B^{(2)},\\ldots,A^{(N)}:B ^{(N)}\\}$, measures how well other pairs A:B fit in with the set $\\mathbf{S}$. Our work addresses the following question: is the relation between objects A and B analogous to those relations found in $\\mathbf{S}$? Such questions are particularly relevant in information retrieval, where an investigator might want to search for analogous pairs of objects that match the query set of interest. There are many ways in which objects can be related, making the task of measuring analogies very challenging. Our approach combines a similarity measure on function spaces with Bayesian analysis to produce a ranking. It requires data containing features of the objects of interest and a link matrix specifying which relationships exist; no further attributes of such relationships are necessary. We illustrate the potential of our method on text analysis and information networks. An application on discovering functional interactions between pairs of proteins is discussed in detail, where we show that our approach can work in practice even if a small set of protein pairs is provided.", "source": "arxiv/ml"}
{"id": "arxiv:433", "title": "A survey of statistical network models", "text": "Networks are ubiquitous in science and have become a focal point for discussion in everyday life. Formal statistical models for the analysis of network data have emerged as a major topic of interest in diverse areas of study, and most of these involve a form of graphical representation. Probability models on graphs date back to 1959. Along with empirical studies in social psychology and sociology from the 1960s, these early works generated an active network community and a substantial literature in the 1970s. This effort moved into the statistical literature in the late 1970s and 1980s, and the past decade has seen a burgeoning network literature in statistical physics and computer science. The growth of the World Wide Web and the emergence of online networking communities such as Facebook, MySpace, and LinkedIn, and a host of more specialized professional network communities has intensified interest in the study of networks and network data. Our goal in this review is to provide the reader with an entry point to this burgeoning literature. We begin with an overview of the historical development of statistical network modeling and then we introduce a number of examples that have been studied in the network literature. Our subsequent discussion focuses on a number of prominent static and dynamic network models and their interconnections. We emphasize formal model descriptions, and pay special attention to the interpretation of parameters and their estimation. We end with a description of some open problems and challenges for machine learning and statistics.", "source": "arxiv/ml"}
{"id": "arxiv:434", "title": "Optimal Query Complexity for Reconstructing Hypergraphs", "text": "In this paper we consider the problem of reconstructing a hidden weighted hypergraph of constant rank using additive queries. We prove the following: Let $G$ be a weighted hidden hypergraph of constant rank with n vertices and $m$ hyperedges. For any $m$ there exists a non-adaptive algorithm that finds the edges of the graph and their weights using $$ O(\\frac{m\\log n}{\\log m}) $$ additive queries. This solves the open problem in [S. Choi, J. H. Kim. Optimal Query Complexity Bounds for Finding Graphs. {\\em STOC}, 749--758,~2008]. When the weights of the hypergraph are integers that are less than $O(poly(n^d/m))$ where $d$ is the rank of the hypergraph (and therefore for unweighted hypergraphs) there exists a non-adaptive algorithm that finds the edges of the graph and their weights using $$ O(\\frac{m\\log \\frac{n^d}{m}}{\\log m}). $$ additive queries. Using the information theoretic bound the above query complexities are tight.", "source": "arxiv/ml"}
{"id": "arxiv:435", "title": "Comparing Distributions and Shapes using the Kernel Distance", "text": "Starting with a similarity function between objects, it is possible to define a distance metric on pairs of objects, and more generally on probability distributions over them. These distance metrics have a deep basis in functional analysis, measure theory and geometric measure theory, and have a rich structure that includes an isometric embedding into a (possibly infinite dimensional) Hilbert space. They have recently been applied to numerous problems in machine learning and shape analysis. In this paper, we provide the first algorithmic analysis of these distance metrics. Our main contributions are as follows: (i) We present fast approximation algorithms for computing the kernel distance between two point sets P and Q that runs in near-linear time in the size of (P cup Q) (note that an explicit calculation would take quadratic time). (ii) We present polynomial-time algorithms for approximately minimizing the kernel distance under rigid transformation; they run in time O(n + poly(1/epsilon, log n)). (iii) We provide several general techniques for reducing complex objects to convenient sparse representations (specifically to point sets or sets of points sets) which approximately preserve the kernel distance. In particular, this allows us to reduce problems of computing the kernel distance between various types of objects such as curves, surfaces, and distributions to computing the kernel distance between point sets. These take advantage of the reproducing kernel Hilbert space and a new relation linking binary range spaces to continuous range spaces with bounded fat-shattering dimension.", "source": "arxiv/ml"}
{"id": "arxiv:436", "title": "Inference of global clusters from locally distributed data", "text": "We consider the problem of analyzing the heterogeneity of clustering distributions for multiple groups of observed data, each of which is indexed by a covariate value, and inferring global clusters arising from observations aggregated over the covariate domain. We propose a novel Bayesian nonparametric method reposing on the formalism of spatial modeling and a nested hierarchy of Dirichlet processes. We provide an analysis of the model properties, relating and contrasting the notions of local and global clusters. We also provide an efficient inference algorithm, and demonstrate the utility of our method in several data examples, including the problem of object tracking and a global clustering analysis of functional data where the functional identity information is not available.", "source": "arxiv/ml"}
{"id": "arxiv:437", "title": "Vandalism Detection in Wikipedia: a Bag-of-Words Classifier Approach", "text": "A bag-of-words based probabilistic classifier is trained using regularized logistic regression to detect vandalism in the English Wikipedia. Isotonic regression is used to calibrate the class membership probabilities. Learning curve, reliability, ROC, and cost analysis are performed.", "source": "arxiv/ml"}
{"id": "arxiv:438", "title": "Linear Probability Forecasting", "text": "Multi-class classification is one of the most important tasks in machine learning. In this paper we consider two online multi-class classification problems: classification by a linear model and by a kernelized model. The quality of predictions is measured by the Brier loss function. We suggest two computationally efficient algorithms to work with these problems and prove theoretical guarantees on their losses. We kernelize one of the algorithms and prove theoretical guarantees on its loss. We perform experiments and compare our algorithms with logistic regression.", "source": "arxiv/ml"}
{"id": "arxiv:439", "title": "Multi-path Probabilistic Available Bandwidth Estimation through Bayesian Active Learning", "text": "Knowing the largest rate at which data can be sent on an end-to-end path such that the egress rate is equal to the ingress rate with high probability can be very practical when choosing transmission rates in video streaming or selecting peers in peer-to-peer applications. We introduce probabilistic available bandwidth, which is defined in terms of ingress rates and egress rates of traffic on a path, rather than in terms of capacity and utilization of the constituent links of the path like the standard available bandwidth metric. In this paper, we describe a distributed algorithm, based on a probabilistic graphical model and Bayesian active learning, for simultaneously estimating the probabilistic available bandwidth of multiple paths through a network. Our procedure exploits the fact that each packet train provides information not only about the path it traverses, but also about any path that shares a link with the monitored path. Simulations and PlanetLab experiments indicate that this process can dramatically reduce the number of probes required to generate accurate estimates.", "source": "arxiv/ml"}
{"id": "arxiv:440", "title": "An Empirical Evaluation of Four Algorithms for Multi-Class Classification: Mart, ABC-Mart, Robust LogitBoost, and ABC-LogitBoost", "text": "This empirical study is mainly devoted to comparing four tree-based boosting algorithms: mart, abc-mart, robust logitboost, and abc-logitboost, for multi-class classification on a variety of publicly available datasets. Some of those datasets have been thoroughly tested in prior studies using a broad range of classification algorithms including SVM, neural nets, and deep learning. In terms of the empirical classification errors, our experiment results demonstrate: 1. Abc-mart considerably improves mart. 2. Abc-logitboost considerably improves (robust) logitboost. 3. Robust) logitboost} considerably improves mart on most datasets. 4. Abc-logitboost considerably improves abc-mart on most datasets. 5. These four boosting algorithms (especially abc-logitboost) outperform SVM on many datasets. 6. Compared to the best deep learning methods, these four boosting algorithms (especially abc-logitboost) are competitive.", "source": "arxiv/ml"}
{"id": "arxiv:441", "title": "An Unsupervised Algorithm For Learning Lie Group Transformations", "text": "We present several theoretical contributions which allow Lie groups to be fit to high dimensional datasets. Transformation operators are represented in their eigen-basis, reducing the computational complexity of parameter estimation to that of training a linear transformation model. A transformation specific \"blurring\" operator is introduced that allows inference to escape local minima via a smoothing of the transformation space. A penalty on traversed manifold distance is added which encourages the discovery of sparse, minimal distance, transformations between states. Both learning and inference are demonstrated using these methods for the full set of affine transformations on natural image patches. Transformation operators are then trained on natural video sequences. It is shown that the learned video transformations provide a better description of inter-frame differences than the standard motion model based on rigid translation.", "source": "arxiv/ml"}
{"id": "arxiv:442", "title": "Measuring Latent Causal Structure", "text": "Discovering latent representations of the observed world has become increasingly more relevant in data analysis. Much of the effort concentrates on building latent variables which can be used in prediction problems, such as classification and regression. A related goal of learning latent structure from data is that of identifying which hidden common causes generate the observations, such as in applications that require predicting the effect of policies. This will be the main problem tackled in our contribution: given a dataset of indicators assumed to be generated by unknown and unmeasured common causes, we wish to discover which hidden common causes are those, and how they generate our data. This is possible under the assumption that observed variables are linear functions of the latent causes with additive noise. Previous results in the literature present solutions for the case where each observed variable is a noisy function of a single latent variable. We show how to extend the existing results for some cases where observed variables measure more than one latent variable.", "source": "arxiv/ml"}
{"id": "arxiv:443", "title": "An Explicit Nonlinear Mapping for Manifold Learning", "text": "Manifold learning is a hot research topic in the field of computer science and has many applications in the real world. A main drawback of manifold learning methods is, however, that there is no explicit mappings from the input data manifold to the output embedding. This prohibits the application of manifold learning methods in many practical problems such as classification and target detection. Previously, in order to provide explicit mappings for manifold learning methods, many methods have been proposed to get an approximate explicit representation mapping with the assumption that there exists a linear projection between the high-dimensional data samples and their low-dimensional embedding. However, this linearity assumption may be too restrictive. In this paper, an explicit nonlinear mapping is proposed for manifold learning, based on the assumption that there exists a polynomial mapping between the high-dimensional data samples and their low-dimensional representations. As far as we know, this is the first time that an explicit nonlinear mapping for manifold learning is given. In particular, we apply this to the method of Locally Linear Embedding (LLE) and derive an explicit nonlinear manifold learning algorithm, named Neighborhood Preserving Polynomial Embedding (NPPE). Experimental results on both synthetic and real-world data show that the proposed mapping is much more effective in preserving the local neighborhood information and the nonlinear geometry of the high-dimensional data samples than previous work.", "source": "arxiv/ml"}
{"id": "arxiv:444", "title": "Kernel machines with two layers and multiple kernel learning", "text": "In this paper, the framework of kernel machines with two layers is introduced, generalizing classical kernel methods. The new learning methodology provide a formal connection between computational architectures with multiple layers and the theme of kernel learning in standard regularization methods. First, a representer theorem for two-layer networks is presented, showing that finite linear combinations of kernels on each layer are optimal architectures whenever the corresponding functions solve suitable variational problems in reproducing kernel Hilbert spaces (RKHS). The input-output map expressed by these architectures turns out to be equivalent to a suitable single-layer kernel machines in which the kernel function is also learned from the data. Recently, the so-called multiple kernel learning methods have attracted considerable attention in the machine learning literature. In this paper, multiple kernel learning methods are shown to be specific cases of kernel machines with two layers in which the second layer is linear. Finally, a simple and effective multiple kernel learning method called RLS2 (regularized least squares with two layers) is introduced, and his performances on several learning problems are extensively analyzed. An open source MATLAB toolbox to train and validate RLS2 models with a Graphic User Interface is available.", "source": "arxiv/ml"}
{"id": "arxiv:445", "title": "A Monte Carlo Algorithm for Universally Optimal Bayesian Sequence Prediction and Planning", "text": "The aim of this work is to address the question of whether we can in principle design rational decision-making agents or artificial intelligences embedded in computable physics such that their decisions are optimal in reasonable mathematical senses. Recent developments in rare event probability estimation, recursive bayesian inference, neural networks, and probabilistic planning are sufficient to explicitly approximate reinforcement learners of the AIXI style with non-trivial model classes (here, the class of resource-bounded Turing machines). Consideration of the effects of resource limitations in a concrete implementation leads to insights about possible architectures for learning systems using optimal decision makers as components.", "source": "arxiv/ml"}
{"id": "arxiv:446", "title": "Asymptotic Learning Curve and Renormalizable Condition in Statistical Learning Theory", "text": "Bayes statistics and statistical physics have the common mathematical structure, where the log likelihood function corresponds to the random Hamiltonian. Recently, it was discovered that the asymptotic learning curves in Bayes estimation are subject to a universal law, even if the log likelihood function can not be approximated by any quadratic form. However, it is left unknown what mathematical property ensures such a universal law. In this paper, we define a renormalizable condition of the statistical estimation problem, and show that, under such a condition, the asymptotic learning curves are ensured to be subject to the universal law, even if the true distribution is unrealizable and singular for a statistical model. Also we study a nonrenormalizable case, in which the learning curves have the different asymptotic behaviors from the universal law.", "source": "arxiv/ml"}
{"id": "arxiv:447", "title": "Feature Extraction for Universal Hypothesis Testing via Rank-constrained Optimization", "text": "This paper concerns the construction of tests for universal hypothesis testing problems, in which the alternate hypothesis is poorly modeled and the observation space is large. The mismatched universal test is a feature-based technique for this purpose. In prior work it is shown that its finite-observation performance can be much better than the (optimal) Hoeffding test, and good performance depends crucially on the choice of features. The contributions of this paper include: 1) We obtain bounds on the number of \\epsilon distinguishable distributions in an exponential family. 2) This motivates a new framework for feature extraction, cast as a rank-constrained optimization problem. 3) We obtain a gradient-based algorithm to solve the rank-constrained optimization problem and prove its local convergence.", "source": "arxiv/ml"}
{"id": "arxiv:448", "title": "The dynamics of message passing on dense graphs, with applications to compressed sensing", "text": "Approximate message passing algorithms proved to be extremely effective in reconstructing sparse signals from a small number of incoherent linear measurements. Extensive numerical experiments further showed that their dynamics is accurately tracked by a simple one-dimensional iteration termed state evolution. In this paper we provide the first rigorous foundation to state evolution. We prove that indeed it holds asymptotically in the large system limit for sensing matrices with independent and identically distributed gaussian entries. While our focus is on message passing algorithms for compressed sensing, the analysis extends beyond this setting, to a general class of algorithms on dense graphs. In this context, state evolution plays the role that density evolution has for sparse graphs. The proof technique is fundamentally different from the standard approach to density evolution, in that it copes with large number of short loops in the underlying factor graph. It relies instead on a conditioning technique recently developed by Erwin Bolthausen in the context of spin glass theory.", "source": "arxiv/ml"}
{"id": "arxiv:449", "title": "Role of Interestingness Measures in CAR Rule Ordering for Associative Classifier: An Empirical Approach", "text": "Associative Classifier is a novel technique which is the integration of Association Rule Mining and Classification. The difficult task in building Associative Classifier model is the selection of relevant rules from a large number of class association rules (CARs). A very popular method of ordering rules for selection is based on confidence, support and antecedent size (CSA). Other methods are based on hybrid orderings in which CSA method is combined with other measures. In the present work, we study the effect of using different interestingness measures of Association rules in CAR rule ordering and selection for associative classifier.", "source": "arxiv/ml"}
{"id": "arxiv:450", "title": "SVM-based Multiview Face Recognition by Generalization of Discriminant Analysis", "text": "Identity verification of authentic persons by their multiview faces is a real valued problem in machine vision. Multiview faces are having difficulties due to non-linear representation in the feature space. This paper illustrates the usability of the generalization of LDA in the form of canonical covariate for face recognition to multiview faces. In the proposed work, the Gabor filter bank is used to extract facial features that characterized by spatial frequency, spatial locality and orientation. Gabor face representation captures substantial amount of variations of the face instances that often occurs due to illumination, pose and facial expression changes. Convolution of Gabor filter bank to face images of rotated profile views produce Gabor faces with high dimensional features vectors. Canonical covariate is then used to Gabor faces to reduce the high dimensional feature spaces into low dimensional subspaces. Finally, support vector machines are trained with canonical sub-spaces that contain reduced set of features and perform recognition task. The proposed system is evaluated with UMIST face database. The experiment results demonstrate the efficiency and robustness of the proposed system with high recognition rates.", "source": "arxiv/ml"}
{"id": "arxiv:451", "title": "Probabilistic Approach to Neural Networks Computation Based on Quantum Probability Model Probabilistic Principal Subspace Analysis Example", "text": "In this paper, we introduce elements of probabilistic model that is suitable for modeling of learning algorithms in biologically plausible artificial neural networks framework. Model is based on two of the main concepts in quantum physics - a density matrix and the Born rule. As an example, we will show that proposed probabilistic interpretation is suitable for modeling of on-line learning algorithms for PSA, which are preferably realized by a parallel hardware based on very simple computational units. Proposed concept (model) can be used in the context of improving algorithm convergence speed, learning factor choice, or input signal scale robustness. We are going to see how the Born rule and the Hebbian learning rule are connected", "source": "arxiv/ml"}
{"id": "arxiv:452", "title": "X-Armed Bandits", "text": "We consider a generalization of stochastic bandits where the set of arms, $\\cX$, is allowed to be a generic measurable space and the mean-payoff function is \"locally Lipschitz\" with respect to a dissimilarity function that is known to the decision maker. Under this condition we construct an arm selection policy, called HOO (hierarchical optimistic optimization), with improved regret bounds compared to previous results for a large class of problems. In particular, our results imply that if $\\cX$ is the unit hypercube in a Euclidean space and the mean-payoff function has a finite number of global maxima around which the behavior of the function is locally continuous with a known smoothness degree, then the expected regret of HOO is bounded up to a logarithmic factor by $\\sqrt{n}$, i.e., the rate of growth of the regret is independent of the dimension of the space. We also prove the minimax optimality of our algorithm when the dissimilarity is a metric. Our basic strategy has quadratic computational complexity as a function of the number of time steps and does not rely on the doubling trick. We also introduce a modified strategy, which relies on the doubling trick but runs in linearithmic time. Both results are improvements with respect to previous approaches.", "source": "arxiv/ml"}
{"id": "arxiv:453", "title": "Trajectory Clustering and an Application to Airspace Monitoring", "text": "This paper presents a framework aimed at monitoring the behavior of aircraft in a given airspace. Nominal trajectories are determined and learned using data driven methods. Standard procedures are used by air traffic controllers (ATC) to guide aircraft, ensure the safety of the airspace, and to maximize the runway occupancy. Even though standard procedures are used by ATC, the control of the aircraft remains with the pilots, leading to a large variability in the flight patterns observed. Two methods to identify typical operations and their variability from recorded radar tracks are presented. This knowledge base is then used to monitor the conformance of current operations against operations previously identified as standard. A tool called AirTrajectoryMiner is presented, aiming at monitoring the instantaneous health of the airspace, in real time. The airspace is \"healthy\" when all aircraft are flying according to the nominal procedures. A measure of complexity is introduced, measuring the conformance of current flight to nominal flight patterns. When an aircraft does not conform, the complexity increases as more attention from ATC is required to ensure a safe separation between aircraft.", "source": "arxiv/ml"}
{"id": "arxiv:454", "title": "Performance Comparisons of PSO based Clustering", "text": "In this paper we have investigated the performance of PSO Particle Swarm Optimization based clustering on few real world data sets and one artificial data set. The performances are measured by two metric namely quantization error and inter-cluster distance. The K means clustering algorithm is first implemented for all data sets, the results of which form the basis of comparison of PSO based approaches. We have explored different variants of PSO such as gbest, lbest ring, lbest vonneumann and Hybrid PSO for comparison purposes. The results reveal that PSO based clustering algorithms perform better compared to K means in all data sets.", "source": "arxiv/ml"}
{"id": "arxiv:455", "title": "Feature Level Clustering of Large Biometric Database", "text": "This paper proposes an efficient technique for partitioning large biometric database during identification. In this technique feature vector which comprises of global and local descriptors extracted from offline signature are used by fuzzy clustering technique to partition the database. As biometric features posses no natural order of sorting, thus it is difficult to index them alphabetically or numerically. Hence, some supervised criteria is required to partition the search space. At the time of identification the fuzziness criterion is introduced to find the nearest clusters for declaring the identity of query sample. The system is tested using bin-miss rate and performs better in comparison to traditional k-means approach.", "source": "arxiv/ml"}
{"id": "arxiv:456", "title": "Fusion of Multiple Matchers using SVM for Offline Signature Identification", "text": "This paper uses Support Vector Machines (SVM) to fuse multiple classifiers for an offline signature system. From the signature images, global and local features are extracted and the signatures are verified with the help of Gaussian empirical rule, Euclidean and Mahalanobis distance based classifiers. SVM is used to fuse matching scores of these matchers. Finally, recognition of query signatures is done by comparing it with all signatures of the database. The proposed system is tested on a signature database contains 5400 offline signatures of 600 individuals and the results are found to be promising.", "source": "arxiv/ml"}
{"id": "arxiv:457", "title": "Aggregating Algorithm competing with Banach lattices", "text": "The paper deals with on-line regression settings with signals belonging to a Banach lattice. Our algorithms work in a semi-online setting where all the inputs are known in advance and outcomes are unknown and given step by step. We apply the Aggregating Algorithm to construct a prediction method whose cumulative loss over all the input vectors is comparable with the cumulative loss of any linear functional on the Banach lattice. As a by-product we get an algorithm that takes signals from an arbitrary domain. Its cumulative loss is comparable with the cumulative loss of any predictor function from Besov and Triebel-Lizorkin spaces. We describe several applications of our setting.", "source": "arxiv/ml"}
{"id": "arxiv:458", "title": "Efficient Bayesian Learning in Social Networks with Gaussian Estimators", "text": "We consider a group of Bayesian agents who try to estimate a state of the world $\\theta$ through interaction on a social network. Each agent $v$ initially receives a private measurement of $\\theta$: a number $S_v$ picked from a Gaussian distribution with mean $\\theta$ and standard deviation one. Then, in each discrete time iteration, each reveals its estimate of $\\theta$ to its neighbors, and, observing its neighbors' actions, updates its belief using Bayes' Law. This process aggregates information efficiently, in the sense that all the agents converge to the belief that they would have, had they access to all the private measurements. We show that this process is computationally efficient, so that each agent's calculation can be easily carried out. We also show that on any graph the process converges after at most $2N \\cdot D$ steps, where $N$ is the number of agents and $D$ is the diameter of the network. Finally, we show that on trees and on distance transitive-graphs the process converges after $D$ steps, and that it preserves privacy, so that agents learn very little about the private signal of most other agents, despite the efficient aggregation of information. Our results extend those in an unpublished manuscript of the first and last authors.", "source": "arxiv/ml"}
{"id": "arxiv:459", "title": "Prequential Plug-In Codes that Achieve Optimal Redundancy Rates even if the Model is Wrong", "text": "We analyse the prequential plug-in codes relative to one-parameter exponential families M. We show that if data are sampled i.i.d. from some distribution outside M, then the redundancy of any plug-in prequential code grows at rate larger than 1/2 ln(n) in the worst case. This means that plug-in codes, such as the Rissanen-Dawid ML code, may behave inferior to other important universal codes such as the 2-part MDL, Shtarkov and Bayes codes, for which the redundancy is always 1/2 ln(n) + O(1). However, we also show that a slight modification of the ML plug-in code, \"almost\" in the model, does achieve the optimal redundancy even if the the true distribution is outside M.", "source": "arxiv/ml"}
{"id": "arxiv:460", "title": "A CHAID Based Performance Prediction Model in Educational Data Mining", "text": "The performance in higher secondary school education in India is a turning point in the academic lives of all students. As this academic performance is influenced by many factors, it is essential to develop predictive data mining model for students' performance so as to identify the slow learners and study the influence of the dominant factors on their academic performance. In the present investigation, a survey cum experimental methodology was adopted to generate a database and it was constructed from a primary and a secondary source. While the primary data was collected from the regular students, the secondary data was gathered from the school and office of the Chief Educational Officer (CEO). A total of 1000 datasets of the year 2006 from five different schools in three different districts of Tamilnadu were collected. The raw data was preprocessed in terms of filling up missing values, transforming values in one form into another and relevant attribute/ variable selection. As a result, we had 772 student records, which were used for CHAID prediction model construction. A set of prediction rules were extracted from CHIAD prediction model and the efficiency of the generated CHIAD prediction model was found. The accuracy of the present model was compared with other model and it has been found to be satisfactory.", "source": "arxiv/ml"}
{"id": "arxiv:461", "title": "Dimensionality Reduction: An Empirical Study on the Usability of IFE-CF (Independent Feature Elimination- by C-Correlation and F-Correlation) Measures", "text": "The recent increase in dimensionality of data has thrown a great challenge to the existing dimensionality reduction methods in terms of their effectiveness. Dimensionality reduction has emerged as one of the significant preprocessing steps in machine learning applications and has been effective in removing inappropriate data, increasing learning accuracy, and improving comprehensibility. Feature redundancy exercises great influence on the performance of classification process. Towards the better classification performance, this paper addresses the usefulness of truncating the highly correlated and redundant attributes. Here, an effort has been made to verify the utility of dimensionality reduction by applying LVQ (Learning Vector Quantization) method on two Benchmark datasets of 'Pima Indian Diabetic patients' and 'Lung cancer patients'.", "source": "arxiv/ml"}
{"id": "arxiv:462", "title": "A Minimum Relative Entropy Controller for Undiscounted Markov Decision Processes", "text": "Adaptive control problems are notoriously difficult to solve even in the presence of plant-specific controllers. One way to by-pass the intractable computation of the optimal policy is to restate the adaptive control as the minimization of the relative entropy of a controller that ignores the true plant dynamics from an informed controller. The solution is given by the Bayesian control rule-a set of equations characterizing a stochastic adaptive controller for the class of possible plant dynamics. Here, the Bayesian control rule is applied to derive BCR-MDP, a controller to solve undiscounted Markov decision processes with finite state and action spaces and unknown dynamics. In particular, we derive a non-parametric conjugate prior distribution over the policy space that encapsulates the agent's whole relevant history and we present a Gibbs sampler to draw random policies from this distribution. Preliminary results show that BCR-MDP successfully avoids sub-optimal limit cycles due to its built-in mechanism to balance exploration versus exploitation.", "source": "arxiv/ml"}
{"id": "arxiv:463", "title": "Online Distributed Sensor Selection", "text": "A key problem in sensor networks is to decide which sensors to query when, in order to obtain the most useful information (e.g., for performing accurate prediction), subject to constraints (e.g., on power and bandwidth). In many applications the utility function is not known a priori, must be learned from data, and can even change over time. Furthermore for large sensor networks solving a centralized optimization problem to select sensors is not feasible, and thus we seek a fully distributed solution. In this paper, we present Distributed Online Greedy (DOG), an efficient, distributed algorithm for repeatedly selecting sensors online, only receiving feedback about the utility of the selected sensors. We prove very strong theoretical no-regret guarantees that apply whenever the (unknown) utility function satisfies a natural diminishing returns property called submodularity. Our algorithm has extremely low communication requirements, and scales well to large sensor deployments. We extend DOG to allow observation-dependent sensor selection. We empirically demonstrate the effectiveness of our algorithm on several real-world sensing tasks.", "source": "arxiv/ml"}
{"id": "arxiv:464", "title": "On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers", "text": "Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-stability is sufficient for consistency of Empirical Risk Minimization while distribution-free CV-stability is necessary and sufficient for having finite VC-dimension. This paper concerns a phase transition in the training stability of ERM, conjectured by the same authors. Kutin and Niyogi proved that ERM on finite hypothesis spaces containing a unique risk minimizer has training stability that scales exponentially with sample size, and conjectured that the existence of multiple risk minimizers prevents even super-quadratic convergence. We prove this result for the strictly weaker notion of CV-stability, positively resolving the conjecture.", "source": "arxiv/ml"}
{"id": "arxiv:465", "title": "Intrinsic dimension estimation of data by principal component analysis", "text": "Estimating intrinsic dimensionality of data is a classic problem in pattern recognition and statistics. Principal Component Analysis (PCA) is a powerful tool in discovering dimensionality of data sets with a linear structure; it, however, becomes ineffective when data have a nonlinear structure. In this paper, we propose a new PCA-based method to estimate intrinsic dimension of data with nonlinear structures. Our method works by first finding a minimal cover of the data set, then performing PCA locally on each subset in the cover and finally giving the estimation result by checking up the data variance on all small neighborhood regions. The proposed method utilizes the whole data set to estimate its intrinsic dimension and is convenient for incremental learning. In addition, our new PCA procedure can filter out noise in data and converge to a stable estimation with the neighborhood region size increasing. Experiments on synthetic and real world data sets show effectiveness of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:466", "title": "Reverse Engineering Financial Markets with Majority and Minority Games using Genetic Algorithms", "text": "Using virtual stock markets with artificial interacting software investors, aka agent-based models (ABMs), we present a method to reverse engineer real-world financial time series. We model financial markets as made of a large number of interacting boundedly rational agents. By optimizing the similarity between the actual data and that generated by the reconstructed virtual stock market, we obtain parameters and strategies, which reveal some of the inner workings of the target stock market. We validate our approach by out-of-sample predictions of directional moves of the Nasdaq Composite Index.", "source": "arxiv/ml"}
{"id": "arxiv:467", "title": "A Generalization of the Chow-Liu Algorithm and its Application to Statistical Learning", "text": "We extend the Chow-Liu algorithm for general random variables while the previous versions only considered finite cases. In particular, this paper applies the generalization to Suzuki's learning algorithm that generates from data forests rather than trees based on the minimum description length by balancing the fitness of the data to the forest and the simplicity of the forest. As a result, we successfully obtain an algorithm when both of the Gaussian and finite random variables are present.", "source": "arxiv/ml"}
{"id": "arxiv:468", "title": "Application of k Means Clustering algorithm for prediction of Students Academic Performance", "text": "The ability to monitor the progress of students academic performance is a critical issue to the academic community of higher learning. A system for analyzing students results based on cluster analysis and uses standard statistical algorithms to arrange their scores data according to the level of their performance is described. In this paper, we also implemented k mean clustering algorithm for analyzing students result data. The model was combined with the deterministic model to analyze the students results of a private Institution in Nigeria which is a good benchmark to monitor the progression of academic performance of students in higher Institution for the purpose of making an effective decision by the academic planners.", "source": "arxiv/ml"}
{"id": "arxiv:469", "title": "Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm", "text": "We show that matrix completion with trace-norm regularization can be significantly hurt when entries of the matrix are sampled non-uniformly. We introduce a weighted version of the trace-norm regularizer that works well also with non-uniform sampling. Our experimental results demonstrate that the weighted trace-norm regularization indeed yields significant gains on the (highly non-uniformly sampled) Netflix dataset.", "source": "arxiv/ml"}
{"id": "arxiv:470", "title": "Convergence of Bayesian Control Rule", "text": "Recently, new approaches to adaptive control have sought to reformulate the problem as a minimization of a relative entropy criterion to obtain tractable solutions. In particular, it has been shown that minimizing the expected deviation from the causal input-output dependencies of the true plant leads to a new promising stochastic control rule called the Bayesian control rule. This work proves the convergence of the Bayesian control rule under two sufficient assumptions: boundedness, which is an ergodicity condition; and consistency, which is an instantiation of the sure-thing principle.", "source": "arxiv/ml"}
{"id": "arxiv:471", "title": "A new approach to content-based file type detection", "text": "File type identification and file type clustering may be difficult tasks that have an increasingly importance in the field of computer and network security. Classical methods of file type detection including considering file extensions and magic bytes can be easily spoofed. Content-based file type detection is a newer way that is taken into account recently. In this paper, a new content-based method for the purpose of file type detection and file type clustering is proposed that is based on the PCA and neural networks. The proposed method has a good accuracy and is fast enough.", "source": "arxiv/ml"}
{"id": "arxiv:472", "title": "A Complete Characterization of Statistical Query Learning with Applications to Evolvability", "text": "Statistical query (SQ) learning model of Kearns (1993) is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical properties of the examples but cannot see the examples themselves. We describe a new and simple characterization of the query complexity of learning in the SQ learning model. Unlike the previously known bounds on SQ learning our characterization preserves the accuracy and the efficiency of learning. The preservation of accuracy implies that that our characterization gives the first characterization of SQ learning in the agnostic learning framework. The preservation of efficiency is achieved using a new boosting technique and allows us to derive a new approach to the design of evolutionary algorithms in Valiant's (2006) model of evolvability. We use this approach to demonstrate the existence of a large class of monotone evolutionary learning algorithms based on square loss performance estimation. These results differ significantly from the few known evolutionary algorithms and give evidence that evolvability in Valiant's model is a more versatile phenomenon than there had been previous reason to suspect.", "source": "arxiv/ml"}
{"id": "arxiv:473", "title": "Interactive Submodular Set Cover", "text": "We introduce a natural generalization of submodular set cover and exact active learning with a finite hypothesis class (query learning). We call this new problem interactive submodular set cover. Applications include advertising in social networks with hidden information. We give an approximation guarantee for a novel greedy algorithm and give a hardness of approximation result which matches up to constant factors. We also discuss negative results for simpler approaches and present encouraging early experimental results.", "source": "arxiv/ml"}
{"id": "arxiv:474", "title": "Word level Script Identification from Bangla and Devanagri Handwritten Texts mixed with Roman Script", "text": "India is a multi-lingual country where Roman script is often used alongside different Indic scripts in a text document. To develop a script specific handwritten Optical Character Recognition (OCR) system, it is therefore necessary to identify the scripts of handwritten text correctly. In this paper, we present a system, which automatically separates the scripts of handwritten words from a document, written in Bangla or Devanagri mixed with Roman scripts. In this script separation technique, we first, extract the text lines and words from document pages using a script independent Neighboring Component Analysis technique. Then we have designed a Multi Layer Perceptron (MLP) based classifier for script separation, trained with 8 different wordlevel holistic features. Two equal sized datasets, one with Bangla and Roman scripts and the other with Devanagri and Roman scripts, are prepared for the system evaluation. On respective independent text samples, word-level script identification accuracies of 99.29% and 98.43% are achieved.", "source": "arxiv/ml"}
{"id": "arxiv:475", "title": "Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier", "text": "A novel approach for recognition of handwritten compound Bangla characters, along with the Basic characters of Bangla alphabet, is presented here. Compared to English like Roman script, one of the major stumbling blocks in Optical Character Recognition (OCR) of handwritten Bangla script is the large number of complex shaped character classes of Bangla alphabet. In addition to 50 basic character classes, there are nearly 160 complex shaped compound character classes in Bangla alphabet. Dealing with such a large varieties of handwritten characters with a suitably designed feature set is a challenging problem. Uncertainty and imprecision are inherent in handwritten script. Moreover, such a large varieties of complex shaped characters, some of which have close resemblance, makes the problem of OCR of handwritten Bangla characters more difficult. Considering the complexity of the problem, the present approach makes an attempt to identify compound character classes from most frequently to less frequently occurred ones, i.e., in order of importance. This is to develop a frame work for incrementally increasing the number of learned classes of compound characters from more frequently occurred ones to less frequently occurred ones along with Basic characters. On experimentation, the technique is observed produce an average recognition rate of 79.25 after three fold cross validation of data with future scope of improvement and extension.", "source": "arxiv/ml"}
{"id": "arxiv:476", "title": "Supervised Classification Performance of Multispectral Images", "text": "Nowadays government and private agencies use remote sensing imagery for a wide range of applications from military applications to farm development. The images may be a panchromatic, multispectral, hyperspectral or even ultraspectral of terra bytes. Remote sensing image classification is one amongst the most significant application worlds for remote sensing. A few number of image classification algorithms have proved good precision in classifying remote sensing data. But, of late, due to the increasing spatiotemporal dimensions of the remote sensing data, traditional classification algorithms have exposed weaknesses necessitating further research in the field of remote sensing image classification. So an efficient classifier is needed to classify the remote sensing images to extract information. We are experimenting with both supervised and unsupervised classification. Here we compare the different classification methods and their performances. It is found that Mahalanobis classifier performed the best in our classification.", "source": "arxiv/ml"}
{"id": "arxiv:477", "title": "Contextual Bandit Algorithms with Supervised Learning Guarantees", "text": "We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm called Exp4.P, we show that it is possible to compete with the best in a set of $N$ experts with probability $1-\\delta$ while incurring regret at most $O(\\sqrt{KT\\ln(N/\\delta)})$ over $T$ time steps. The new algorithm is tested empirically in a large-scale, real-world dataset. Second, we give a new algorithm called VE that competes with a possibly infinite set of policies of VC-dimension $d$ while incurring regret at most $O(\\sqrt{T(d\\ln(T) + \\ln (1/\\delta))})$ with probability $1-\\delta$. These guarantees improve on those of all previous algorithms, whether in a stochastic or adversarial environment, and bring us closer to providing supervised learning type guarantees for the contextual bandit setting.", "source": "arxiv/ml"}
{"id": "arxiv:478", "title": "Principal Component Analysis with Contaminated Data: The High Dimensional Case", "text": "We consider the dimensionality-reduction problem (finding a subspace approximation of observed data) for contaminated data in the high dimensional regime, where the number of observations is of the same magnitude as the number of variables of each observation, and the data set contains some (arbitrarily) corrupted observations. We propose a High-dimensional Robust Principal Component Analysis (HR-PCA) algorithm that is tractable, robust to contaminated points, and easily kernelizable. The resulting subspace has a bounded deviation from the desired one, achieves maximal robustness -- a breakdown point of 50% while all existing algorithms have a breakdown point of zero, and unlike ordinary PCA algorithms, achieves optimality in the limit case where the proportion of corrupted points goes to zero.", "source": "arxiv/ml"}
{"id": "arxiv:479", "title": "Gaussian Process Structural Equation Models with Latent Variables", "text": "In a variety of disciplines such as social sciences, psychology, medicine and economics, the recorded data are considered to be noisy measurements of latent variables connected by some causal structure. This corresponds to a family of graphical models known as the structural equation model with latent variables. While linear non-Gaussian variants have been well-studied, inference in nonparametric structural equation models is still underdeveloped. We introduce a sparse Gaussian process parameterization that defines a non-linear structure connecting latent variables, unlike common formulations of Gaussian process latent variable models. The sparse parameterization is given a full Bayesian treatment without compromising Markov chain Monte Carlo efficiency. We compare the stability of the sampling procedure and the predictive ability of the model against the current practice.", "source": "arxiv/ml"}
{"id": "arxiv:480", "title": "Less Regret via Online Conditioning", "text": "We analyze and evaluate an online gradient descent algorithm with adaptive per-coordinate adjustment of learning rates. Our algorithm can be thought of as an online version of batch gradient descent with a diagonal preconditioner. This approach leads to regret bounds that are stronger than those of standard online gradient descent for general online convex optimization problems. Experimentally, we show that our algorithm is competitive with state-of-the-art algorithms for large scale machine learning problems.", "source": "arxiv/ml"}
{"id": "arxiv:481", "title": "Adaptive Bound Optimization for Online Convex Optimization", "text": "We introduce a new online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions observed so far. This is in contrast to previous algorithms that use a fixed regularization function such as L2-squared, and modify it only via a single time-dependent parameter. Our algorithm's regret bounds are worst-case optimal, and for certain realistic classes of loss functions they are much better than existing bounds. These bounds are problem-dependent, which means they can exploit the structure of the actual problem instance. Critically, however, our algorithm does not need to know this structure in advance. Rather, we prove competitive guarantees that show the algorithm provides a bound within a constant factor of the best possible bound (of a certain functional form) in hindsight.", "source": "arxiv/ml"}
{"id": "arxiv:482", "title": "Asymptotic Analysis of Generative Semi-Supervised Learning", "text": "Semisupervised learning has emerged as a popular framework for improving modeling accuracy while controlling labeling cost. Based on an extension of stochastic composite likelihood we quantify the asymptotic accuracy of generative semi-supervised learning. In doing so, we complement distribution-free analysis by providing an alternative framework to measure the value associated with different labeling policies and resolve the fundamental question of how much data to label and in what manner. We demonstrate our approach with both simulation studies and real world experiments using naive Bayes for text classification and MRFs and CRFs for structured prediction in NLP.", "source": "arxiv/ml"}
{"id": "arxiv:483", "title": "A New Understanding of Prediction Markets Via No-Regret Learning", "text": "We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We show that any cost function based prediction market can be interpreted as an algorithm for the commonly studied problem of learning from expert advice by equating trades made in the market with losses observed by the learning algorithm. If the loss of the market organizer is bounded, this bound can be used to derive an O(sqrt(T)) regret bound for the corresponding learning algorithm. We then show that the class of markets with convex cost functions exactly corresponds to the class of Follow the Regularized Leader learning algorithms, with the choice of a cost function in the market corresponding to the choice of a regularizer in the learning problem. Finally, we show an equivalence between market scoring rules and prediction markets with convex cost functions. This implies that market scoring rules can also be interpreted naturally as Follow the Regularized Leader algorithms, and may be of independent interest. These connections provide new insight into how it is that commonly studied markets, such as the Logarithmic Market Scoring Rule, can aggregate opinions into accurate estimates of the likelihood of future events.", "source": "arxiv/ml"}
{"id": "arxiv:484", "title": "Non-Sparse Regularization for Multiple Kernel Learning", "text": "Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and scalability. Unfortunately, this 1-norm MKL is rarely observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures, we generalize MKL to arbitrary norms. We devise new insights on the connection between several existing MKL formulations and develop two efficient interleaved optimization strategies for arbitrary norms, like p-norms with p>1. Empirically, we demonstrate that the interleaved optimization strategies are much faster compared to the commonly used wrapper approaches. A theoretical analysis and an experiment on controlled artificial data experiment sheds light on the appropriateness of sparse, non-sparse and $\\ell_\\infty$-norm MKL in various scenarios. Empirical applications of p-norm MKL to three real-world problems from computational biology show that non-sparse MKL achieves accuracies that go beyond the state-of-the-art.", "source": "arxiv/ml"}
{"id": "arxiv:485", "title": "Learning from Logged Implicit Exploration Data", "text": "We provide a sound and consistent foundation for the use of \\emph{nonrandom} exploration data in \"contextual bandit\" or \"partially labeled\" settings where only the value of a chosen action is learned. The primary challenge in a variety of settings is that the exploration policy, in which \"offline\" data is logged, is not explicitly known. Prior solutions here require either control of the actions during the learning process, recorded random exploration, or actions chosen obliviously in a repeated manner. The techniques reported here lift these restrictions, allowing the learning of a policy for choosing actions given features from historical data where no randomization occurred or was logged. We empirically verify our solution on two reasonably sized sets of real-world data obtained from Yahoo!.", "source": "arxiv/ml"}
{"id": "arxiv:486", "title": "A Contextual-Bandit Approach to Personalized News Article Recommendation", "text": "Personalized web services strive to adapt their services (advertisements, news articles, etc) to individual users by making use of both content and user information. Despite a few recent advances, this problem remains challenging for at least two reasons. First, web service is featured with dynamically changing pools of content, rendering traditional collaborative filtering methods inapplicable. Second, the scale of most web services of practical interest calls for solutions that are both fast in learning and computation. In this work, we model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks. The contributions of this work are three-fold. First, we propose a new, general contextual bandit algorithm that is computationally efficient and well motivated from learning theory. Second, we argue that any bandit algorithm can be reliably evaluated offline using previously recorded random traffic. Finally, using this offline evaluation method, we successfully applied our new algorithm to a Yahoo! Front Page Today Module dataset containing over 33 million events. Results showed a 12.5% click lift compared to a standard context-free bandit algorithm, and the advantage becomes even greater when data gets more scarce.", "source": "arxiv/ml"}
{"id": "arxiv:487", "title": "Detecting Weak but Hierarchically-Structured Patterns in Networks", "text": "The ability to detect weak distributed activation patterns in networks is critical to several applications, such as identifying the onset of anomalous activity or incipient congestion in the Internet, or faint traces of a biochemical spread by a sensor network. This is a challenging problem since weak distributed patterns can be invisible in per node statistics as well as a global network-wide aggregate. Most prior work considers situations in which the activation/non-activation of each node is statistically independent, but this is unrealistic in many problems. In this paper, we consider structured patterns arising from statistical dependencies in the activation process. Our contributions are three-fold. First, we propose a sparsifying transform that succinctly represents structured activation patterns that conform to a hierarchical dependency graph. Second, we establish that the proposed transform facilitates detection of very weak activation patterns that cannot be detected with existing methods. Third, we show that the structure of the hierarchical dependency graph governing the activation process, and hence the network transform, can be learnt from very few (logarithmic in network size) independent snapshots of network activity.", "source": "arxiv/ml"}
{"id": "arxiv:488", "title": "Unsupervised Supervised Learning II: Training Margin Based Classifiers without Labels", "text": "Many popular linear classifiers, such as logistic regression, boosting, or SVM, are trained by optimizing a margin-based risk function. Traditionally, these risk functions are computed based on a labeled dataset. We develop a novel technique for estimating such risks using only unlabeled data and the marginal label distribution. We prove that the proposed risk estimator is consistent on high-dimensional datasets and demonstrate it on synthetic and real-world data. In particular, we show how the estimate is used for evaluating classifiers in transfer learning, and for training classifiers with no labeled data whatsoever.", "source": "arxiv/ml"}
{"id": "arxiv:489", "title": "Model Selection with the Loss Rank Principle", "text": "A key issue in statistics and machine learning is to automatically select the \"right\" model complexity, e.g., the number of neighbors to be averaged over in k nearest neighbor (kNN) regression or the polynomial degree in regression with polynomials. We suggest a novel principle - the Loss Rank Principle (LoRP) - for model selection in regression and classification. It is based on the loss rank, which counts how many other (fictitious) data would be fitted better. LoRP selects the model that has minimal loss rank. Unlike most penalized maximum likelihood variants (AIC, BIC, MDL), LoRP depends only on the regression functions and the loss function. It works without a stochastic noise model, and is directly applicable to any non-parametric regressor, like kNN.", "source": "arxiv/ml"}
{"id": "arxiv:490", "title": "A Unified Algorithmic Framework for Multi-Dimensional Scaling", "text": "In this paper, we propose a unified algorithmic framework for solving many known variants of \\mds. Our algorithm is a simple iterative scheme with guaranteed convergence, and is \\emph{modular}; by changing the internals of a single subroutine in the algorithm, we can switch cost functions and target spaces easily. In addition to the formal guarantees of convergence, our algorithms are accurate; in most cases, they converge to better quality solutions than existing methods, in comparable time. We expect that this framework will be useful for a number of \\mds variants that have not yet been studied. Our framework extends to embedding high-dimensional points lying on a sphere to points on a lower dimensional sphere, preserving geodesic distances. As a compliment to this result, we also extend the Johnson-Lindenstrauss Lemma to this spherical setting, where projecting to a random $O((1/\\eps^2) \\log n)$-dimensional sphere causes $\\eps$-distortion.", "source": "arxiv/ml"}
{"id": "arxiv:491", "title": "Statistical and Computational Tradeoffs in Stochastic Composite Likelihood", "text": "Maximum likelihood estimators are often of limited practical use due to the intensive computation they require. We propose a family of alternative estimators that maximize a stochastic variation of the composite likelihood function. Each of the estimators resolve the computation-accuracy tradeoff differently, and taken together they span a continuous spectrum of computation-accuracy tradeoff resolutions. We prove the consistency of the estimators, provide formulas for their asymptotic variance, statistical robustness, and computational complexity. We discuss experimental results in the context of Boltzmann machines and conditional random fields. The theoretical and experimental studies demonstrate the effectiveness of the estimators when the computational resources are insufficient. They also demonstrate that in some cases reduced computational complexity is associated with robustness thereby increasing statistical accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:492", "title": "Exponential Family Hybrid Semi-Supervised Learning", "text": "We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/discriminative models. Our model is more flexible and natural than previous approaches. Experimental results on several data sets show that our approach also performs better in practice.", "source": "arxiv/ml"}
{"id": "arxiv:493", "title": "Learning by random walks in the weight space of the Ising perceptron", "text": "Several variants of a stochastic local search process for constructing the synaptic weights of an Ising perceptron are studied. In this process, binary patterns are sequentially presented to the Ising perceptron and are then learned as the synaptic weight configuration is modified through a chain of single- or double-weight flips within the compatible weight configuration space of the earlier learned patterns. This process is able to reach a storage capacity of $\\alpha \\approx 0.63$ for pattern length N = 101 and $\\alpha \\approx 0.41$ for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of $\\alpha \\approx 0.80$ for N = 101 and $\\alpha \\approx 0.42$ for N=1001. We found that, for a given learning task, the solutions constructed by the random walk learning process are separated by a typical Hamming distance, which decreases with the constraint density $\\alpha$ of the learning task; at a fixed value of $\\alpha$, the width of the Hamming distance distributions decreases with $N$.", "source": "arxiv/ml"}
{"id": "arxiv:494", "title": "From Frequency to Meaning: Vector Space Models of Semantics", "text": "Computers understand very little of the meaning of human language. This profoundly limits our ability to give instructions to computers, the ability of computers to explain their actions to us, and the ability of computers to analyse and process text. Vector space models (VSMs) of semantics are beginning to address these limits. This paper surveys the use of VSMs for semantic processing of text. We organize the literature on VSMs according to the structure of the matrix in a VSM. There are currently three broad classes of VSMs, based on term-document, word-context, and pair-pattern matrices, yielding three classes of applications. We survey a broad range of applications in these three categories and we take a detailed look at a specific open source project in each category. Our goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs for those who are already familiar with the area, and to provide pointers into the literature for those who are less familiar with the field.", "source": "arxiv/ml"}
{"id": "arxiv:495", "title": "Hitting and commute times in large graphs are often misleading", "text": "Next to the shortest path distance, the second most popular distance function between vertices in a graph is the commute distance (resistance distance). For two vertices u and v, the hitting time H_{uv} is the expected time it takes a random walk to travel from u to v. The commute time is its symmetrized version C_{uv} = H_{uv} + H_{vu}. In our paper we study the behavior of hitting times and commute distances when the number n of vertices in the graph is very large. We prove that as n converges to infinty, hitting times and commute distances converge to expressions that do not take into account the global structure of the graph at all. Namely, the hitting time H_{uv} converges to 1/d_v and the commute time to 1/d_u + 1/d_v where d_u and d_v denote the degrees of vertices u and v. In these cases, the hitting and commute times are misleading in the sense that they do not provide information about the structure of the graph. We focus on two major classes of random graphs: random geometric graphs (k-nearest neighbor graphs, epsilon-graphs, Gaussian similarity graphs) and random graphs with given expected degrees (in particular, Erdos-Renyi graphs with and without planted partitions)", "source": "arxiv/ml"}
{"id": "arxiv:496", "title": "Faster Rates for training Max-Margin Markov Networks", "text": "Structured output prediction is an important machine learning problem both in theory and practice, and the max-margin Markov network (\\mcn) is an effective approach. All state-of-the-art algorithms for optimizing \\mcn\\ objectives take at least $O(1/\\epsilon)$ number of iterations to find an $\\epsilon$ accurate solution. Recent results in structured optimization suggest that faster rates are possible by exploiting the structure of the objective function. Towards this end \\citet{Nesterov05} proposed an excessive gap reduction technique based on Euclidean projections which converges in $O(1/\\sqrt{\\epsilon})$ iterations on strongly convex functions. Unfortunately when applied to \\mcn s, this approach does not admit graphical model factorization which, as in many existing algorithms, is crucial for keeping the cost per iteration tractable. In this paper, we present a new excessive gap reduction technique based on Bregman projections which admits graphical model factorization naturally, and converges in $O(1/\\sqrt{\\epsilon})$ iterations. Compared with existing algorithms, the convergence rate of our method has better dependence on $\\epsilon$ and other parameters of the problem, and can be easily kernelized.", "source": "arxiv/ml"}
{"id": "arxiv:497", "title": "Local Space-Time Smoothing for Version Controlled Documents", "text": "Unlike static documents, version controlled documents are continuously edited by one or more authors. Such collaborative revision process makes traditional modeling and visualization techniques inappropriate. In this paper we propose a new representation based on local space-time smoothing that captures important revision patterns. We demonstrate the applicability of our framework using experiments on synthetic and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:498", "title": "A New Clustering Approach based on Page's Path Similarity for Navigation Patterns Mining", "text": "In recent years, predicting the user's next request in web navigation has received much attention. An information source to be used for dealing with such problem is the left information by the previous web users stored at the web access log on the web servers. Purposed systems for this problem work based on this idea that if a large number of web users request specific pages of a website on a given session, it can be concluded that these pages are satisfying similar information needs, and therefore they are conceptually related. In this study, a new clustering approach is introduced that employs logical path storing of a website pages as another parameter which is regarded as a similarity parameter and conceptual relation between web pages. The results of simulation have shown that the proposed approach is more than others precise in determining the clusters.", "source": "arxiv/ml"}
{"id": "arxiv:499", "title": "Evaluation of E-Learners Behaviour using Different Fuzzy Clustering Models: A Comparative Study", "text": "This paper introduces an evaluation methodologies for the e-learners' behaviour that will be a feedback to the decision makers in e-learning system. Learner's profile plays a crucial role in the evaluation process to improve the e-learning process performance. The work focuses on the clustering of the e-learners based on their behaviour into specific categories that represent the learner's profiles. The learners' classes named as regular, workers, casual, bad, and absent. The work may answer the question of how to return bad students to be regular ones. The work presented the use of different fuzzy clustering techniques as fuzzy c-means and kernelized fuzzy c-means to find the learners' categories and predict their profiles. The paper presents the main phases as data description, preparation, features selection, and the experiments design using different fuzzy clustering models. Analysis of the obtained results and comparison with the real world behavior of those learners proved that there is a match with percentage of 78%. Fuzzy clustering reflects the learners' behavior more than crisp clustering. Comparison between FCM and KFCM proved that the KFCM is much better than FCM in predicting the learners' behaviour.", "source": "arxiv/ml"}
{"id": "arxiv:500", "title": "Hierarchical Web Page Classification Based on a Topic Model and Neighboring Pages Integration", "text": "Most Web page classification models typically apply the bag of words (BOW) model to represent the feature space. The original BOW representation, however, is unable to recognize semantic relationships between terms. One possible solution is to apply the topic model approach based on the Latent Dirichlet Allocation algorithm to cluster the term features into a set of latent topics. Terms assigned into the same topic are semantically related. In this paper, we propose a novel hierarchical classification method based on a topic model and by integrating additional term features from neighboring pages. Our hierarchical classification method consists of two phases: (1) feature representation by using a topic model and integrating neighboring pages, and (2) hierarchical Support Vector Machines (SVM) classification model constructed from a confusion matrix. From the experimental results, the approach of using the proposed hierarchical SVM model by integrating current page with neighboring pages via the topic model yielded the best performance with the accuracy equal to 90.33% and the F1 measure of 90.14%; an improvement of 5.12% and 5.13% over the original SVM model, respectively.", "source": "arxiv/ml"}
{"id": "arxiv:501", "title": "A Survey of Na\\\"ive Bayes Machine Learning approach in Text Document Classification", "text": "Text Document classification aims in associating one or more predefined categories based on the likelihood suggested by the training set of labeled documents. Many machine learning algorithms play a vital role in training the system with predefined categories among which Na\\\"ive Bayes has some intriguing facts that it is simple, easy to implement and draws better accuracy in large datasets in spite of the na\\\"ive dependence. The importance of Na\\\"ive Bayes Machine learning approach has felt hence the study has been taken up for text document classification and the statistical event models available. This survey the various feature selection methods has been discussed and compared along with the metrics related to text document classification.", "source": "arxiv/ml"}
{"id": "arxiv:502", "title": "Supermartingales in Prediction with Expert Advice", "text": "We apply the method of defensive forecasting, based on the use of game-theoretic supermartingales, to prediction with expert advice. In the traditional setting of a countable number of experts and a finite number of outcomes, the Defensive Forecasting Algorithm is very close to the well-known Aggregating Algorithm. Not only the performance guarantees but also the predictions are the same for these two methods of fundamentally different nature. We discuss also a new setting where the experts can give advice conditional on the learner's future decision. Both the algorithms can be adapted to the new setting and give the same performance guarantees as in the traditional setting. Finally, we outline an application of defensive forecasting to a setting with several loss functions.", "source": "arxiv/ml"}
{"id": "arxiv:503", "title": "Structure-Aware Stochastic Control for Transmission Scheduling", "text": "In this paper, we consider the problem of real-time transmission scheduling over time-varying channels. We first formulate the transmission scheduling problem as a Markov decision process (MDP) and systematically unravel the structural properties (e.g. concavity in the state-value function and monotonicity in the optimal scheduling policy) exhibited by the optimal solutions. We then propose an online learning algorithm which preserves these structural properties and achieves -optimal solutions for an arbitrarily small . The advantages of the proposed online method are that: (i) it does not require a priori knowledge of the traffic arrival and channel statistics and (ii) it adaptively approximates the state-value functions using piece-wise linear functions and has low storage and computation complexity. We also extend the proposed low-complexity online learning solution to the prioritized data transmission. The simulation results demonstrate that the proposed method achieves significantly better utility (or delay)-energy trade-offs when comparing to existing state-of-art online optimization methods.", "source": "arxiv/ml"}
{"id": "arxiv:504", "title": "Inductive Logic Programming in Databases: from Datalog to DL+log", "text": "In this paper we address an issue that has been brought to the attention of the database community with the advent of the Semantic Web, i.e. the issue of how ontologies (and semantics conveyed by them) can help solving typical database problems, through a better understanding of KR aspects related to databases. In particular, we investigate this issue from the ILP perspective by considering two database problems, (i) the definition of views and (ii) the definition of constraints, for a database whose schema is represented also by means of an ontology. Both can be reformulated as ILP problems and can benefit from the expressive and deductive power of the KR framework DL+log. We illustrate the application scenarios by means of examples. Keywords: Inductive Logic Programming, Relational Databases, Ontologies, Description Logics, Hybrid Knowledge Representation and Reasoning Systems. Note: To appear in Theory and Practice of Logic Programming (TPLP).", "source": "arxiv/ml"}
{"id": "arxiv:505", "title": "Near-Optimal Evasion of Convex-Inducing Classifiers", "text": "Classifiers are often used to detect miscreant activities. We study how an adversary can efficiently query a classifier to elicit information that allows the adversary to evade detection at near-minimal cost. We generalize results of Lowd and Meek (2005) to convex-inducing classifiers. We present algorithms that construct undetected instances of near-minimal cost using only polynomially many queries in the dimension of the space and without reverse engineering the decision boundary.", "source": "arxiv/ml"}
{"id": "arxiv:506", "title": "A New Heuristic for Feature Selection by Consistent Biclustering", "text": "Given a set of data, biclustering aims at finding simultaneous partitions in biclusters of its samples and of the features which are used for representing the samples. Consistent biclusterings allow to obtain correct classifications of the samples from the known classification of the features, and vice versa, and they are very useful for performing supervised classifications. The problem of finding consistent biclusterings can be seen as a feature selection problem, where the features that are not relevant for classification purposes are removed from the set of data, while the total number of features is maximized in order to preserve information. This feature selection problem can be formulated as a linear fractional 0-1 optimization problem. We propose a reformulation of this problem as a bilevel optimization problem, and we present a heuristic algorithm for an efficient solution of the reformulated problem. Computational experiments show that the presented algorithm is able to find better solutions with respect to the ones obtained by employing previously presented heuristic algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:507", "title": "A Formal Approach to Modeling the Memory of a Living Organism", "text": "We consider a living organism as an observer of the evolution of its environment recording sensory information about the state space X of the environment in real time. Sensory information is sampled and then processed on two levels. On the biological level, the organism serves as an evaluation mechanism of the subjective relevance of the incoming data to the observer: the observer assigns excitation values to events in X it could recognize using its sensory equipment. On the algorithmic level, sensory input is used for updating a database, the memory of the observer whose purpose is to serve as a geometric/combinatorial model of X, whose nodes are weighted by the excitation values produced by the evaluation mechanism. These values serve as a guidance system for deciding how the database should transform as observation data mounts. We define a searching problem for the proposed model and discuss the model's flexibility and its computational efficiency, as well as the possibility of implementing it as a dynamic network of neuron-like units. We show how various easily observable properties of the human memory and thought process can be explained within the framework of this model. These include: reasoning (with efficiency bounds), errors, temporary and permanent loss of information. We are also able to define general learning problems in terms of the new model, such as the language acquisition problem.", "source": "arxiv/ml"}
{"id": "arxiv:508", "title": "Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization", "text": "Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously difficult challenge. In this paper, we introduce the concept of adaptive submodularity, generalizing submodular set functions to adaptive policies. We prove that if a problem satisfies this property, a simple adaptive greedy algorithm is guaranteed to be competitive with the optimal policy. In addition to providing performance guarantees for both stochastic maximization and coverage, adaptive submodularity can be exploited to drastically speed up the greedy algorithm by using lazy evaluations. We illustrate the usefulness of the concept by giving several examples of adaptive submodular objectives arising in diverse applications including sensor placement, viral marketing and active learning. Proving adaptive submodularity for these problems allows us to recover existing results in these applications as special cases, improve approximation guarantees and handle natural generalizations.", "source": "arxiv/ml"}
{"id": "arxiv:509", "title": "Gene Expression Data Knowledge Discovery using Global and Local Clustering", "text": "To understand complex biological systems, the research community has produced huge corpus of gene expression data. A large number of clustering approaches have been proposed for the analysis of gene expression data. However, extracting important biological knowledge is still harder. To address this task, clustering techniques are used. In this paper, hybrid Hierarchical k-Means algorithm is used for clustering and biclustering gene expression data is used. To discover both local and global clustering structure biclustering and clustering algorithms are utilized. A validation technique, Figure of Merit is used to determine the quality of clustering results. Appropriate knowledge is mined from the clusters by embedding a BLAST similarity search program into the clustering and biclustering process. To discover both local and global clustering structure biclustering and clustering algorithms are utilized. To determine the quality of clustering results, a validation technique, Figure of Merit is used. Appropriate knowledge is mined from the clusters by embedding a BLAST similarity search program into the clustering and biclustering process.", "source": "arxiv/ml"}
{"id": "arxiv:510", "title": "Unbeatable Imitation", "text": "We show that for many classes of symmetric two-player games, the simple decision rule \"imitate-the-best\" can hardly be beaten by any other decision rule. We provide necessary and sufficient conditions for imitation to be unbeatable and show that it can only be beaten by much in games that are of the rock-scissors-paper variety. Thus, in many interesting examples, like 2x2 games, Cournot duopoly, price competition, rent seeking, public goods games, common pool resource games, minimum effort coordination games, arms race, search, bargaining, etc., imitation cannot be beaten by much even by a very clever opponent.", "source": "arxiv/ml"}
{"id": "arxiv:511", "title": "Large Margin Boltzmann Machines and Large Margin Sigmoid Belief Networks", "text": "Current statistical models for structured prediction make simplifying assumptions about the underlying output graph structure, such as assuming a low-order Markov chain, because exact inference becomes intractable as the tree-width of the underlying graph increases. Approximate inference algorithms, on the other hand, force one to trade off representational power with computational efficiency. In this paper, we propose two new types of probabilistic graphical models, large margin Boltzmann machines (LMBMs) and large margin sigmoid belief networks (LMSBNs), for structured prediction. LMSBNs in particular allow a very fast inference algorithm for arbitrary graph structures that runs in polynomial time with a high probability. This probability is data-distribution dependent and is maximized in learning. The new approach overcomes the representation-efficiency trade-off in previous models and allows fast structured prediction with complicated graph structures. We present results from applying a fully connected model to multi-label scene classification and demonstrate that the proposed approach can yield significant performance gains over current state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:512", "title": "Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes", "text": "Probabilistic matrix factorization (PMF) is a powerful method for modeling data associated with pairwise relationships, finding use in collaborative filtering, computational biology, and document analysis, among other areas. In many domains, there is additional information that can assist in prediction. For example, when modeling movie ratings, we might know when the rating occurred, where the user lives, or what actors appear in the movie. It is difficult, however, to incorporate this side information into the PMF model. We propose a framework for incorporating side information by coupling together multiple PMF problems via Gaussian process priors. We replace scalar latent features with functions that vary over the space of side information. The GP priors on these functions require them to vary smoothly and share information. We successfully use this new method to predict the scores of professional basketball games, where side information about the venue and date of the game are relevant for the outcome.", "source": "arxiv/ml"}
{"id": "arxiv:513", "title": "Spoken Language Identification Using Hybrid Feature Extraction Methods", "text": "This paper introduces and motivates the use of hybrid robust feature extraction technique for spoken language identification (LID) system. The speech recognizers use a parametric form of a signal to get the most important distinguishable features of speech signal for recognition task. In this paper Mel-frequency cepstral coefficients (MFCC), Perceptual linear prediction coefficients (PLP) along with two hybrid features are used for language Identification. Two hybrid features, Bark Frequency Cepstral Coefficients (BFCC) and Revised Perceptual Linear Prediction Coefficients (RPLP) were obtained from combination of MFCC and PLP. Two different classifiers, Vector Quantization (VQ) with Dynamic Time Warping (DTW) and Gaussian Mixture Model (GMM) were used for classification. The experiment shows better identification rate using hybrid feature extraction techniques compared to conventional feature extraction methods.BFCC has shown better performance than MFCC with both classifiers. RPLP along with GMM has shown best identification performance among all feature extraction techniques.", "source": "arxiv/ml"}
{"id": "arxiv:514", "title": "Wavelet-Based Mel-Frequency Cepstral Coefficients for Speaker Identification using Hidden Markov Models", "text": "To improve the performance of speaker identification systems, an effective and robust method is proposed to extract speech features, capable of operating in noisy environment. Based on the time-frequency multi-resolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. For capturing the characteristic of the signal, the Mel-Frequency Cepstral Coefficients (MFCCs) of the wavelet channels are calculated. Hidden Markov Models (HMMs) were used for the recognition stage as they give better recognition for the speaker's features than Dynamic Time Warping (DTW). Comparison of the proposed approach with the MFCCs conventional feature extraction method shows that the proposed method not only effectively reduces the influence of noise, but also improves recognition. A recognition rate of 99.3% was obtained using the proposed feature extraction technique compared to 98.7% using the MFCCs. When the test patterns were corrupted by additive white Gaussian noise with 20 dB S/N ratio, the recognition rate was 97.3% using the proposed method compared to 93.3% using the MFCCs.", "source": "arxiv/ml"}
{"id": "arxiv:515", "title": "Etiqueter un corpus oral par apprentissage automatique \\`a l'aide de connaissances linguistiques", "text": "Thanks to the Eslo1 (\"Enqu\\^ete sociolinguistique d'Orl\\'eans\", i.e. \"Sociolinguistic Inquiery of Orl\\'eans\") campain, a large oral corpus has been gathered and transcribed in a textual format. The purpose of the work presented here is to associate a morpho-syntactic label to each unit of this corpus. To this aim, we have first studied the specificities of the necessary labels, and their various possible levels of description. This study has led to a new original hierarchical structuration of labels. Then, considering that our new set of labels was different from the one used in every available software, and that these softwares usually do not fit for oral data, we have built a new labeling tool by a Machine Learning approach, from data labeled by Cordial and corrected by hand. We have applied linear CRF (Conditional Random Fields) trying to take the best possible advantage of the linguistic knowledge that was used to define the set of labels. We obtain an accuracy between 85 and 90%, depending of the parameters used.", "source": "arxiv/ml"}
{"id": "arxiv:516", "title": "Offline Signature Identification by Fusion of Multiple Classifiers using Statistical Learning Theory", "text": "This paper uses Support Vector Machines (SVM) to fuse multiple classifiers for an offline signature system. From the signature images, global and local features are extracted and the signatures are verified with the help of Gaussian empirical rule, Euclidean and Mahalanobis distance based classifiers. SVM is used to fuse matching scores of these matchers. Finally, recognition of query signatures is done by comparing it with all signatures of the database. The proposed system is tested on a signature database contains 5400 offline signatures of 600 individuals and the results are found to be promising.", "source": "arxiv/ml"}
{"id": "arxiv:517", "title": "Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms", "text": "Contextual bandit algorithms have become popular for online recommendation systems such as Digg, Yahoo! Buzz, and news recommendation in general. \\emph{Offline} evaluation of the effectiveness of new algorithms in these applications is critical for protecting online user experiences but very challenging due to their \"partial-label\" nature. Common practice is to create a simulator which simulates the online environment for the problem at hand and then run an algorithm against this simulator. However, creating simulator itself is often difficult and modeling bias is usually unavoidably introduced. In this paper, we introduce a \\emph{replay} methodology for contextual bandit algorithm evaluation. Different from simulator-based approaches, our method is completely data-driven and very easy to adapt to different applications. More importantly, our method can provide provably unbiased evaluations. Our empirical results on a large-scale news article recommendation dataset collected from Yahoo! Front Page conform well with our theoretical results. Furthermore, comparisons between our offline replay and online bucket evaluation of several contextual bandit algorithms show accuracy and effectiveness of our offline evaluation method.", "source": "arxiv/ml"}
{"id": "arxiv:518", "title": "Facial Expression Representation and Recognition Using 2DHLDA, Gabor Wavelets, and Ensemble Learning", "text": "In this paper, a novel method for representation and recognition of the facial expressions in two-dimensional image sequences is presented. We apply a variation of two-dimensional heteroscedastic linear discriminant analysis (2DHLDA) algorithm, as an efficient dimensionality reduction technique, to Gabor representation of the input sequence. 2DHLDA is an extension of the two-dimensional linear discriminant analysis (2DLDA) approach and it removes the equal within-class covariance. By applying 2DHLDA in two directions, we eliminate the correlations between both image columns and image rows. Then, we perform a one-dimensional LDA on the new features. This combined method can alleviate the small sample size problem and instability encountered by HLDA. Also, employing both geometric and appearance features and using an ensemble learning scheme based on data fusion, we create a classifier which can efficiently classify the facial expressions. The proposed method is robust to illumination changes and it can properly represent temporal information as well as subtle changes in facial muscles. We provide experiments on Cohn-Kanade database that show the superiority of the proposed method. KEYWORDS: two-dimensional heteroscedastic linear discriminant analysis (2DHLDA), subspace learning, facial expression analysis, Gabor wavelets, ensemble learning.", "source": "arxiv/ml"}
{"id": "arxiv:519", "title": "Exploratory Analysis of Functional Data via Clustering and Optimal Segmentation", "text": "We propose in this paper an exploratory analysis algorithm for functional data. The method partitions a set of functions into $K$ clusters and represents each cluster by a simple prototype (e.g., piecewise constant). The total number of segments in the prototypes, $P$, is chosen by the user and optimally distributed among the clusters via two dynamic programming algorithms. The practical relevance of the method is shown on two real world datasets.", "source": "arxiv/ml"}
{"id": "arxiv:520", "title": "Recognizing Combinations of Facial Action Units with Different Intensity Using a Mixture of Hidden Markov Models and Neural Network", "text": "Facial Action Coding System consists of 44 action units (AUs) and more than 7000 combinations. Hidden Markov models (HMMs) classifier has been used successfully to recognize facial action units (AUs) and expressions due to its ability to deal with AU dynamics. However, a separate HMM is necessary for each single AU and each AU combination. Since combinations of AU numbering in thousands, a more efficient method will be needed. In this paper an accurate real-time sequence-based system for representation and recognition of facial AUs is presented. Our system has the following characteristics: 1) employing a mixture of HMMs and neural network, we develop a novel accurate classifier, which can deal with AU dynamics, recognize subtle changes, and it is also robust to intensity variations, 2) although we use an HMM for each single AU only, by employing a neural network we can recognize each single and combination AU, and 3) using both geometric and appearance-based features, and applying efficient dimension reduction techniques, our system is robust to illumination changes and it can represent the temporal information involved in formation of the facial expressions. Extensive experiments on Cohn-Kanade database show the superiority of the proposed method, in comparison with other classifiers. Keywords: classifier design and evaluation, data fusion, facial action units (AUs), hidden Markov models (HMMs), neural network (NN).", "source": "arxiv/ml"}
{"id": "arxiv:521", "title": "Multilinear Biased Discriminant Analysis: A Novel Method for Facial Action Unit Representation", "text": "In this paper a novel efficient method for representation of facial action units by encoding an image sequence as a fourth-order tensor is presented. The multilinear tensor-based extension of the biased discriminant analysis (BDA) algorithm, called multilinear biased discriminant analysis (MBDA), is first proposed. Then, we apply the MBDA and two-dimensional BDA (2DBDA) algorithms, as the dimensionality reduction techniques, to Gabor representations and the geometric features of the input image sequence respectively. The proposed scheme can deal with the asymmetry between positive and negative samples as well as curse of dimensionality dilemma. Extensive experiments on Cohn-Kanade database show the superiority of the proposed method for representation of the subtle changes and the temporal information involved in formation of the facial expressions. As an accurate tool, this representation can be applied to many areas such as recognition of spontaneous and deliberate facial expressions, multi modal/media human computer interaction and lie detection efforts.", "source": "arxiv/ml"}
{"id": "arxiv:522", "title": "Using Rough Set and Support Vector Machine for Network Intrusion Detection", "text": "The main function of IDS (Intrusion Detection System) is to protect the system, analyze and predict the behaviors of users. Then these behaviors will be considered an attack or a normal behavior. Though IDS has been developed for many years, the large number of return alert messages makes managers maintain system inefficiently. In this paper, we use RST (Rough Set Theory) and SVM (Support Vector Machine) to detect intrusions. First, RST is used to preprocess the data and reduce the dimensions. Next, the features were selected by RST will be sent to SVM model to learn and test respectively. The method is effective to decrease the space density of data. The experiments will compare the results with different methods and show RST and SVM schema could improve the false positive rate and accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:523", "title": "Extended Two-Dimensional PCA for Efficient Face Representation and Recognition", "text": "In this paper a novel method called Extended Two-Dimensional PCA (E2DPCA) is proposed which is an extension to the original 2DPCA. We state that the covariance matrix of 2DPCA is equivalent to the average of the main diagonal of the covariance matrix of PCA. This implies that 2DPCA eliminates some covariance information that can be useful for recognition. E2DPCA instead of just using the main diagonal considers a radius of r diagonals around it and expands the averaging so as to include the covariance information within those diagonals. The parameter r unifies PCA and 2DPCA. r = 1 produces the covariance of 2DPCA, r = n that of PCA. Hence, by controlling r it is possible to control the trade-offs between recognition accuracy and energy compression (fewer coefficients), and between training and recognition complexity. Experiments on ORL face database show improvement in both recognition accuracy and recognition time over the original 2DPCA.", "source": "arxiv/ml"}
{"id": "arxiv:524", "title": "Message-Passing Inference on a Factor Graph for Collaborative Filtering", "text": "This paper introduces a novel message-passing (MP) framework for the collaborative filtering (CF) problem associated with recommender systems. We model the movie-rating prediction problem popularized by the Netflix Prize, using a probabilistic factor graph model and study the model by deriving generalization error bounds in terms of the training error. Based on the model, we develop a new MP algorithm, termed IMP, for learning the model. To show superiority of the IMP algorithm, we compare it with the closely related expectation-maximization (EM) based algorithm and a number of other matrix completion algorithms. Our simulation results on Netflix data show that, while the methods perform similarly with large amounts of data, the IMP algorithm is superior for small amounts of data. This improves the cold-start problem of the CF systems in practice. Another advantage of the IMP algorithm is that it can be analyzed using the technique of density evolution (DE) that was originally developed for MP decoding of error-correcting codes.", "source": "arxiv/ml"}
{"id": "arxiv:525", "title": "On Tsallis Entropy Bias and Generalized Maximum Entropy Models", "text": "In density estimation task, maximum entropy model (Maxent) can effectively use reliable prior information via certain constraints, i.e., linear constraints without empirical parameters. However, reliable prior information is often insufficient, and the selection of uncertain constraints becomes necessary but poses considerable implementation complexity. Improper setting of uncertain constraints can result in overfitting or underfitting. To solve this problem, a generalization of Maxent, under Tsallis entropy framework, is proposed. The proposed method introduces a convex quadratic constraint for the correction of (expected) Tsallis entropy bias (TEB). Specifically, we demonstrate that the expected Tsallis entropy of sampling distributions is smaller than the Tsallis entropy of the underlying real distribution. This expected entropy reduction is exactly the (expected) TEB, which can be expressed by a closed-form formula and act as a consistent and unbiased correction. TEB indicates that the entropy of a specific sampling distribution should be increased accordingly. This entails a quantitative re-interpretation of the Maxent principle. By compensating TEB and meanwhile forcing the resulting distribution to be close to the sampling distribution, our generalized TEBC Maxent can be expected to alleviate the overfitting and underfitting. We also present a connection between TEB and Lidstone estimator. As a result, TEB-Lidstone estimator is developed by analytically identifying the rate of probability correction in Lidstone. Extensive empirical evaluation shows promising performance of both TEBC Maxent and TEB-Lidstone in comparison with various state-of-the-art density estimation methods.", "source": "arxiv/ml"}
{"id": "arxiv:526", "title": "Ontology-supported processing of clinical text using medical knowledge integration for multi-label classification of diagnosis coding", "text": "This paper discusses the knowledge integration of clinical information extracted from distributed medical ontology in order to ameliorate a machine learning-based multi-label coding assignment system. The proposed approach is implemented using a decision tree based cascade hierarchical technique on the university hospital data for patients with Coronary Heart Disease (CHD). The preliminary results obtained show a satisfactory finding.", "source": "arxiv/ml"}
{"id": "arxiv:527", "title": "An Analytical Study on Behavior of Clusters Using K Means, EM and K* Means Algorithm", "text": "Clustering is an unsupervised learning method that constitutes a cornerstone of an intelligent data analysis process. It is used for the exploration of inter-relationships among a collection of patterns, by organizing them into homogeneous clusters. Clustering has been dynamically applied to a variety of tasks in the field of Information Retrieval (IR). Clustering has become one of the most active area of research and the development. Clustering attempts to discover the set of consequential groups where those within each group are more closely related to one another than the others assigned to different groups. The resultant clusters can provide a structure for organizing large bodies of text for efficient browsing and searching. There exists a wide variety of clustering algorithms that has been intensively studied in the clustering problem. Among the algorithms that remain the most common and effectual, the iterative optimization clustering algorithms have been demonstrated reasonable performance for clustering, e.g. the Expectation Maximization (EM) algorithm and its variants, and the well known k-means algorithm. This paper presents an analysis on how partition method clustering techniques - EM, K -means and K* Means algorithm work on heartspect dataset with below mentioned features - Purity, Entropy, CPU time, Cluster wise analysis, Mean value analysis and inter cluster distance. Thus the paper finally provides the experimental results of datasets for five clusters to strengthen the results that the quality of the behavior in clusters in EM algorithm is far better than k-means algorithm and k*means algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:528", "title": "State-Space Dynamics Distance for Clustering Sequential Data", "text": "This paper proposes a novel similarity measure for clustering sequential data. We first construct a common state-space by training a single probabilistic model with all the sequences in order to get a unified representation for the dataset. Then, distances are obtained attending to the transition matrices induced by each sequence in that state-space. This approach solves some of the usual overfitting and scalability issues of the existing semi-parametric techniques, that rely on training a model for each sequence. Empirical studies on both synthetic and real-world datasets illustrate the advantages of the proposed similarity measure for clustering sequences.", "source": "arxiv/ml"}
{"id": "arxiv:529", "title": "An optimized recursive learning algorithm for three-layer feedforward neural networks for mimo nonlinear system identifications", "text": "Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given. Although this approach is proposed for three-layer, feed-forward neural networks, it could be extended to multiple layer feed-forward neural networks. The effectiveness of the proposed algorithms applied to the identification of behavior of a two-input and two-output non-linear dynamic system is demonstrated by simulation experiments.", "source": "arxiv/ml"}
{"id": "arxiv:530", "title": "Dynamic Policy Programming", "text": "In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation error. The bounds are expressed in terms of the l\\infty-norm of the average accumulated error as opposed to the l\\infty-norm of the error in the case of the standard approximate value iteration (AVI) and the approximate policy iteration (API). This suggests that DPP can achieve a better performance than AVI and API since it averages out the simulation noise caused by Monte-Carlo sampling throughout the learning process. We examine this theoretical results numerically by com- paring the performance of the approximate variants of DPP with existing reinforcement learning (RL) methods on different problem domains. Our results show that, in all cases, DPP-based algorithms outperform other RL methods by a wide margin.", "source": "arxiv/ml"}
{"id": "arxiv:531", "title": "Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory", "text": "In regular statistical models, the leave-one-out cross-validation is asymptotically equivalent to the Akaike information criterion. However, since many learning machines are singular statistical models, the asymptotic behavior of the cross-validation remains unknown. In previous studies, we established the singular learning theory and proposed a widely applicable information criterion, the expectation value of which is asymptotically equal to the average Bayes generalization loss. In the present paper, we theoretically compare the Bayes cross-validation loss and the widely applicable information criterion and prove two theorems. First, the Bayes cross-validation loss is asymptotically equivalent to the widely applicable information criterion as a random variable. Therefore, model selection and hyperparameter optimization using these two values are asymptotically equivalent. Second, the sum of the Bayes generalization error and the Bayes cross-validation error is asymptotically equal to $2\\lambda/n$, where $\\lambda$ is the real log canonical threshold and $n$ is the number of training samples. Therefore the relation between the cross-validation error and the generalization error is determined by the algebraic geometrical structure of a learning machine. We also clarify that the deviance information criteria are different from the Bayes cross-validation and the widely applicable information criterion.", "source": "arxiv/ml"}
{"id": "arxiv:532", "title": "Generation and Interpretation of Temporal Decision Rules", "text": "We present a solution to the problem of understanding a system that produces a sequence of temporally ordered observations. Our solution is based on generating and interpreting a set of temporal decision rules. A temporal decision rule is a decision rule that can be used to predict or retrodict the value of a decision attribute, using condition attributes that are observed at times other than the decision attribute's time of observation. A rule set, consisting of a set of temporal decision rules with the same decision attribute, can be interpreted by our Temporal Investigation Method for Enregistered Record Sequences (TIMERS) to signify an instantaneous, an acausal or a possibly causal relationship between the condition attributes and the decision attribute. We show the effectiveness of our method, by describing a number of experiments with both synthetic and real temporal data.", "source": "arxiv/ml"}
{"id": "arxiv:533", "title": "From open quantum systems to open quantum maps", "text": "For a class of quantized open chaotic systems satisfying a natural dynamical assumption, we show that the study of the resolvent, and hence of scattering and resonances, can be reduced to the study of a family of open quantum maps, that is of finite dimensional operators obtained by quantizing the Poincar\\'e map associated with the flow near the set of trapped trajectories.", "source": "arxiv/ml"}
{"id": "arxiv:534", "title": "Bregman Distance to L1 Regularized Logistic Regression", "text": "In this work we investigate the relationship between Bregman distances and regularized Logistic Regression model. We present a detailed study of Bregman Distance minimization, a family of generalized entropy measures associated with convex functions. We convert the L1-regularized logistic regression into this more general framework and propose a primal-dual method based algorithm for learning the parameters. We pose L1-regularized logistic regression into Bregman distance minimization and then apply non-linear constrained optimization techniques to estimate the parameters of the logistic model.", "source": "arxiv/ml"}
{"id": "arxiv:535", "title": "Settling the Polynomial Learnability of Mixtures of Gaussians", "text": "Given data drawn from a mixture of multivariate Gaussians, a basic problem is to accurately estimate the mixture parameters. We give an algorithm for this problem that has a running time, and data requirement polynomial in the dimension and the inverse of the desired accuracy, with provably minimal assumptions on the Gaussians. As simple consequences of our learning algorithm, we can perform near-optimal clustering of the sample points and density estimation for mixtures of k Gaussians, efficiently. The building blocks of our algorithm are based on the work Kalai et al. [STOC 2010] that gives an efficient algorithm for learning mixtures of two Gaussians by considering a series of projections down to one dimension, and applying the method of moments to each univariate projection. A major technical hurdle in Kalai et al. is showing that one can efficiently learn univariate mixtures of two Gaussians. In contrast, because pathological scenarios can arise when considering univariate projections of mixtures of more than two Gaussians, the bulk of the work in this paper concerns how to leverage an algorithm for learning univariate mixtures (of many Gaussians) to yield an efficient algorithm for learning in high dimensions. Our algorithm employs hierarchical clustering and rescaling, together with delicate methods for backtracking and recovering from failures that can occur in our univariate algorithm. Finally, while the running time and data requirements of our algorithm depend exponentially on the number of Gaussians in the mixture, we prove that such a dependence is necessary.", "source": "arxiv/ml"}
{"id": "arxiv:536", "title": "Efficient Learning with Partially Observed Attributes", "text": "We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the case, for instance, in medical research, where each patient participating in the experiment is only willing to go through a small number of tests. Our analysis bounds the number of additional examples sufficient to compensate for the lack of full information on each training example. We demonstrate the efficiency of our algorithms by showing that when running on digit recognition data, they obtain a high prediction accuracy even when the learner gets to see only four pixels of each image.", "source": "arxiv/ml"}
{"id": "arxiv:537", "title": "Evolutionary Inference for Function-valued Traits: Gaussian Process Regression on Phylogenies", "text": "Biological data objects often have both of the following features: (i) they are functions rather than single numbers or vectors, and (ii) they are correlated due to phylogenetic relationships. In this paper we give a flexible statistical model for such data, by combining assumptions from phylogenetics with Gaussian processes. We describe its use as a nonparametric Bayesian prior distribution, both for prediction (placing posterior distributions on ancestral functions) and model selection (comparing rates of evolution across a phylogeny, or identifying the most likely phylogenies consistent with the observed data). Our work is integrative, extending the popular phylogenetic Brownian Motion and Ornstein-Uhlenbeck models to functional data and Bayesian inference, and extending Gaussian Process regression to phylogenies. We provide a brief illustration of the application of our method.", "source": "arxiv/ml"}
{"id": "arxiv:538", "title": "Polynomial Learning of Distribution Families", "text": "The question of polynomial learnability of probability distributions, particularly Gaussian mixture distributions, has recently received significant attention in theoretical computer science and machine learning. However, despite major progress, the general question of polynomial learnability of Gaussian mixture distributions still remained open. The current work resolves the question of polynomial learnability for Gaussian mixtures in high dimension with an arbitrary fixed number of components. The result on learning Gaussian mixtures relies on an analysis of distributions belonging to what we call \"polynomial families\" in low dimension. These families are characterized by their moments being polynomial in parameters and include almost all common probability distributions as well as their mixtures and products. Using tools from real algebraic geometry, we show that parameters of any distribution belonging to such a family can be learned in polynomial time and using a polynomial number of sample points. The result on learning polynomial families is quite general and is of independent interest. To estimate parameters of a Gaussian mixture distribution in high dimensions, we provide a deterministic algorithm for dimensionality reduction. This allows us to reduce learning a high-dimensional mixture to a polynomial number of parameter estimations in low dimension. Combining this reduction with the results on polynomial families yields our result on learning arbitrary Gaussian mixtures in high dimensions.", "source": "arxiv/ml"}
{"id": "arxiv:539", "title": "Clustering processes", "text": "The problem of clustering is considered, for the case when each data point is a sample generated by a stationary ergodic process. We propose a very natural asymptotic notion of consistency, and show that simple consistent algorithms exist, under most general non-parametric assumptions. The notion of consistency is as follows: two samples should be put into the same cluster if and only if they were generated by the same distribution. With this notion of consistency, clustering generalizes such classical statistical problems as homogeneity testing and process classification. We show that, for the case of a known number of clusters, consistency can be achieved under the only assumption that the joint distribution of the data is stationary ergodic (no parametric or Markovian assumptions, no assumptions of independence, neither between nor within the samples). If the number of clusters is unknown, consistency can be achieved under appropriate assumptions on the mixing rates of the processes. (again, no parametric or independence assumptions). In both cases we give examples of simple (at most quadratic in each argument) algorithms which are consistent.", "source": "arxiv/ml"}
{"id": "arxiv:540", "title": "Optimism in Reinforcement Learning and Kullback-Leibler Divergence", "text": "We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint of consistency with the estimated model tran- sition probabilities. The UCRL2 algorithm by Auer, Jaksch and Ortner (2009), which follows this strategy, has recently been shown to guarantee near-optimal regret bounds. In this paper, we strongly argue in favor of using the Kullback-Leibler (KL) divergence for this purpose. By studying the linear maximization problem under KL constraints, we provide an ef- ficient algorithm, termed KL-UCRL, for solving KL-optimistic extended value iteration. Using recent deviation bounds on the KL divergence, we prove that KL-UCRL provides the same guarantees as UCRL2 in terms of regret. However, numerical experiments on classical benchmarks show a significantly improved behavior, particularly when the MDP has reduced connectivity. To support this observation, we provide elements of com- parison between the two algorithms based on geometric considerations.", "source": "arxiv/ml"}
{"id": "arxiv:541", "title": "Designing neural networks that process mean values of random variables", "text": "We introduce a class of neural networks derived from probabilistic models in the form of Bayesian networks. By imposing additional assumptions about the nature of the probabilistic models represented in the networks, we derive neural networks with standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the random variables, that can pool multiple sources of evidence, and that deal cleanly and consistently with inconsistent or contradictory evidence. The presented neural networks capture many properties of Bayesian networks, providing distributed versions of probabilistic models.", "source": "arxiv/ml"}
{"id": "arxiv:542", "title": "Learning from Multiple Outlooks", "text": "We propose a novel problem formulation of learning a single task when the data are provided in different feature spaces. Each such space is called an outlook, and is assumed to contain both labeled and unlabeled data. The objective is to take advantage of the data from all the outlooks to better classify each of the outlooks. We devise an algorithm that computes optimal affine mappings from different outlooks to a target outlook by matching moments of the empirical distributions. We further derive a probabilistic interpretation of the resulting algorithm and a sample complexity bound indicating how many samples are needed to adequately find the mapping. We report the results of extensive experiments on activity recognition tasks that show the value of the proposed approach in boosting performance.", "source": "arxiv/ml"}
{"id": "arxiv:543", "title": "A Geometric View of Conjugate Priors", "text": "In Bayesian machine learning, conjugate priors are popular, mostly due to mathematical convenience. In this paper, we show that there are deeper reasons for choosing a conjugate prior. Specifically, we formulate the conjugate prior in the form of Bregman divergence and show that it is the inherent geometry of conjugate priors that makes them appropriate and intuitive. This geometric interpretation allows one to view the hyperparameters of conjugate priors as the {\\it effective} sample points, thus providing additional intuition. We use this geometric understanding of conjugate priors to derive the hyperparameters and expression of the prior used to couple the generative and discriminative components of a hybrid model for semi-supervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:544", "title": "Large Margin Multiclass Gaussian Classification with Differential Privacy", "text": "As increasing amounts of sensitive personal information is aggregated into data repositories, it has become important to develop mechanisms for processing the data without revealing information about individual data instances. The differential privacy model provides a framework for the development and theoretical analysis of such mechanisms. In this paper, we propose an algorithm for learning a discriminatively trained multi-class Gaussian classifier that satisfies differential privacy using a large margin loss function with a perturbed regularization term. We present a theoretical upper bound on the excess risk of the classifier introduced by the perturbation.", "source": "arxiv/ml"}
{"id": "arxiv:545", "title": "Distributive Stochastic Learning for Delay-Optimal OFDMA Power and Subband Allocation", "text": "In this paper, we consider the distributive queue-aware power and subband allocation design for a delay-optimal OFDMA uplink system with one base station, $K$ users and $N_F$ independent subbands. Each mobile has an uplink queue with heterogeneous packet arrivals and delay requirements. We model the problem as an infinite horizon average reward Markov Decision Problem (MDP) where the control actions are functions of the instantaneous Channel State Information (CSI) as well as the joint Queue State Information (QSI). To address the distributive requirement and the issue of exponential memory requirement and computational complexity, we approximate the subband allocation Q-factor by the sum of the per-user subband allocation Q-factor and derive a distributive online stochastic learning algorithm to estimate the per-user Q-factor and the Lagrange multipliers (LM) simultaneously and determine the control actions using an auction mechanism. We show that under the proposed auction mechanism, the distributive online learning converges almost surely (with probability 1). For illustration, we apply the proposed distributive stochastic learning framework to an application example with exponential packet size distribution. We show that the delay-optimal power control has the {\\em multi-level water-filling} structure where the CSI determines the instantaneous power allocation and the QSI determines the water-level. The proposed algorithm has linear signaling overhead and computational complexity $\\mathcal O(KN)$, which is desirable from an implementation perspective.", "source": "arxiv/ml"}
{"id": "arxiv:546", "title": "Adaptive Bases for Reinforcement Learning", "text": "We consider the problem of reinforcement learning using function approximation, where the approximating basis can change dynamically while interacting with the environment. A motivation for such an approach is maximizing the value function fitness to the problem faced. Three errors are considered: approximation square error, Bellman residual, and projected Bellman residual. Algorithms under the actor-critic framework are presented, and shown to converge. The advantage of such an adaptive basis is demonstrated in simulations.", "source": "arxiv/ml"}
{"id": "arxiv:547", "title": "Generative and Latent Mean Map Kernels", "text": "We introduce two kernels that extend the mean map, which embeds probability measures in Hilbert spaces. The generative mean map kernel (GMMK) is a smooth similarity measure between probabilistic models. The latent mean map kernel (LMMK) generalizes the non-iid formulation of Hilbert space embeddings of empirical distributions in order to incorporate latent variable models. When comparing certain classes of distributions, the GMMK exhibits beneficial regularization and generalization properties not shown for previous generative kernels. We present experiments comparing support vector machine performance using the GMMK and LMMK between hidden Markov models to the performance of other methods on discrete and continuous observation sequence data. The results suggest that, in many cases, the GMMK has generalization error competitive with or better than other methods.", "source": "arxiv/ml"}
{"id": "arxiv:548", "title": "Statistical Learning in Automated Troubleshooting: Application to LTE Interference Mitigation", "text": "This paper presents a method for automated healing as part of off-line automated troubleshooting. The method combines statistical learning with constraint optimization. The automated healing aims at locally optimizing radio resource management (RRM) or system parameters of cells with poor performance in an iterative manner. The statistical learning processes the data using Logistic Regression (LR) to extract closed form (functional) relations between Key Performance Indicators (KPIs) and Radio Resource Management (RRM) parameters. These functional relations are then processed by an optimization engine which proposes new parameter values. The advantage of the proposed formulation is the small number of iterations required by the automated healing method to converge, making it suitable for off-line implementation. The proposed method is applied to heal an Inter-Cell Interference Coordination (ICIC) process in a 3G Long Term Evolution (LTE) network which is based on soft-frequency reuse scheme. Numerical simulations illustrate the benefits of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:549", "title": "Machine Learning for Galaxy Morphology Classification", "text": "In this work, decision tree learning algorithms and fuzzy inferencing systems are applied for galaxy morphology classification. In particular, the CART, the C4.5, the Random Forest and fuzzy logic algorithms are studied and reliable classifiers are developed to distinguish between spiral galaxies, elliptical galaxies or star/unknown galactic objects. Morphology information for the training and testing datasets is obtained from the Galaxy Zoo project while the corresponding photometric and spectra parameters are downloaded from the SDSS DR7 catalogue.", "source": "arxiv/ml"}
{"id": "arxiv:550", "title": "A Unifying View of Multiple Kernel Learning", "text": "Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying general optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion's dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.", "source": "arxiv/ml"}
{"id": "arxiv:551", "title": "Feature Selection with Conjunctions of Decision Stumps and Learning from Microarray Data", "text": "One of the objectives of designing feature selection learning algorithms is to obtain classifiers that depend on a small number of attributes and have verifiable future performance guarantees. There are few, if any, approaches that successfully address the two goals simultaneously. Performance guarantees become crucial for tasks such as microarray data analysis due to very small sample sizes resulting in limited empirical evaluation. To the best of our knowledge, such algorithms that give theoretical bounds on the future performance have not been proposed so far in the context of the classification of gene expression data. In this work, we investigate the premise of learning a conjunction (or disjunction) of decision stumps in Occam's Razor, Sample Compression, and PAC-Bayes learning settings for identifying a small subset of attributes that can be used to perform reliable classification tasks. We apply the proposed approaches for gene identification from DNA microarray data and compare our results to those of well known successful approaches proposed for the task. We show that our algorithm not only finds hypotheses with much smaller number of genes while giving competitive classification accuracy but also have tight risk guarantees on future performance unlike other approaches. The proposed approaches are general and extensible in terms of both designing novel algorithms and application to other domains.", "source": "arxiv/ml"}
{"id": "arxiv:552", "title": "Active Learning for Hidden Attributes in Networks", "text": "In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing which vertex to query in order to learn as much as possible about the attributes of the other vertices. We assume the network is generated by a stochastic block model, but we make no assumptions about its assortativity or disassortativity. We choose which vertex to query using two methods: 1) maximizing the mutual information between its attributes and those of the others (a well-known approach in active learning) and 2) maximizing the average agreement between two independent samples of the conditional Gibbs distribution. Experimental results show that both these methods do much better than simple heuristics. They also consistently identify certain vertices as important by querying them early on.", "source": "arxiv/ml"}
{"id": "arxiv:554", "title": "The Complex Gaussian Kernel LMS algorithm", "text": "Although the real reproducing kernels are used in an increasing number of machine learning problems, complex kernels have not, yet, been used, in spite of their potential interest in applications such as communications. In this work, we focus our attention on the complex gaussian kernel and its possible application in the complex Kernel LMS algorithm. In order to derive the gradients needed to develop the complex kernel LMS (CKLMS), we employ the powerful tool of Wirtinger's Calculus, which has recently attracted much attention in the signal processing community. Writinger's calculus simplifies computations and offers an elegant tool for treating complex signals. To this end, the notion of Writinger's calculus is extended to include complex RKHSs. Experiments verify that the CKLMS offers significant performance improvements over the traditional complex LMS or Widely Linear complex LMS (WL-LMS) algorithms, when dealing with nonlinearities.", "source": "arxiv/ml"}
{"id": "arxiv:555", "title": "Extension of Wirtinger Calculus in RKH Spaces and the Complex Kernel LMS", "text": "Over the last decade, kernel methods for nonlinear processing have successfully been used in the machine learning community. However, so far, the emphasis has been on batch techniques. It is only recently, that online adaptive techniques have been considered in the context of signal processing tasks. To the best of our knowledge, no kernel-based strategy has been developed, so far, that is able to deal with complex valued signals. In this paper, we take advantage of a technique called complexification of real RKHSs to attack this problem. In order to derive gradients and subgradients of operators that need to be defined on the associated complex RKHSs, we employ the powerful tool ofWirtinger's Calculus, which has recently attracted much attention in the signal processing community. Writinger's calculus simplifies computations and offers an elegant tool for treating complex signals. To this end, in this paper, the notion of Writinger's calculus is extended, for the first time, to include complex RKHSs and use it to derive the Complex Kernel Least-Mean-Square (CKLMS) algorithm. Experiments verify that the CKLMS can be used to derive nonlinear stable algorithms, which offer significant performance improvements over the traditional complex LMS orWidely Linear complex LMS (WL-LMS) algorithms, when dealing with nonlinearities.", "source": "arxiv/ml"}
{"id": "arxiv:556", "title": "Estimating small moments of data stream in nearly optimal space-time", "text": "For each $p \\in (0,2]$, we present a randomized algorithm that returns an $\\epsilon$-approximation of the $p$th frequency moment of a data stream $F_p = \\sum_{i = 1}^n \\abs{f_i}^p$. The algorithm requires space $O(\\epsilon^{-2} \\log (mM)(\\log n))$ and processes each stream update using time $O((\\log n) (\\log \\epsilon^{-1}))$. It is nearly optimal in terms of space (lower bound $O(\\epsilon^{-2} \\log (mM))$ as well as time and is the first algorithm with these properties. The technique separates heavy hitters from the remaining items in the stream using an appropriate threshold and estimates the contribution of the heavy hitters and the light elements to $F_p$ separately. A key component is the design of an unbiased estimator for $\\abs{f_i}^p$ whose data structure has low update time and low variance.", "source": "arxiv/ml"}
{"id": "arxiv:557", "title": "Improving Semi-Supervised Support Vector Machines Through Unlabeled Instances Selection", "text": "Semi-supervised support vector machines (S3VMs) are a kind of popular approaches which try to improve learning performance by exploiting unlabeled data. Though S3VMs have been found helpful in many situations, they may degenerate performance and the resultant generalization ability may be even worse than using the labeled data only. In this paper, we try to reduce the chance of performance degeneration of S3VMs. Our basic idea is that, rather than exploiting all unlabeled data, the unlabeled instances should be selected such that only the ones which are very likely to be helpful are exploited, while some highly risky unlabeled instances are avoided. We propose the S3VM-\\emph{us} method by using hierarchical clustering to select the unlabeled instances. Experiments on a broad range of data sets over eighty-eight different settings show that the chance of performance degeneration of S3VM-\\emph{us} is much smaller than that of existing S3VMs.", "source": "arxiv/ml"}
{"id": "arxiv:558", "title": "Prediction with Expert Advice under Discounted Loss", "text": "We study prediction with expert advice in the setting where the losses are accumulated with some discounting---the impact of old losses may gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression to this case, propose a suitable new variant of exponential weights algorithm, and prove respective loss bounds.", "source": "arxiv/ml"}
{"id": "arxiv:559", "title": "On the Finite Time Convergence of Cyclic Coordinate Descent Methods", "text": "Cyclic coordinate descent is a classic optimization method that has witnessed a resurgence of interest in machine learning. Reasons for this include its simplicity, speed and stability, as well as its competitive performance on $\\ell_1$ regularized smooth optimization problems. Surprisingly, very little is known about its finite time convergence behavior on these problems. Most existing results either just prove convergence or provide asymptotic rates. We fill this gap in the literature by proving $O(1/k)$ convergence rates (where $k$ is the iteration counter) for two variants of cyclic coordinate descent under an isotonicity assumption. Our analysis proceeds by comparing the objective values attained by the two variants with each other, as well as with the gradient descent algorithm. We show that the iterates generated by the cyclic coordinate descent methods remain better than those of gradient descent uniformly over time.", "source": "arxiv/ml"}
{"id": "arxiv:560", "title": "Detecting Blackholes and Volcanoes in Directed Networks", "text": "In this paper, we formulate a novel problem for finding blackhole and volcano patterns in a large directed graph. Specifically, a blackhole pattern is a group which is made of a set of nodes in a way such that there are only inlinks to this group from the rest nodes in the graph. In contrast, a volcano pattern is a group which only has outlinks to the rest nodes in the graph. Both patterns can be observed in real world. For instance, in a trading network, a blackhole pattern may represent a group of traders who are manipulating the market. In the paper, we first prove that the blackhole mining problem is a dual problem of finding volcanoes. Therefore, we focus on finding the blackhole patterns. Along this line, we design two pruning schemes to guide the blackhole finding process. In the first pruning scheme, we strategically prune the search space based on a set of pattern-size-independent pruning rules and develop an iBlackhole algorithm. The second pruning scheme follows a divide-and-conquer strategy to further exploit the pruning results from the first pruning scheme. Indeed, a target directed graphs can be divided into several disconnected subgraphs by the first pruning scheme, and thus the blackhole finding can be conducted in each disconnected subgraph rather than in a large graph. Based on these two pruning schemes, we also develop an iBlackhole-DC algorithm. Finally, experimental results on real-world data show that the iBlackhole-DC algorithm can be several orders of magnitude faster than the iBlackhole algorithm, which has a huge computational advantage over a brute-force method.", "source": "arxiv/ml"}
{"id": "arxiv:561", "title": "Robustness and Generalization", "text": "We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is \"similar\" to a training sample, then the testing error is close to the training error. This provides a novel approach, different from the complexity or stability arguments, to study generalization of learning algorithms. We further show that a weak notion of robustness is both sufficient and necessary for generalizability, which implies that robustness is a fundamental property for learning algorithms to work.", "source": "arxiv/ml"}
{"id": "arxiv:562", "title": "Context models on sequences of covers", "text": "We present a class of models that, via a simple construction, enables exact, incremental, non-parametric, polynomial-time, Bayesian inference of conditional measures. The approach relies upon creating a sequence of covers on the conditioning variable and maintaining a different model for each set within a cover. Inference remains tractable by specifying the probabilistic model in terms of a random walk within the sequence of covers. We demonstrate the approach on problems of conditional density estimation, which, to our knowledge is the first closed-form, non-parametric Bayesian approach to this problem.", "source": "arxiv/ml"}
{"id": "arxiv:563", "title": "Online Learning of Noisy Data with Kernels", "text": "We study online learning when individual instances are corrupted by adversarially chosen random noise. We assume the noise distribution is unknown, and may change over time with no restriction other than having zero mean and bounded variance. Our technique relies on a family of unbiased estimators for non-linear functions, which may be of independent interest. We show that a variant of online gradient descent can learn functions in any dot-product (e.g., polynomial) or Gaussian kernel space with any analytic convex loss function. Our variant uses randomized estimates that need to query a random number of noisy copies of each instance, where with high probability this number is upper bounded by a constant. Allowing such multiple queries cannot be avoided: Indeed, we show that online learning is in general impossible when only one noisy copy of each instance can be accessed.", "source": "arxiv/ml"}
{"id": "arxiv:564", "title": "A Short Introduction to Model Selection, Kolmogorov Complexity and Minimum Description Length (MDL)", "text": "The concept of overfitting in model selection is explained and demonstrated with an example. After providing some background information on information theory and Kolmogorov complexity, we provide a short explanation of Minimum Description Length and error minimization. We conclude with a discussion of the typical features of overfitting in model selection.", "source": "arxiv/ml"}
{"id": "arxiv:565", "title": "Eigenvectors for clustering: Unipartite, bipartite, and directed graph cases", "text": "This paper presents a concise tutorial on spectral clustering for broad spectrum graphs which include unipartite (undirected) graph, bipartite graph, and directed graph. We show how to transform bipartite graph and directed graph into corresponding unipartite graph, therefore allowing a unified treatment to all cases. In bipartite graph, we show that the relaxed solution to the $K$-way co-clustering can be found by computing the left and right eigenvectors of the data matrix. This gives a theoretical basis for $K$-way spectral co-clustering algorithms proposed in the literatures. We also show that solving row and column co-clustering is equivalent to solving row and column clustering separately, thus giving a theoretical support for the claim: ``column clustering implies row clustering and vice versa''. And in the last part, we generalize the Ky Fan theorem---which is the central theorem for explaining spectral clustering---to rectangular complex matrix motivated by the results from bipartite graph analysis.", "source": "arxiv/ml"}
{"id": "arxiv:566", "title": "Hierarchical Clustering for Finding Symmetries and Other Patterns in Massive, High Dimensional Datasets", "text": "Data analysis and data mining are concerned with unsupervised pattern finding and structure determination in data sets. \"Structure\" can be understood as symmetry and a range of symmetries are expressed by hierarchy. Such symmetries directly point to invariants, that pinpoint intrinsic properties of the data and of the background empirical domain of interest. We review many aspects of hierarchy here, including ultrametric topology, generalized ultrametric, linkages with lattices and other discrete algebraic structures and with p-adic number representations. By focusing on symmetries in data we have a powerful means of structuring and analyzing massive, high dimensional data stores. We illustrate the powerfulness of hierarchical clustering in case studies in chemistry and finance, and we provide pointers to other published case studies.", "source": "arxiv/ml"}
{"id": "arxiv:567", "title": "Structural Drift: The Population Dynamics of Sequential Learning", "text": "We introduce a theory of sequential causal inference in which learners in a chain estimate a structural model from their upstream teacher and then pass samples from the model to their downstream student. It extends the population dynamics of genetic drift, recasting Kimura's selectively neutral theory as a special case of a generalized drift process using structured populations with memory. We examine the diffusion and fixation properties of several drift processes and propose applications to learning, inference, and evolution. We also demonstrate how the organization of drift process space controls fidelity, facilitates innovations, and leads to information loss in sequential learning with and without memory.", "source": "arxiv/ml"}
{"id": "arxiv:568", "title": "Evolution with Drifting Targets", "text": "We consider the question of the stability of evolutionary algorithms to gradual changes, or drift, in the target concept. We define an algorithm to be resistant to drift if, for some inverse polynomial drift rate in the target function, it converges to accuracy 1 -- \\epsilon , with polynomial resources, and then stays within that accuracy indefinitely, except with probability \\epsilon , at any one time. We show that every evolution algorithm, in the sense of Valiant (2007; 2009), can be converted using the Correlational Query technique of Feldman (2008), into such a drift resistant algorithm. For certain evolutionary algorithms, such as for Boolean conjunctions, we give bounds on the rates of drift that they can resist. We develop some new evolution algorithms that are resistant to significant drift. In particular, we give an algorithm for evolving linear separators over the spherically symmetric distribution that is resistant to a drift rate of O(\\epsilon /n), and another algorithm over the more general product normal distributions that resists a smaller drift rate. The above translation result can be also interpreted as one on the robustness of the notion of evolvability itself under changes of definition. As a second result in that direction we show that every evolution algorithm can be converted to a quasi-monotonic one that can evolve from any starting point without the performance ever dipping significantly below that of the starting point. This permits the somewhat unnatural feature of arbitrary performance degradations to be removed from several known robustness translations.", "source": "arxiv/ml"}
{"id": "arxiv:569", "title": "Graph-Structured Multi-task Regression and an Efficient Optimization Method for General Fused Lasso", "text": "We consider the problem of learning a structured multi-task regression, where the output consists of multiple responses that are related by a graph and the correlated response variables are dependent on the common inputs in a sparse but synergistic manner. Previous methods such as l1/l2-regularized multi-task regression assume that all of the output variables are equally related to the inputs, although in many real-world problems, outputs are related in a complex manner. In this paper, we propose graph-guided fused lasso (GFlasso) for structured multi-task regression that exploits the graph structure over the output variables. We introduce a novel penalty function based on fusion penalty to encourage highly correlated outputs to share a common set of relevant inputs. In addition, we propose a simple yet efficient proximal-gradient method for optimizing GFlasso that can also be applied to any optimization problems with a convex smooth loss and the general class of fusion penalty defined on arbitrary graph structures. By exploiting the structure of the non-smooth ''fusion penalty'', our method achieves a faster convergence rate than the standard first-order method, sub-gradient method, and is significantly more scalable than the widely adopted second-order cone-programming and quadratic-programming formulations. In addition, we provide an analysis of the consistency property of the GFlasso model. Experimental results not only demonstrate the superiority of GFlasso over the standard lasso but also show the efficiency and scalability of our proximal-gradient method.", "source": "arxiv/ml"}
{"id": "arxiv:570", "title": "Learning Kernel-Based Halfspaces with the Zero-One Loss", "text": "We describe and analyze a new algorithm for agnostically learning kernel-based halfspaces with respect to the \\emph{zero-one} loss function. Unlike most previous formulations which rely on surrogate convex loss functions (e.g. hinge-loss in SVM and log-loss in logistic regression), we provide finite time/sample guarantees with respect to the more natural zero-one loss function. The proposed algorithm can learn kernel-based halfspaces in worst-case time $\\poly(\\exp(L\\log(L/\\epsilon)))$, for $\\emph{any}$ distribution, where $L$ is a Lipschitz constant (which can be thought of as the reciprocal of the margin), and the learned classifier is worse than the optimal halfspace by at most $\\epsilon$. We also prove a hardness result, showing that under a certain cryptographic assumption, no algorithm can learn kernel-based halfspaces in time polynomial in $L$.", "source": "arxiv/ml"}
{"id": "arxiv:571", "title": "Distantly Labeling Data for Large Scale Cross-Document Coreference", "text": "Cross-document coreference, the problem of resolving entity mentions across multi-document collections, is crucial to automated knowledge base construction and data mining tasks. However, the scarcity of large labeled data sets has hindered supervised machine learning research for this task. In this paper we develop and demonstrate an approach based on ``distantly-labeling'' a data set from which we can train a discriminative cross-document coreference model. In particular we build a dataset of more than a million people mentions extracted from 3.5 years of New York Times articles, leverage Wikipedia for distant labeling with a generative model (and measure the reliability of such labeling); then we train and evaluate a conditional random field coreference model that has factors on cross-document entities as well as mention-pairs. This coreference model obtains high accuracy in resolving mentions and entities that are not present in the training data, indicating applicability to non-Wikipedia data. Given the large amount of data, our work is also an exercise demonstrating the scalability of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:572", "title": "Smoothing proximal gradient method for general structured sparse regression", "text": "We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted types of penalties of this kind as motivating examples: (1) the general overlapping-group-lasso penalty, generalized from the group-lasso penalty; and (2) the graph-guided-fused-lasso penalty, generalized from the fused-lasso penalty. For both types of penalties, due to their nonseparability and nonsmoothness, developing an efficient optimization method remains a challenging problem. In this paper we propose a general optimization approach, the smoothing proximal gradient (SPG) method, which can solve structured sparse regression problems with any smooth convex loss under a wide spectrum of structured sparsity-inducing penalties. Our approach combines a smoothing technique with an effective proximal gradient method. It achieves a convergence rate significantly faster than the standard first-order methods, subgradient methods, and is much more scalable than the most widely used interior-point methods. The efficiency and scalability of our method are demonstrated on both simulation experiments and real genetic data sets.", "source": "arxiv/ml"}
{"id": "arxiv:573", "title": "On Recursive Edit Distance Kernels with Application to Time Series Classification", "text": "This paper proposes some extensions to the work on kernels dedicated to string or time series global alignment based on the aggregation of scores obtained by local alignments. The extensions we propose allow to construct, from classical recursive definition of elastic distances, recursive edit distance (or time-warp) kernels that are positive definite if some sufficient conditions are satisfied. The sufficient conditions we end-up with are original and weaker than those proposed in earlier works, although a recursive regularizing term is required to get the proof of the positive definiteness as a direct consequence of the Haussler's convolution theorem. The classification experiment we conducted on three classical time warp distances (two of which being metrics), using Support Vector Machine classifier, leads to conclude that, when the pairwise distance matrix obtained from the training data is \\textit{far} from definiteness, the positive definite recursive elastic kernels outperform in general the distance substituting kernels for the classical elastic distances we have tested.", "source": "arxiv/ml"}
{"id": "arxiv:574", "title": "Wirtinger's Calculus in general Hilbert Spaces", "text": "The present report, has been inspired by the need of the author and its colleagues to understand the underlying theory of Wirtinger's Calculus and to further extend it to include the kernel case. The aim of the present manuscript is twofold: a) it endeavors to provide a more rigorous presentation of the related material, focusing on aspects that the author finds more insightful and b) it extends the notions of Wirtinger's calculus on general Hilbert spaces (such as Reproducing Hilbert Kernel Spaces).", "source": "arxiv/ml"}
{"id": "arxiv:575", "title": "Ranked bandits in metric spaces: learning optimally diverse rankings over large document collections", "text": "Most learning to rank research has assumed that the utility of different documents is independent, which results in learned ranking functions that return redundant results. The few approaches that avoid this have rather unsatisfyingly lacked theoretical foundations, or do not scale. We present a learning-to-rank formulation that optimizes the fraction of satisfied users, with several scalable algorithms that explicitly takes document similarity and ranking context into account. Our formulation is a non-trivial common generalization of two multi-armed bandit models from the literature: \"ranked bandits\" (Radlinski et al., ICML 2008) and \"Lipschitz bandits\" (Kleinberg et al., STOC 2008). We present theoretical justifications for this approach, as well as a near-optimal algorithm. Our evaluation adds optimizations that improve empirical performance, and shows that our algorithms learn orders of magnitude more quickly than previous approaches.", "source": "arxiv/ml"}
{"id": "arxiv:576", "title": "Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes", "text": "The contribution of this paper is to provide a semantic model (using soft constraints) of the words used by web-users to describe objects in a language game; a game in which one user describes a selected object of those composing the scene, and another user has to guess which object has been described. The given description needs to be non ambiguous and accurate enough to allow other users to guess the described shape correctly. To build these semantic models the descriptions need to be analyzed to extract the syntax and words' classes used. We have modeled the meaning of these descriptions using soft constraints as a way for grounding the meaning. The descriptions generated by the system took into account the context of the object to avoid ambiguous descriptions, and allowed users to guess the described object correctly 72% of the times.", "source": "arxiv/ml"}
{"id": "arxiv:577", "title": "Using a Kernel Adatron for Object Classification with RCS Data", "text": "Rapid identification of object from radar cross section (RCS) signals is important for many space and military applications. This identification is a problem in pattern recognition which either neural networks or support vector machines should prove to be high-speed. Bayesian networks would also provide value but require significant preprocessing of the signals. In this paper, we describe the use of a support vector machine for object identification from synthesized RCS data. Our best results are from data fusion of X-band and S-band signals, where we obtained 99.4%, 95.3%, 100% and 95.6% correct identification for cylinders, frusta, spheres, and polygons, respectively. We also compare our results with a Bayesian approach and show that the SVM is three orders of magnitude faster, as measured by the number of floating point operations.", "source": "arxiv/ml"}
{"id": "arxiv:578", "title": "On the clustering aspect of nonnegative matrix factorization", "text": "This paper provides a theoretical explanation on the clustering aspect of nonnegative matrix factorization (NMF). We prove that even without imposing orthogonality nor sparsity constraint on the basis and/or coefficient matrix, NMF still can give clustering results, thus providing a theoretical support for many works, e.g., Xu et al. [1] and Kim et al. [2], that show the superiority of the standard NMF as a clustering method.", "source": "arxiv/ml"}
{"id": "arxiv:579", "title": "Empirical learning aided by weak domain knowledge in the form of feature importance", "text": "Standard hybrid learners that use domain knowledge require stronger knowledge that is hard and expensive to acquire. However, weaker domain knowledge can benefit from prior knowledge while being cost effective. Weak knowledge in the form of feature relative importance (FRI) is presented and explained. Feature relative importance is a real valued approximation of a feature's importance provided by experts. Advantage of using this knowledge is demonstrated by IANN, a modified multilayer neural network algorithm. IANN is a very simple modification of standard neural network algorithm but attains significant performance gains. Experimental results in the field of molecular biology show higher performance over other empirical learning algorithms including standard backpropagation and support vector machines. IANN performance is even comparable to a theory refinement system KBANN that uses stronger domain knowledge. This shows Feature relative importance can improve performance of existing empirical learning algorithms significantly with minimal effort.", "source": "arxiv/ml"}
{"id": "arxiv:580", "title": "Multi-View Active Learning in the Non-Realizable Case", "text": "The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the non-realizable case under multi-view setting. We prove that, with unbounded Tsybakov noise, the sample complexity of multi-view active learning can be $\\widetilde{O}(\\log\\frac{1}{\\epsilon})$, contrasting to single-view setting where the polynomial improvement is the best possible achievement. We also prove that in general multi-view setting the sample complexity of active learning with unbounded Tsybakov noise is $\\widetilde{O}(\\frac{1}{\\epsilon})$, where the order of $1/\\epsilon$ is independent of the parameter in Tsybakov noise, contrasting to previous polynomial bounds where the order of $1/\\epsilon$ is related to the parameter in Tsybakov noise.", "source": "arxiv/ml"}
{"id": "arxiv:581", "title": "On the Relation between Realizable and Nonrealizable Cases of the Sequence Prediction Problem", "text": "A sequence $x_1,\\dots,x_n,\\dots$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\\mu$. After observing each outcome, one is required to give conditional probabilities of the next observation. The realizable case is when the measure $\\mu$ belongs to an arbitrary but known class $\\mathcal C$ of process measures. The non-realizable case is when $\\mu$ is completely arbitrary, but the prediction performance is measured with respect to a given set $\\mathcal C$ of process measures. We are interested in the relations between these problems and between their solutions, as well as in characterizing the cases when a solution exists and finding these solutions. We show that if the quality of prediction is measured using the total variation distance, then these problems coincide, while if it is measured using the expected average KL divergence, then they are different. For some of the formalizations we also show that when a solution exists, it can be obtained as a Bayes mixture over a countable subset of $\\mathcal C$. We also obtain several characterization of those sets $\\mathcal C$ for which solutions to the considered problems exist. As an illustration to the general results obtained, we show that a solution to the non-realizable case of the sequence prediction problem exists for the set of all finite-memory processes, but does not exist for the set of all stationary processes. It should be emphasized that the framework is completely general: the processes measures considered are not required to be i.i.d., mixing, stationary, or to belong to any parametric family.", "source": "arxiv/ml"}
{"id": "arxiv:582", "title": "Information theoretic model validation for clustering", "text": "Model selection in clustering requires (i) to specify a suitable clustering principle and (ii) to control the model order complexity by choosing an appropriate number of clusters depending on the noise level in the data. We advocate an information theoretic perspective where the uncertainty in the measurements quantizes the set of data partitionings and, thereby, induces uncertainty in the solution space of clusterings. A clustering model, which can tolerate a higher level of fluctuations in the measurements than alternative models, is considered to be superior provided that the clustering solution is equally informative. This tradeoff between \\emph{informativeness} and \\emph{robustness} is used as a model selection criterion. The requirement that data partitionings should generalize from one data set to an equally probable second data set gives rise to a new notion of structure induced information.", "source": "arxiv/ml"}
{"id": "arxiv:583", "title": "Prediction with Advice of Unknown Number of Experts", "text": "In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the NormalHedge bound, which mainly depends on the effective number of experts and also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.", "source": "arxiv/ml"}
{"id": "arxiv:584", "title": "Predictive PAC learnability: a paradigm for learning from exchangeable input data", "text": "Exchangeable random variables form an important and well-studied generalization of i.i.d. variables, however simple examples show that no nontrivial concept or function classes are PAC learnable under general exchangeable data inputs $X_1,X_2,\\ldots$. Inspired by the work of Berti and Rigo on a Glivenko--Cantelli theorem for exchangeable inputs, we propose a new paradigm, adequate for learning from exchangeable data: predictive PAC learnability. A learning rule $\\mathcal L$ for a function class $\\mathscr F$ is predictive PAC if for every $\\e,\\delta>0$ and each function $f\\in {\\mathscr F}$, whenever $\\abs{\\sigma}\\geq s(\\delta,\\e)$, we have with confidence $1-\\delta$ that the expected difference between $f(X_{n+1})$ and the image of $f\\vert\\sigma$ under $\\mathcal L$ does not exceed $\\e$ conditionally on $X_1,X_2,\\ldots,X_n$. Thus, instead of learning the function $f$ as such, we are learning to a given accuracy $\\e$ the predictive behaviour of $f$ at the future points $X_i(\\omega)$, $i>n$ of the sample path. Using de Finetti's theorem, we show that if a universally separable function class $\\mathscr F$ is distribution-free PAC learnable under i.i.d. inputs, then it is distribution-free predictive PAC learnable under exchangeable inputs, with a slightly worse sample complexity.", "source": "arxiv/ml"}
{"id": "arxiv:585", "title": "Online Learning via Sequential Complexities", "text": "We consider the problem of sequential prediction and provide tools to study the minimax value of the associated game. Classical statistical learning theory provides several useful complexity measures to study learning with i.i.d. data. Our proposed sequential complexities can be seen as extensions of these measures to the sequential setting. The developed theory is shown to yield precise learning guarantees for the problem of sequential prediction. In particular, we show necessary and sufficient conditions for online learnability in the setting of supervised learning. Several examples show the utility of our framework: we can establish learnability without having to exhibit an explicit online learning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:586", "title": "Regression on fixed-rank positive semidefinite matrices: a Riemannian approach", "text": "The paper addresses the problem of learning a regression model parameterized by a fixed-rank positive semidefinite matrix. The focus is on the nonlinear nature of the search space and on scalability to high-dimensional problems. The mathematical developments rely on the theory of gradient descent algorithms adapted to the Riemannian geometry that underlies the set of fixed-rank positive semidefinite matrices. In contrast with previous contributions in the literature, no restrictions are imposed on the range space of the learned matrix. The resulting algorithms maintain a linear complexity in the problem size and enjoy important invariance properties. We apply the proposed algorithms to the problem of learning a distance function parameterized by a positive semidefinite matrix. Good performance is observed on classical benchmarks.", "source": "arxiv/ml"}
{"id": "arxiv:587", "title": "Uncovering the Riffled Independence Structure of Rankings", "text": "Representing distributions over permutations can be a daunting task due to the fact that the number of permutations of $n$ objects scales factorially in $n$. One recent way that has been used to reduce storage complexity has been to exploit probabilistic independence, but as we argue, full independence assumptions impose strong sparsity constraints on distributions and are unsuitable for modeling rankings. We identify a novel class of independence structures, called \\emph{riffled independence}, encompassing a more expressive family of distributions while retaining many of the properties necessary for performing efficient inference and reducing sample complexity. In riffled independence, one draws two permutations independently, then performs the \\emph{riffle shuffle}, common in card games, to combine the two permutations to form a single permutation. Within the context of ranking, riffled independence corresponds to ranking disjoint sets of objects independently, then interleaving those rankings. In this paper, we provide a formal introduction to riffled independence and present algorithms for using riffled independence within Fourier-theoretic frameworks which have been explored by a number of recent papers. Additionally, we propose an automated method for discovering sets of items which are riffle independent from a training set of rankings. We show that our clustering-like algorithms can be used to discover meaningful latent coalitions from real preference ranking datasets and to learn the structure of hierarchically decomposable models based on riffled independence.", "source": "arxiv/ml"}
{"id": "arxiv:588", "title": "Calibration and Internal no-Regret with Partial Monitoring", "text": "Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of Blackwell's approachability theorem, in an other auxiliary game. We establish the converse: a strategy that approaches a convex $B$-set can be derived from the construction of a calibrated strategy. We develop these tools in the framework of a game with partial monitoring, where players do not observe the actions of their opponents but receive random signals, to define a notion of internal regret and construct strategies that have no such regret.", "source": "arxiv/ml"}
{"id": "arxiv:589", "title": "Dyadic Prediction Using a Latent Feature Log-Linear Model", "text": "In dyadic prediction, labels must be predicted for pairs (dyads) whose members possess unique identifiers and, sometimes, additional features called side-information. Special cases of this problem include collaborative filtering and link prediction. We present the first model for dyadic prediction that satisfies several important desiderata: (i) labels may be ordinal or nominal, (ii) side-information can be easily exploited if present, (iii) with or without side-information, latent features are inferred for dyad members, (iv) it is resistant to sample-selection bias, (v) it can learn well-calibrated probabilities, and (vi) it can scale to very large datasets. To our knowledge, no existing method satisfies all the above criteria. In particular, many methods assume that the labels are ordinal and ignore side-information when it is present. Experimental results show that the new method is competitive with state-of-the-art methods for the special cases of collaborative filtering and link prediction, and that it makes accurate predictions on nominal data.", "source": "arxiv/ml"}
{"id": "arxiv:590", "title": "On the Achievability of Cram\\'er-Rao Bound In Noisy Compressed Sensing", "text": "Recently, it has been proved in Babadi et al. that in noisy compressed sensing, a joint typical estimator can asymptotically achieve the Cramer-Rao lower bound of the problem.To prove this result, this paper used a lemma,which is provided in Akcakaya et al,that comprises the main building block of the proof. This lemma is based on the assumption of Gaussianity of the measurement matrix and its randomness in the domain of noise. In this correspondence, we generalize the results obtained in Babadi et al by dropping the Gaussianity assumption on the measurement matrix. In fact, by considering the measurement matrix as a deterministic matrix in our analysis, we find a theorem similar to the main theorem of Babadi et al for a family of randomly generated (but deterministic in the noise domain) measurement matrices that satisfy a generalized condition known as The Concentration of Measures Inequality. By this, we finally show that under our generalized assumptions, the Cramer-Rao bound of the estimation is achievable by using the typical estimator introduced in Babadi et al.", "source": "arxiv/ml"}
{"id": "arxiv:591", "title": "Agnostic Active Learning Without Constraints", "text": "We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate hypotheses is maintained throughout learning, and only hypotheses from this set are ever returned. By avoiding this version space approach, our algorithm sheds the computational burden and brittleness associated with maintaining version spaces, yet still allows for substantial improvements over supervised learning for classification.", "source": "arxiv/ml"}
{"id": "arxiv:592", "title": "Outlier Detection Using Nonconvex Penalized Regression", "text": "This paper studies the outlier detection problem from the point of view of penalized regressions. Our regression model adds one mean shift parameter for each of the $n$ data points. We then apply a regularization favoring a sparse vector of mean shift parameters. The usual $L_1$ penalty yields a convex criterion, but we find that it fails to deliver a robust estimator. The $L_1$ penalty corresponds to soft thresholding. We introduce a thresholding (denoted by $\\Theta$) based iterative procedure for outlier detection ($\\Theta$-IPOD). A version based on hard thresholding correctly identifies outliers on some hard test problems. We find that $\\Theta$-IPOD is much faster than iteratively reweighted least squares for large data because each iteration costs at most $O(np)$ (and sometimes much less) avoiding an $O(np^2)$ least squares estimate. We describe the connection between $\\Theta$-IPOD and $M$-estimators. Our proposed method has one tuning parameter with which to both identify outliers and estimate regression coefficients. A data-dependent choice can be made based on BIC. The tuned $\\Theta$-IPOD shows outstanding performance in identifying outliers in various situations in comparison to other existing approaches. This methodology extends to high-dimensional modeling with $p\\gg n$, if both the coefficient vector and the outlier pattern are sparse.", "source": "arxiv/ml"}
{"id": "arxiv:593", "title": "Approximated Structured Prediction for Learning Large Scale Graphical Models", "text": "This manuscripts contains the proofs for \"A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction\".", "source": "arxiv/ml"}
{"id": "arxiv:594", "title": "Extension of Wirtinger's Calculus to Reproducing Kernel Hilbert Spaces and the Complex Kernel LMS", "text": "Over the last decade, kernel methods for nonlinear processing have successfully been used in the machine learning community. The primary mathematical tool employed in these methods is the notion of the Reproducing Kernel Hilbert Space. However, so far, the emphasis has been on batch techniques. It is only recently, that online techniques have been considered in the context of adaptive signal processing tasks. Moreover, these efforts have only been focussed on real valued data sequences. To the best of our knowledge, no adaptive kernel-based strategy has been developed, so far, for complex valued signals. Furthermore, although the real reproducing kernels are used in an increasing number of machine learning problems, complex kernels have not, yet, been used, in spite of their potential interest in applications that deal with complex signals, with Communications being a typical example. In this paper, we present a general framework to attack the problem of adaptive filtering of complex signals, using either real reproducing kernels, taking advantage of a technique called \\textit{complexification} of real RKHSs, or complex reproducing kernels, highlighting the use of the complex gaussian kernel. In order to derive gradients of operators that need to be defined on the associated complex RKHSs, we employ the powerful tool of Wirtinger's Calculus, which has recently attracted attention in the signal processing community. To this end, in this paper, the notion of Wirtinger's calculus is extended, for the first time, to include complex RKHSs and use it to derive several realizations of the Complex Kernel Least-Mean-Square (CKLMS) algorithm. Experiments verify that the CKLMS offers significant performance improvements over several linear and nonlinear algorithms, when dealing with nonlinearities.", "source": "arxiv/ml"}
{"id": "arxiv:595", "title": "Fictitious Play with Time-Invariant Frequency Update for Network Security", "text": "We study two-player security games which can be viewed as sequences of nonzero-sum matrix games played by an Attacker and a Defender. The evolution of the game is based on a stochastic fictitious play process, where players do not have access to each other's payoff matrix. Each has to observe the other's actions up to present and plays the action generated based on the best response to these observations. In a regular fictitious play process, each player makes a maximum likelihood estimate of her opponent's mixed strategy, which results in a time-varying update based on the previous estimate and current action. In this paper, we explore an alternative scheme for frequency update, whose mean dynamic is instead time-invariant. We examine convergence properties of the mean dynamic of the fictitious play process with such an update scheme, and establish local stability of the equilibrium point when both players are restricted to two actions. We also propose an adaptive algorithm based on this time-invariant frequency update.", "source": "arxiv/ml"}
{"id": "arxiv:596", "title": "Segmentation of Natural Images by Texture and Boundary Compression", "text": "We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes as multi-scale texture features. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. We test our algorithm on the publicly available Berkeley Segmentation Dataset. It achieves state-of-the-art segmentation results compared to other existing methods.", "source": "arxiv/ml"}
{"id": "arxiv:597", "title": "Least Squares Superposition Codes of Moderate Dictionary Size, Reliable at Rates up to Capacity", "text": "For the additive white Gaussian noise channel with average codeword power constraint, new coding methods are devised in which the codewords are sparse superpositions, that is, linear combinations of subsets of vectors from a given design, with the possible messages indexed by the choice of subset. Decoding is by least squares, tailored to the assumed form of linear combination. Communication is shown to be reliable with error probability exponentially small for all rates up to the Shannon capacity.", "source": "arxiv/ml"}
{"id": "arxiv:598", "title": "Toward Fast Reliable Communication at Rates Near Capacity with Gaussian Noise", "text": "For the additive Gaussian noise channel with average codeword power constraint, sparse superposition codes and adaptive successive decoding is developed. Codewords are linear combinations of subsets of vectors, with the message indexed by the choice of subset. A feasible decoding algorithm is presented. Communication is reliable with error probability exponentially small for all rates below the Shannon capacity.", "source": "arxiv/ml"}
{"id": "arxiv:599", "title": "Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties", "text": "Online learning has become increasingly popular on handling massive data. The sequential nature of online learning, however, requires a centralized learner to store data and update parameters. In this paper, we consider online learning with {\\em distributed} data sources. The autonomous learners update local parameters based on local data sources and periodically exchange information with a small subset of neighbors in a communication network. We derive the regret bound for strongly convex functions that generalizes the work by Ram et al. (2010) for convex functions. Most importantly, we show that our algorithm has \\emph{intrinsic} privacy-preserving properties, and we prove the sufficient and necessary conditions for privacy preservation in the network. These conditions imply that for networks with greater-than-one connectivity, a malicious learner cannot reconstruct the subgradients (and sensitive raw data) of other learners, which makes our algorithm appealing in privacy sensitive applications.", "source": "arxiv/ml"}
{"id": "arxiv:600", "title": "On the Implementation of the Probabilistic Logic Programming Language ProbLog", "text": "The past few years have seen a surge of interest in the field of probabilistic logic learning and statistical relational learning. In this endeavor, many probabilistic logics have been developed. ProbLog is a recent probabilistic extension of Prolog motivated by the mining of large biological networks. In ProbLog, facts can be labeled with probabilities. These facts are treated as mutually independent random variables that indicate whether these facts belong to a randomly sampled program. Different kinds of queries can be posed to ProbLog programs. We introduce algorithms that allow the efficient execution of these queries, discuss their implementation on top of the YAP-Prolog system, and evaluate their performance in the context of large networks of biological entities.", "source": "arxiv/ml"}
{"id": "arxiv:601", "title": "A Novel Rough Set Reduct Algorithm for Medical Domain Based on Bee Colony Optimization", "text": "Feature selection refers to the problem of selecting relevant features which produce the most predictive outcome. In particular, feature selection task is involved in datasets containing huge number of features. Rough set theory has been one of the most successful methods used for feature selection. However, this method is still not able to find optimal subsets. This paper proposes a new feature selection method based on Rough set theory hybrid with Bee Colony Optimization (BCO) in an attempt to combat this. This proposed work is applied in the medical domain to find the minimal reducts and experimentally compared with the Quick Reduct, Entropy Based Reduct, and other hybrid Rough Set methods such as Genetic Algorithm (GA), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO).", "source": "arxiv/ml"}
{"id": "arxiv:602", "title": "MINLIP for the Identification of Monotone Wiener Systems", "text": "This paper studies the MINLIP estimator for the identification of Wiener systems consisting of a sequence of a linear FIR dynamical model, and a monotonically increasing (or decreasing) static function. Given $T$ observations, this algorithm boils down to solving a convex quadratic program with $O(T)$ variables and inequality constraints, implementing an inference technique which is based entirely on model complexity control. The resulting estimates of the linear submodel are found to be almost consistent when no noise is present in the data, under a condition of smoothness of the true nonlinearity and local Persistency of Excitation (local PE) of the data. This result is novel as it does not rely on classical tools as a 'linearization' using a Taylor decomposition, nor exploits stochastic properties of the data. It is indicated how to extend the method to cope with noisy data, and empirical evidence contrasts performance of the estimator against other recently proposed techniques.", "source": "arxiv/ml"}
{"id": "arxiv:603", "title": "GraphLab: A New Framework for Parallel Machine Learning", "text": "Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and Pthreads leave ML experts repeatedly solving the same design challenges. By targeting common patterns in ML, we developed GraphLab, which improves upon abstractions like MapReduce by compactly expressing asynchronous iterative algorithms with sparse computational dependencies while ensuring data consistency and achieving a high degree of parallel performance. We demonstrate the expressiveness of the GraphLab framework by designing and implementing parallel versions of belief propagation, Gibbs sampling, Co-EM, Lasso and Compressed Sensing. We show that using GraphLab we can achieve excellent parallel performance on large scale real-world problems.", "source": "arxiv/ml"}
{"id": "arxiv:604", "title": "Fast ABC-Boost for Multi-Class Classification", "text": "Abc-boost is a new line of boosting algorithms for multi-class classification, by utilizing the commonly used sum-to-zero constraint. To implement abc-boost, a base class must be identified at each boosting step. Prior studies used a very expensive procedure based on exhaustive search for determining the base class at each boosting step. Good testing performances of abc-boost (implemented as abc-mart and abc-logitboost) on a variety of datasets were reported. For large datasets, however, the exhaustive search strategy adopted in prior abc-boost algorithms can be too prohibitive. To overcome this serious limitation, this paper suggests a heuristic by introducing Gaps when computing the base class during training. That is, we update the choice of the base class only for every $G$ boosting steps (i.e., G=1 in prior studies). We test this idea on large datasets (Covertype and Poker) as well as datasets of moderate sizes. Our preliminary results are very encouraging. On the large datasets, even with G=100 (or larger), there is essentially no loss of test accuracy. On the moderate datasets, no obvious loss of test accuracy is observed when G<= 20~50. Therefore, aided by this heuristic, it is promising that abc-boost will be a practical tool for accurate multi-class classification.", "source": "arxiv/ml"}
{"id": "arxiv:605", "title": "Learning sparse gradients for variable selection and dimension reduction", "text": "Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning (SGL), for variable selection and dimension reduction via learning the gradients of the prediction function directly from samples. By imposing a sparsity constraint on the gradients, variable selection is achieved by selecting variables corresponding to non-zero partial derivatives, and effective dimensions are extracted based on the eigenvectors of the derived sparse empirical gradient covariance matrix. An error analysis is given for the convergence of the estimated gradients to the true ones in both the Euclidean and the manifold setting. We also develop an efficient forward-backward splitting algorithm to solve the SGL problem, making the framework practically scalable for medium or large datasets. The utility of SGL for variable selection and feature extraction is explicitly given and illustrated on artificial data as well as real-world examples. The main advantages of our method include variable selection for both linear and nonlinear predictions, effective dimension reduction with sparse loadings, and an efficient algorithm for large p, small n problems.", "source": "arxiv/ml"}
{"id": "arxiv:606", "title": "Split Bregman method for large scale fused Lasso", "text": "rdering of regression or classification coefficients occurs in many real-world applications. Fused Lasso exploits this ordering by explicitly regularizing the differences between neighboring coefficients through an $\\ell_1$ norm regularizer. However, due to nonseparability and nonsmoothness of the regularization term, solving the fused Lasso problem is computationally demanding. Existing solvers can only deal with problems of small or medium size, or a special case of the fused Lasso problem in which the predictor matrix is identity matrix. In this paper, we propose an iterative algorithm based on split Bregman method to solve a class of large-scale fused Lasso problems, including a generalized fused Lasso and a fused Lasso support vector classifier. We derive our algorithm using augmented Lagrangian method and prove its convergence properties. The performance of our method is tested on both artificial data and real-world applications including proteomic data from mass spectrometry and genomic data from array CGH. We demonstrate that our method is many times faster than the existing solvers, and show that it is especially efficient for large p, small n problems.", "source": "arxiv/ml"}
{"id": "arxiv:607", "title": "PAC learnability of a concept class under non-atomic measures: a problem by Vidyasagar", "text": "In response to a 1997 problem of M. Vidyasagar, we state a necessary and sufficient condition for distribution-free PAC learnability of a concept class $\\mathscr C$ under the family of all non-atomic (diffuse) measures on the domain $\\Omega$. Clearly, finiteness of the classical Vapnik-Chervonenkis dimension of $\\mathscr C$ is a sufficient, but no longer necessary, condition. Besides, learnability of $\\mathscr C$ under non-atomic measures does not imply the uniform Glivenko-Cantelli property with regard to non-atomic measures. Our learnability criterion is stated in terms of a combinatorial parameter $\\VC({\\mathscr C}\\,{\\mathrm{mod}}\\,\\omega_1)$ which we call the VC dimension of $\\mathscr C$ modulo countable sets. The new parameter is obtained by ``thickening up'' single points in the definition of VC dimension to uncountable ``clusters''. Equivalently, $\\VC(\\mathscr C\\modd\\omega_1)\\leq d$ if and only if every countable subclass of $\\mathscr C$ has VC dimension $\\leq d$ outside a countable subset of $\\Omega$. The new parameter can be also expressed as the classical VC dimension of $\\mathscr C$ calculated on a suitable subset of a compactification of $\\Omega$. We do not make any measurability assumptions on $\\mathscr C$, assuming instead the validity of Martin's Axiom (MA).", "source": "arxiv/ml"}
{"id": "arxiv:608", "title": "Feature Construction for Relational Sequence Learning", "text": "We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences. To deal with this problem, firstly each relational sequence is mapped into a feature vector using the result of a feature construction method. Since, the efficacy of sequence learning algorithms strongly depends on the features used to represent the sequences, the second step is to find an optimal subset of the constructed features leading to high classification accuracy. This feature selection task has been solved adopting a wrapper approach that uses a stochastic local search algorithm embedding a naive Bayes classifier. The performance of the proposed method applied to a real-world dataset shows an improvement when compared to other established methods, such as hidden Markov models, Fisher kernels and conditional random fields for relational sequences.", "source": "arxiv/ml"}
{"id": "arxiv:609", "title": "Data Stream Clustering: Challenges and Issues", "text": "Very large databases are required to store massive amounts of data that are continuously inserted and queried. Analyzing huge data sets and extracting valuable pattern in many applications are interesting for researchers. We can identify two main groups of techniques for huge data bases mining. One group refers to streaming data and applies mining techniques whereas second group attempts to solve this problem directly with efficient algorithms. Recently many researchers have focused on data stream as an efficient strategy against huge data base mining instead of mining on entire data base. The main problem in data stream mining means evolving data is more difficult to detect in this techniques therefore unsupervised methods should be applied. However, clustering techniques can lead us to discover hidden information. In this survey, we try to clarify: first, the different problem definitions related to data stream clustering in general; second, the specific difficulties encountered in this field of research; third, the varying assumptions, heuristics, and intuitions forming the basis of different approaches; and how several prominent solutions tackle different problems. Index Terms- Data Stream, Clustering, K-Means, Concept drift", "source": "arxiv/ml"}
{"id": "arxiv:610", "title": "A Survey Paper on Recommender Systems", "text": "Recommender systems apply data mining techniques and prediction algorithms to predict users' interest on information, products and services among the tremendous amount of available items. The vast growth of information on the Internet as well as number of visitors to websites add some key challenges to recommender systems. These are: producing accurate recommendation, handling many recommendations efficiently and coping with the vast growth of number of participants in the system. Therefore, new recommender system technologies are needed that can quickly produce high quality recommendations even for huge data sets. To address these issues we have explored several collaborative filtering techniques such as the item based approach, which identify relationship between items and indirectly compute recommendations for users based on these relationships. The user based approach was also studied, it identifies relationships between users of similar tastes and computes recommendations based on these relationships. In this paper, we introduce the topic of recommender system. It provides ways to evaluate efficiency, scalability and accuracy of recommender system. The paper also analyzes different algorithms of user based and item based techniques for recommendation generation. Moreover, a simple experiment was conducted using a data mining application -Weka- to apply data mining algorithms to recommender system. We conclude by proposing our approach that might enhance the quality of recommender systems.", "source": "arxiv/ml"}
{"id": "arxiv:611", "title": "The Link Prediction Problem in Bipartite Networks", "text": "We define and study the link prediction problem in bipartite networks, specializing general link prediction algorithms to the bipartite case. In a graph, a link prediction function of two vertices denotes the similarity or proximity of the vertices. Common link prediction functions for general graphs are defined using paths of length two between two nodes. Since in a bipartite graph adjacency vertices can only be connected by paths of odd lengths, these functions do not apply to bipartite graphs. Instead, a certain class of graph kernels (spectral transformation kernels) can be generalized to bipartite graphs when the positive-semidefinite kernel constraint is relaxed. This generalization is realized by the odd component of the underlying spectral transformation. This construction leads to several new link prediction pseudokernels such as the matrix hyperbolic sine, which we examine for rating graphs, authorship graphs, folksonomies, document--feature networks and other types of bipartite networks.", "source": "arxiv/ml"}
{"id": "arxiv:612", "title": "A Bayesian View of the Poisson-Dirichlet Process", "text": "The two parameter Poisson-Dirichlet Process (PDP), a generalisation of the Dirichlet Process, is increasingly being used for probabilistic modelling in discrete areas such as language technology, bioinformatics, and image analysis. There is a rich literature about the PDP and its derivative distributions such as the Chinese Restaurant Process (CRP). This article reviews some of the basic theory and then the major results needed for Bayesian modelling of discrete problems including details of priors, posteriors and computation. The PDP allows one to build distributions over countable partitions. The PDP has two other remarkable properties: first it is partially conjugate to itself, which allows one to build hierarchies of PDPs, and second using a marginalised relative the CRP, one gets fragmentation and clustering properties that lets one layer partitions to build trees. This article presents the basic theory for understanding the notion of partitions and distributions over them, the PDP and the CRP, and the important properties of conjugacy, fragmentation and clustering, as well as some key related properties such as consistency and convergence. This article also presents a Bayesian interpretation of the Poisson-Dirichlet process based on an improper and infinite dimensional Dirichlet distribution. This means we can understand the process as just another Dirichlet and thus all its sampling properties emerge naturally. The theory of PDPs is usually presented for continuous distributions (more generally referred to as non-atomic distributions), however, when applied to discrete distributions its remarkable conjugacy property emerges. This context and basic results are also presented, as well as techniques for computing the second order Stirling numbers that occur in the posteriors for discrete distributions.", "source": "arxiv/ml"}
{"id": "arxiv:613", "title": "Additive Non-negative Matrix Factorization for Missing Data", "text": "Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. We interpret the factorization in a new way and use it to generate missing attributes from test data. We provide a joint optimization scheme for the missing attributes as well as the NMF factors. We prove the monotonic convergence of our algorithms. We present classification results for cases with missing attributes.", "source": "arxiv/ml"}
{"id": "arxiv:614", "title": "IMP: A Message-Passing Algorithmfor Matrix Completion", "text": "A new message-passing (MP) method is considered for the matrix completion problem associated with recommender systems. We attack the problem using a (generative) factor graph model that is related to a probabilistic low-rank matrix factorization. Based on the model, we propose a new algorithm, termed IMP, for the recovery of a data matrix from incomplete observations. The algorithm is based on a clustering followed by inference via MP (IMP). The algorithm is compared with a number of other matrix completion algorithms on real collaborative filtering (e.g., Netflix) data matrices. Our results show that, while many methods perform similarly with a large number of revealed entries, the IMP algorithm outperforms all others when the fraction of observed entries is small. This is helpful because it reduces the well-known cold-start problem associated with collaborative filtering (CF) systems in practice.", "source": "arxiv/ml"}
{"id": "arxiv:615", "title": "Query Strategies for Evading Convex-Inducing Classifiers", "text": "Classifiers are often used to detect miscreant activities. We study how an adversary can systematically query a classifier to elicit information that allows the adversary to evade detection while incurring a near-minimal cost of modifying their intended malfeasance. We generalize the theory of Lowd and Meek (2005) to the family of convex-inducing classifiers that partition input space into two sets one of which is convex. We present query algorithms for this family that construct undetected instances of approximately minimal cost using only polynomially-many queries in the dimension of the space and in the level of approximation. Our results demonstrate that near-optimal evasion can be accomplished without reverse-engineering the classifier's decision boundary. We also consider general lp costs and show that near-optimal evasion on the family of convex-inducing classifiers is generally efficient for both positive and negative convexity for all levels of approximation if p=1.", "source": "arxiv/ml"}
{"id": "arxiv:616", "title": "Computational Model of Music Sight Reading: A Reinforcement Learning Approach", "text": "Although the Music Sight Reading process has been studied from the cognitive psychology view points, but the computational learning methods like the Reinforcement Learning have not yet been used to modeling of such processes. In this paper, with regards to essential properties of our specific problem, we consider the value function concept and will indicate that the optimum policy can be obtained by the method we offer without to be getting involved with computing of the complex value functions. Also, we will offer a normative behavioral model for the interaction of the agent with the musical pitch environment and by using a slightly different version of Partially observable Markov decision processes we will show that our method helps for faster learning of state-action pairs in our implemented agents.", "source": "arxiv/ml"}
{"id": "arxiv:617", "title": "A Reinforcement Learning Model Using Neural Networks for Music Sight Reading Learning Problem", "text": "Music Sight Reading is a complex process in which when it is occurred in the brain some learning attributes would be emerged. Besides giving a model based on actor-critic method in the Reinforcement Learning, the agent is considered to have a neural network structure. We studied on where the sight reading process is happened and also a serious problem which is how the synaptic weights would be adjusted through the learning process. The model we offer here is a computational model on which an updated weights equation to fix the weights is accompanied too.", "source": "arxiv/ml"}
{"id": "arxiv:618", "title": "Minimax Manifold Estimation", "text": "We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^D given a noisy sample from the manifold. We assume that the manifold satisfies a smoothness condition and that the noise distribution has compact support. We show that the optimal rate of convergence is n^{-2/(2+d)}. Thus, the minimax rate depends only on the dimension of the manifold, not on the dimension of the space in which M is embedded.", "source": "arxiv/ml"}
{"id": "arxiv:619", "title": "The Latent Bernoulli-Gauss Model for Data Analysis", "text": "We present a new latent-variable model employing a Gaussian mixture integrated with a feature selection procedure (the Bernoulli part of the model) which together form a \"Latent Bernoulli-Gauss\" distribution. The model is applied to MAP estimation, clustering, feature selection and collaborative filtering and fares favorably with the state-of-the-art latent-variable models.", "source": "arxiv/ml"}
{"id": "arxiv:620", "title": "Filtrage vaste marge pour l'\\'etiquetage s\\'equentiel \\`a noyaux de signaux", "text": "We address in this paper the problem of multi-channel signal sequence labeling. In particular, we consider the problem where the signals are contaminated by noise or may present some dephasing with respect to their labels. For that, we propose to jointly learn a SVM sample classifier with a temporal filtering of the channels. This will lead to a large margin filtering that is adapted to the specificity of each channel (noise and time-lag). We derive algorithms to solve the optimization problem and we discuss different filter regularizations for automated scaling or selection of channels. Our approach is tested on a non-linear toy example and on a BCI dataset. Results show that the classification performance on these problems can be improved by learning a large margin filtering.", "source": "arxiv/ml"}
{"id": "arxiv:621", "title": "A note on sample complexity of learning binary output neural networks under fixed input distributions", "text": "We show that the learning sample complexity of a sigmoidal neural network constructed by Sontag (1992) required to achieve a given misclassification error under a fixed purely atomic distribution can grow arbitrarily fast: for any prescribed rate of growth there is an input distribution having this rate as the sample complexity, and the bound is asymptotically tight. The rate can be superexponential, a non-recursive function, etc. We further observe that Sontag's ANN is not Glivenko-Cantelli under any input distribution having a non-atomic part.", "source": "arxiv/ml"}
{"id": "arxiv:622", "title": "Reinforcement Learning via AIXI Approximation", "text": "This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents. Previously, it has been unclear whether the theory of AIXI could motivate the design of practical algorithms. We answer this hitherto open question in the affirmative, by providing the first computationally feasible approximation to the AIXI agent. To develop our approximation, we introduce a Monte Carlo Tree Search algorithm along with an agent-specific extension of the Context Tree Weighting algorithm. Empirically, we present a set of encouraging results on a number of stochastic, unknown, and partially observable domains.", "source": "arxiv/ml"}
{"id": "arxiv:623", "title": "Consistency of Feature Markov Processes", "text": "We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed to summarize useful information from the history. We want a method that is asymptotically consistent in the sense it will provably eventually only choose between alternatives that satisfy an optimality property related to the used criterion. We extend our work to the case where there is side information that one can take advantage of and, furthermore, we briefly discuss the active setting where an agent takes actions to achieve desirable outcomes.", "source": "arxiv/ml"}
{"id": "arxiv:624", "title": "Online Algorithms for the Multi-Armed Bandit Problem with Markovian Rewards", "text": "We consider the classical multi-armed bandit problem with Markovian rewards. When played an arm changes its state in a Markovian fashion while it remains frozen when not played. The player receives a state-dependent reward each time it plays an arm. The number of states and the state transition probabilities of an arm are unknown to the player. The player's objective is to maximize its long-term total reward by learning the best arm over time. We show that under certain conditions on the state transition probabilities of the arms, a sample mean based index policy achieves logarithmic regret uniformly over the total number of trials. The result shows that sample mean based index policies can be applied to learning problems under the rested Markovian bandit model without loss of optimality in the order. Moreover, comparision between Anantharam's index policy and UCB shows that by choosing a small exploration parameter UCB can have a smaller regret than Anantharam's index policy.", "source": "arxiv/ml"}
{"id": "arxiv:625", "title": "A Brief Introduction to Temporality and Causality", "text": "Causality is a non-obvious concept that is often considered to be related to temporality. In this paper we present a number of past and present approaches to the definition of temporality and causality from philosophical, physical, and computational points of view. We note that time is an important ingredient in many relationships and phenomena. The topic is then divided into the two main areas of temporal discovery, which is concerned with finding relations that are stretched over time, and causal discovery, where a claim is made as to the causal influence of certain events on others. We present a number of computational tools used for attempting to automatically discover temporal and causal relations in data.", "source": "arxiv/ml"}
{"id": "arxiv:626", "title": "A Machine Learning Approach to Recovery of Scene Geometry from Images", "text": "Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general machine learning approach called unsupervised CRF learning based on maximizing the conditional likelihood. We apply our approach to computer vision systems that recover the 3-D scene geometry from images. We focus on recovering 3D geometry from single images, stereo pairs and video sequences. Building these systems requires algorithms for doing inference as well as learning the parameters of conditional Markov random fields (MRF). Our system is trained unsupervisedly without using ground-truth labeled data. We employ a slanted-plane stereo vision model in which we use a fixed over-segmentation to segment the left image into coherent regions called superpixels, then assign a disparity plane for each superpixel. Plane parameters are estimated by solving an MRF labelling problem, through minimizing an energy fuction. We demonstrate the use of our unsupervised CRF learning algorithm for a parameterized slanted-plane stereo vision model involving shape from texture cues. Our stereo model with texture cues, only by unsupervised training, outperforms the results in related work on the same stereo dataset. In this thesis, we also formulate structure and motion estimation as an energy minimization problem, in which the model is an extension of our slanted-plane stereo vision model that also handles surface velocity. Velocity estimation is achieved by solving an MRF labeling problem using Loopy BP. Performance analysis is done using our novel evaluation metrics based on the notion of view prediction error. Experiments on road-driving stereo sequences show encouraging results.", "source": "arxiv/ml"}
{"id": "arxiv:627", "title": "Manifold Elastic Net: A Unified Framework for Sparse Dimension Reduction", "text": "It is difficult to find the optimal sparse solution of a manifold learning based dimensionality reduction algorithm. The lasso or the elastic net penalized manifold learning based dimensionality reduction is not directly a lasso penalized least square problem and thus the least angle regression (LARS) (Efron et al. \\cite{LARS}), one of the most popular algorithms in sparse learning, cannot be applied. Therefore, most current approaches take indirect ways or have strict settings, which can be inconvenient for applications. In this paper, we proposed the manifold elastic net or MEN for short. MEN incorporates the merits of both the manifold learning based dimensionality reduction and the sparse learning based dimensionality reduction. By using a series of equivalent transformations, we show MEN is equivalent to the lasso penalized least square problem and thus LARS is adopted to obtain the optimal sparse solution of MEN. In particular, MEN has the following advantages for subsequent classification: 1) the local geometry of samples is well preserved for low dimensional data representation, 2) both the margin maximization and the classification error minimization are considered for sparse projection calculation, 3) the projection matrix of MEN improves the parsimony in computation, 4) the elastic net penalty reduces the over-fitting problem, and 5) the projection matrix of MEN can be interpreted psychologically and physiologically. Experimental evidence on face recognition over various popular datasets suggests that MEN is superior to top level dimensionality reduction algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:628", "title": "A generalized risk approach to path inference based on hidden Markov models", "text": "Motivated by the unceasing interest in hidden Markov models (HMMs), this paper re-examines hidden path inference in these models, using primarily a risk-based framework. While the most common maximum a posteriori (MAP), or Viterbi, path estimator and the minimum error, or Posterior Decoder (PD), have long been around, other path estimators, or decoders, have been either only hinted at or applied more recently and in dedicated applications generally unfamiliar to the statistical learning community. Over a decade ago, however, a family of algorithmically defined decoders aiming to hybridize the two standard ones was proposed (Brushe et al., 1998). The present paper gives a careful analysis of this hybridization approach, identifies several problems and issues with it and other previously proposed approaches, and proposes practical resolutions of those. Furthermore, simple modifications of the classical criteria for hidden path recognition are shown to lead to a new class of decoders. Dynamic programming algorithms to compute these decoders in the usual forward-backward manner are presented. A particularly interesting subclass of such estimators can be also viewed as hybrids of the MAP and PD estimators. Similar to previously proposed MAP-PD hybrids, the new class is parameterized by a small number of tunable parameters. Unlike their algorithmic predecessors, the new risk-based decoders are more clearly interpretable, and, most importantly, work \"out of the box\" in practice, which is demonstrated on some real bioinformatics tasks and data. Some further generalizations and applications are discussed in conclusion.", "source": "arxiv/ml"}
{"id": "arxiv:629", "title": "Adapting to the Shifting Intent of Search Queries", "text": "Search engines today present results that are often oblivious to abrupt shifts in intent. For example, the query `independence day' usually refers to a US holiday, but the intent of this query abruptly changed during the release of a major film by that name. While no studies exactly quantify the magnitude of intent-shifting traffic, studies suggest that news events, seasonal topics, pop culture, etc account for 50% of all search queries. This paper shows that the signals a search engine receives can be used to both determine that a shift in intent has happened, as well as find a result that is now more relevant. We present a meta-algorithm that marries a classifier with a bandit algorithm to achieve regret that depends logarithmically on the number of query impressions, under certain assumptions. We provide strong evidence that this regret is close to the best achievable. Finally, via a series of experiments, we demonstrate that our algorithm outperforms prior approaches, particularly as the amount of intent-shifting traffic increases.", "source": "arxiv/ml"}
{"id": "arxiv:630", "title": "CHR(PRISM)-based Probabilistic Logic Learning", "text": "PRISM is an extension of Prolog with probabilistic predicates and built-in support for expectation-maximization learning. Constraint Handling Rules (CHR) is a high-level programming language based on multi-headed multiset rewrite rules. In this paper, we introduce a new probabilistic logic formalism, called CHRiSM, based on a combination of CHR and PRISM. It can be used for high-level rapid prototyping of complex statistical models by means of \"chance rules\". The underlying PRISM system can then be used for several probabilistic inference tasks, including probability computation and parameter learning. We define the CHRiSM language in terms of syntax and operational semantics, and illustrate it with examples. We define the notion of ambiguous programs and define a distribution semantics for unambiguous programs. Next, we describe an implementation of CHRiSM, based on CHR(PRISM). We discuss the relation between CHRiSM and other probabilistic logic programming languages, in particular PCHR. Finally we identify potential application domains.", "source": "arxiv/ml"}
{"id": "arxiv:631", "title": "Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress", "text": "Recently, applying the novel data mining techniques for evaluating enterprise financial distress has received much research alternation. Support Vector Machine (SVM) and back propagation neural (BPN) network has been applied successfully in many areas with excellent generalization results, such as rule extraction, classification and evaluation. In this paper, a model based on SVM with Gaussian RBF kernel is proposed here for enterprise financial distress evaluation. BPN network is considered one of the simplest and are most general methods used for supervised training of multilayered neural network. The comparative results show that through the difference between the performance measures is marginal; SVM gives higher precision and lower error rates.", "source": "arxiv/ml"}
{"id": "arxiv:632", "title": "Close Clustering Based Automated Color Image Annotation", "text": "Most image-search approaches today are based on the text based tags associated with the images which are mostly human generated and are subject to various kinds of errors. The results of a query to the image database thus can often be misleading and may not satisfy the requirements of the user. In this work we propose our approach to automate this tagging process of images, where image results generated can be fine filtered based on a probabilistic tagging mechanism. We implement a tool which helps to automate the tagging process by maintaining a training database, wherein the system is trained to identify certain set of input images, the results generated from which are used to create a probabilistic tagging mechanism. Given a certain set of segments in an image it calculates the probability of presence of particular keywords. This probability table is further used to generate the candidate tags for input images.", "source": "arxiv/ml"}
{"id": "arxiv:633", "title": "Bounded Coordinate-Descent for Biological Sequence Classification in High Dimensional Predictor Space", "text": "We present a framework for discriminative sequence classification where the learner works directly in the high dimensional predictor space of all subsequences in the training set. This is possible by employing a new coordinate-descent algorithm coupled with bounding the magnitude of the gradient for selecting discriminative subsequences fast. We characterize the loss functions for which our generic learning algorithm can be applied and present concrete implementations for logistic regression (binomial log-likelihood loss) and support vector machines (squared hinge loss). Application of our algorithm to protein remote homology detection and remote fold recognition results in performance comparable to that of state-of-the-art methods (e.g., kernel support vector machines). Unlike state-of-the-art classifiers, the resulting classification models are simply lists of weighted discriminative subsequences and can thus be interpreted and related to the biological problem.", "source": "arxiv/ml"}
{"id": "arxiv:634", "title": "Semi-Supervised Kernel PCA", "text": "We present three generalisations of Kernel Principal Components Analysis (KPCA) which incorporate knowledge of the class labels of a subset of the data points. The first, MV-KPCA, penalises within class variances similar to Fisher discriminant analysis. The second, LSKPCA is a hybrid of least squares regression and kernel PCA. The final LR-KPCA is an iteratively reweighted version of the previous which achieves a sigmoid loss function on the labeled points. We provide a theoretical risk bound as well as illustrative experiments on real and toy data sets.", "source": "arxiv/ml"}
{"id": "arxiv:635", "title": "Separate Training for Conditional Random Fields Using Co-occurrence Rate Factorization", "text": "The standard training method of Conditional Random Fields (CRFs) is very slow for large-scale applications. As an alternative, piecewise training divides the full graph into pieces, trains them independently, and combines the learned weights at test time. In this paper, we present \\emph{separate} training for undirected models based on the novel Co-occurrence Rate Factorization (CR-F). Separate training is a local training method. In contrast to MEMMs, separate training is unaffected by the label bias problem. Experiments show that separate training (i) is unaffected by the label bias problem; (ii) reduces the training time from weeks to seconds; and (iii) obtains competitive results to the standard and piecewise training on linear-chain CRFs.", "source": "arxiv/ml"}
{"id": "arxiv:636", "title": "A Learning Algorithm based on High School Teaching Wisdom", "text": "A learning algorithm based on primary school teaching and learning is presented. The methodology is to continuously evaluate a student and to give them training on the examples for which they repeatedly fail, until, they can correctly answer all types of questions. This incremental learning procedure produces better learning curves by demanding the student to optimally dedicate their learning time on the failed examples. When used in machine learning, the algorithm is found to train a machine on a data with maximum variance in the feature space so that the generalization ability of the network improves. The algorithm has interesting applications in data mining, model evaluations and rare objects discovery.", "source": "arxiv/ml"}
{"id": "arxiv:637", "title": "Submodular Functions: Learnability, Structure, and Optimization", "text": "Submodular functions are discrete functions that model laws of diminishing returns and enjoy numerous algorithmic applications. They have been used in many areas, including combinatorial optimization, machine learning, and economics. In this work we study submodular functions from a learning theoretic angle. We provide algorithms for learning submodular functions, as well as lower bounds on their learnability. In doing so, we uncover several novel structural results revealing ways in which submodular functions can be both surprisingly structured and surprisingly unstructured. We provide several concrete implications of our work in other domains including algorithmic game theory and combinatorial optimization. At a technical level, this research combines ideas from many areas, including learning theory (distributional learning and PAC-style analyses), combinatorics and optimization (matroids and submodular functions), and pseudorandomness (lossless expander graphs).", "source": "arxiv/ml"}
{"id": "arxiv:638", "title": "Learning Functions of Few Arbitrary Linear Parameters in High Dimensions", "text": "Let us assume that $f$ is a continuous function defined on the unit ball of $\\mathbb R^d$, of the form $f(x) = g (A x)$, where $A$ is a $k \\times d$ matrix and $g$ is a function of $k$ variables for $k \\ll d$. We are given a budget $m \\in \\mathbb N$ of possible point evaluations $f(x_i)$, $i=1,...,m$, of $f$, which we are allowed to query in order to construct a uniform approximating function. Under certain smoothness and variation assumptions on the function $g$, and an {\\it arbitrary} choice of the matrix $A$, we present in this paper 1. a sampling choice of the points $\\{x_i\\}$ drawn at random for each function approximation; 2. algorithms (Algorithm 1 and Algorithm 2) for computing the approximating function, whose complexity is at most polynomial in the dimension $d$ and in the number $m$ of points. Due to the arbitrariness of $A$, the choice of the sampling points will be according to suitable random distributions and our results hold with overwhelming probability. Our approach uses tools taken from the {\\it compressed sensing} framework, recent Chernoff bounds for sums of positive-semidefinite matrices, and classical stability bounds for invariant subspaces of singular value decompositions.", "source": "arxiv/ml"}
{"id": "arxiv:639", "title": "Polynomial-Time Approximation Schemes for Knapsack and Related Counting Problems using Branching Programs", "text": "We give a deterministic, polynomial-time algorithm for approximately counting the number of {0,1}-solutions to any instance of the knapsack problem. On an instance of length n with total weight W and accuracy parameter eps, our algorithm produces a (1 + eps)-multiplicative approximation in time poly(n,log W,1/eps). We also give algorithms with identical guarantees for general integer knapsack, the multidimensional knapsack problem (with a constant number of constraints) and for contingency tables (with a constant number of rows). Previously, only randomized approximation schemes were known for these problems due to work by Morris and Sinclair and work by Dyer. Our algorithms work by constructing small-width, read-once branching programs for approximating the underlying solution space under a carefully chosen distribution. As a byproduct of this approach, we obtain new query algorithms for learning functions of k halfspaces with respect to the uniform distribution on {0,1}^n. The running time of our algorithm is polynomial in the accuracy parameter eps. Previously even for the case of k=2, only algorithms with an exponential dependence on eps were known.", "source": "arxiv/ml"}
{"id": "arxiv:640", "title": "Ultrametric and Generalized Ultrametric in Computational Logic and in Data Analysis", "text": "Following a review of metric, ultrametric and generalized ultrametric, we review their application in data analysis. We show how they allow us to explore both geometry and topology of information, starting with measured data. Some themes are then developed based on the use of metric, ultrametric and generalized ultrametric in logic. In particular we study approximation chains in an ultrametric or generalized ultrametric context. Our aim in this work is to extend the scope of data analysis by facilitating reasoning based on the data analysis; and to show how quantitative and qualitative data analysis can be incorporated into logic programming.", "source": "arxiv/ml"}
{"id": "arxiv:641", "title": "Belief Propagation Algorithm for Portfolio Optimization Problems", "text": "The typical behavior of optimal solutions to portfolio optimization problems with absolute deviation and expected shortfall models using replica analysis was pioneeringly estimated by S. Ciliberti and M. M\\'ezard [Eur. Phys. B. 57, 175 (2007)]; however, they have not yet developed an approximate derivation method for finding the optimal portfolio with respect to a given return set. In this study, an approximation algorithm based on belief propagation for the portfolio optimization problem is presented using the Bethe free energy formalism, and the consistency of the numerical experimental results of the proposed algorithm with those of replica analysis is confirmed. Furthermore, the conjecture of H. Konno and H. Yamazaki, that the optimal solutions with the absolute deviation model and with the mean-variance model have the same typical behavior, is verified using replica analysis and the belief propagation algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:642", "title": "Approximate Judgement Aggregation", "text": "In this paper we analyze judgement aggregation problems in which a group of agents independently votes on a set of complex propositions that has some interdependency constraint between them(e.g., transitivity when describing preferences). We consider the issue of judgement aggregation from the perspective of approximation. That is, we generalize the previous results by studying approximate judgement aggregation. We relax the main two constraints assumed in the current literature, Consistency and Independence and consider mechanisms that only approximately satisfy these constraints, that is, satisfy them up to a small portion of the inputs. The main question we raise is whether the relaxation of these notions significantly alters the class of satisfying aggregation mechanisms. The recent works for preference aggregation of Kalai, Mossel, and Keller fit into this framework. The main result of this paper is that, as in the case of preference aggregation, in the case of a subclass of a natural class of aggregation problems termed `truth-functional agendas', the set of satisfying aggregation mechanisms does not extend non-trivially when relaxing the constraints. Our proof techniques involve Boolean Fourier transform and analysis of voter influences for voting protocols. The question we raise for Approximate Aggregation can be stated in terms of Property Testing. For instance, as a corollary from our result we get a generalization of the classic result for property testing of linearity of Boolean functions. An updated version (RePEc:huj:dispap:dp574R) is available at http://www.ratio.huji.ac.il/dp_files/dp574R.pdf", "source": "arxiv/ml"}
{"id": "arxiv:643", "title": "NESVM: a Fast Gradient Method for Support Vector Machines", "text": "Support vector machines (SVMs) are invaluable tools for many practical applications in artificial intelligence, e.g., classification and event recognition. However, popular SVM solvers are not sufficiently efficient for applications with a great deal of samples as well as a large number of features. In this paper, thus, we present NESVM, a fast gradient SVM solver that can optimize various SVM models, e.g., classical SVM, linear programming SVM and least square SVM. Compared against SVM-Perf \\cite{SVM_Perf}\\cite{PerfML} (its convergence rate in solving the dual SVM is upper bounded by $\\mathcal O(1/\\sqrt{k})$, wherein $k$ is the number of iterations.) and Pegasos \\cite{Pegasos} (online SVM that converges at rate $\\mathcal O(1/k)$ for the primal SVM), NESVM achieves the optimal convergence rate at $\\mathcal O(1/k^{2})$ and a linear time complexity. In particular, NESVM smoothes the non-differentiable hinge loss and $\\ell_1$-norm in the primal SVM. Then the optimal gradient method without any line search is adopted to solve the optimization. In each iteration round, the current gradient and historical gradients are combined to determine the descent direction, while the Lipschitz constant determines the step size. Only two matrix-vector multiplications are required in each iteration round. Therefore, NESVM is more efficient than existing SVM solvers. In addition, NESVM is available for both linear and nonlinear kernels. We also propose \"homotopy NESVM\" to accelerate NESVM by dynamically decreasing the smooth parameter and using the continuation method. Our experiments on census income categorization, indoor/outdoor scene classification, event recognition and scene recognition suggest the efficiency and the effectiveness of NESVM. The MATLAB code of NESVM will be available on our website for further assessment.", "source": "arxiv/ml"}
{"id": "arxiv:644", "title": "Structured sparsity-inducing norms through submodular functions", "text": "Sparse methods for supervised learning aim at finding good linear predictors from as few variables as possible, i.e., with small cardinality of their supports. This combinatorial selection problem is often turned into a convex optimization problem by replacing the cardinality function by its convex envelope (tightest convex lower bound), in this case the L1-norm. In this paper, we investigate more general set-functions than the cardinality, that may incorporate prior knowledge or structural constraints which are common in many applications: namely, we show that for nondecreasing submodular set-functions, the corresponding convex envelope can be obtained from its \\lova extension, a common tool in submodular analysis. This defines a family of polyhedral norms, for which we provide generic algorithmic tools (subgradients and proximal operators) and theoretical results (conditions for support recovery or high-dimensional inference). By selecting specific submodular functions, we can give a new interpretation to known norms, such as those based on rank-statistics or grouped norms with potentially overlapping groups; we also define new norms, in particular ones that can be used as non-factorial priors for supervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:645", "title": "Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm", "text": "In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. We present some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on past losses of the experts. New notions of a volume and a scaled fluctuation of a game are introduced. We present a probabilistic algorithm protected from unrestrictedly large one-step losses. This algorithm has the optimal performance in the case when the scaled fluctuations of one-step losses of experts of the pool tend to zero.", "source": "arxiv/ml"}
{"id": "arxiv:646", "title": "Structural Solutions to Dynamic Scheduling for Multimedia Transmission in Unknown Wireless Environments", "text": "In this paper, we propose a systematic solution to the problem of scheduling delay-sensitive media data for transmission over time-varying wireless channels. We first formulate the dynamic scheduling problem as a Markov decision process (MDP) that explicitly considers the users' heterogeneous multimedia data characteristics (e.g. delay deadlines, distortion impacts and dependencies etc.) and time-varying channel conditions, which are not simultaneously considered in state-of-the-art packet scheduling algorithms. This formulation allows us to perform foresighted decisions to schedule multiple data units for transmission at each time in order to optimize the long-term utilities of the multimedia applications. The heterogeneity of the media data enables us to express the transmission priorities between the different data units as a priority graph, which is a directed acyclic graph (DAG). This priority graph provides us with an elegant structure to decompose the multi-data unit foresighted decision at each time into multiple single-data unit foresighted decisions which can be performed sequentially, from the high priority data units to the low priority data units, thereby significantly reducing the computation complexity. When the statistical knowledge of the multimedia data characteristics and channel conditions is unknown a priori, we develop a low-complexity online learning algorithm to update the value functions which capture the impact of the current decision on the future utility. The simulation results show that the proposed solution significantly outperforms existing state-of-the-art scheduling solutions.", "source": "arxiv/ml"}
{"id": "arxiv:647", "title": "Switching between Hidden Markov Models using Fixed Share", "text": "In prediction with expert advice the goal is to design online prediction algorithms that achieve small regret (additional loss on the whole data) compared to a reference scheme. In the simplest such scheme one compares to the loss of the best expert in hindsight. A more ambitious goal is to split the data into segments and compare to the best expert on each segment. This is appropriate if the nature of the data changes between segments. The standard fixed-share algorithm is fast and achieves small regret compared to this scheme. Fixed share treats the experts as black boxes: there are no assumptions about how they generate their predictions. But if the experts are learning, the following question arises: should the experts learn from all data or only from data in their own segment? The original algorithm naturally addresses the first case. Here we consider the second option, which is more appropriate exactly when the nature of the data changes between segments. In general extending fixed share to this second case will slow it down by a factor of T on T outcomes. We show, however, that no such slowdown is necessary if the experts are hidden Markov models.", "source": "arxiv/ml"}
{"id": "arxiv:648", "title": "Freezing and Sleeping: Tracking Experts that Learn by Evolving Past Posteriors", "text": "A problem posed by Freund is how to efficiently track a small pool of experts out of a much larger set. This problem was solved when Bousquet and Warmuth introduced their mixing past posteriors (MPP) algorithm in 2001. In Freund's problem the experts would normally be considered black boxes. However, in this paper we re-examine Freund's problem in case the experts have internal structure that enables them to learn. In this case the problem has two possible interpretations: should the experts learn from all data or only from the subsequence on which they are being tracked? The MPP algorithm solves the first case. Our contribution is to generalise MPP to address the second option. The results we obtain apply to any expert structure that can be formalised using (expert) hidden Markov models. Curiously enough, for our interpretation there are \\emph{two} natural reference schemes: freezing and sleeping. For each scheme, we provide an efficient prediction strategy and prove the relevant loss bound.", "source": "arxiv/ml"}
{"id": "arxiv:649", "title": "An Architecture of Active Learning SVMs with Relevance Feedback for Classifying E-mail", "text": "In this paper, we have proposed an architecture of active learning SVMs with relevance feedback (RF)for classifying e-mail. This architecture combines both active learning strategies where instead of using a randomly selected training set, the learner has access to a pool of unlabeled instances and can request the labels of some number of them and relevance feedback where if any mail misclassified then the next set of support vectors will be different from the present set otherwise the next set will not change. Our proposed architecture will ensure that a legitimate e-mail will not be dropped in the event of overflowing mailbox. The proposed architecture also exhibits dynamic updating characteristics making life as difficult for the spammer as possible.", "source": "arxiv/ml"}
{"id": "arxiv:650", "title": "Entropy-Based Search Algorithm for Experimental Design", "text": "The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about the models to select the most relevant experiment. Optimizing inquiry involves searching the parameterized space of experiments to select the experiment that promises, on average, to be maximally informative. In the case where it is important to learn about each of the model parameters, the relevance of an experiment is quantified by Shannon entropy of the distribution of experimental outcomes predicted by a probable set of models. If the set of potential experiments is described by many parameters, we must search this high-dimensional entropy space. Brute force search methods will be slow and computationally expensive. We present an entropy-based search algorithm, called nested entropy sampling, to select the most informative experiment for efficient experimental design. This algorithm is inspired by Skilling's nested sampling algorithm used in inference and borrows the concept of a rising threshold while a set of experiment samples are maintained. We demonstrate that this algorithm not only selects highly relevant experiments, but also is more efficient than brute force search. Such entropic search techniques promise to greatly benefit autonomous experimental design.", "source": "arxiv/ml"}
{"id": "arxiv:651", "title": "Prediction by Compression", "text": "It is well known that text compression can be achieved by predicting the next symbol in the stream of text data based on the history seen up to the current symbol. The better the prediction the more skewed the conditional probability distribution of the next symbol and the shorter the codeword that needs to be assigned to represent this next symbol. What about the opposite direction ? suppose we have a black box that can compress text stream. Can it be used to predict the next symbol in the stream ? We introduce a criterion based on the length of the compressed data and use it to predict the next symbol. We examine empirically the prediction error rate and its dependency on some compression parameters.", "source": "arxiv/ml"}
{"id": "arxiv:652", "title": "Fixed-point and coordinate descent algorithms for regularized kernel methods", "text": "In this paper, we study two general classes of optimization algorithms for kernel methods with convex loss function and quadratic norm regularization, and analyze their convergence. The first approach, based on fixed-point iterations, is simple to implement and analyze, and can be easily parallelized. The second, based on coordinate descent, exploits the structure of additively separable loss functions to compute solutions of line searches in closed form. Instances of these general classes of algorithms are already incorporated into state of the art machine learning software for large scale problems. We start from a solution characterization of the regularized problem, obtained using sub-differential calculus and resolvents of monotone operators, that holds for general convex loss functions regardless of differentiability. The two methodologies described in the paper can be regarded as instances of non-linear Jacobi and Gauss-Seidel algorithms, and are both well-suited to solve large scale problems.", "source": "arxiv/ml"}
{"id": "arxiv:653", "title": "Indexability, concentration, and VC theory", "text": "Degrading performance of indexing schemes for exact similarity search in high dimensions has long since been linked to histograms of distributions of distances and other 1-Lipschitz functions getting concentrated. We discuss this observation in the framework of the phenomenon of concentration of measure on the structures of high dimension and the Vapnik-Chervonenkis theory of statistical learning.", "source": "arxiv/ml"}
{"id": "arxiv:654", "title": "Memristor Crossbar-based Hardware Implementation of IDS Method", "text": "Ink Drop Spread (IDS) is the engine of Active Learning Method (ALM), which is the methodology of soft computing. IDS, as a pattern-based processing unit, extracts useful information from a system subjected to modeling. In spite of its excellent potential in solving problems such as classification and modeling compared to other soft computing tools, finding its simple and fast hardware implementation is still a challenge. This paper describes a new hardware implementation of IDS method based on the memristor crossbar structure. In addition of simplicity, being completely real-time, having low latency and the ability to continue working after the occurrence of power breakdown are some of the advantages of our proposed circuit.", "source": "arxiv/ml"}
{"id": "arxiv:655", "title": "A Smoothing Stochastic Gradient Method for Composite Optimization", "text": "We consider the unconstrained optimization problem whose objective function is composed of a smooth and a non-smooth conponents where the smooth component is the expectation a random function. This type of problem arises in some interesting applications in machine learning. We propose a stochastic gradient descent algorithm for this class of optimization problem. When the non-smooth component has a particular structure, we propose another stochastic gradient descent algorithm by incorporating a smoothing method into our first algorithm. The proofs of the convergence rates of these two algorithms are given and we show the numerical performance of our algorithm by applying them to regularized linear regression problems with different sets of synthetic data.", "source": "arxiv/ml"}
{"id": "arxiv:656", "title": "Network Flow Algorithms for Structured Sparsity", "text": "We consider a class of learning problems that involve a structured sparsity-inducing norm defined as the sum of $\\ell_\\infty$-norms over groups of variables. Whereas a lot of effort has been put in developing fast optimization methods when the groups are disjoint or embedded in a specific hierarchical structure, we address here the case of general overlapping groups. To this end, we show that the corresponding optimization problem is related to network flow optimization. More precisely, the proximal problem associated with the norm we consider is dual to a quadratic min-cost flow problem. We propose an efficient procedure which computes its solution exactly in polynomial time. Our algorithm scales up to millions of variables, and opens up a whole new range of applications for structured sparse models. We present several experiments on image and video data, demonstrating the applicability and scalability of our approach for various problems.", "source": "arxiv/ml"}
{"id": "arxiv:657", "title": "The adaptive projected subgradient method constrained by families of quasi-nonexpansive mappings and its application to online learning", "text": "Many online, i.e., time-adaptive, inverse problems in signal processing and machine learning fall under the wide umbrella of the asymptotic minimization of a sequence of non-negative, convex, and continuous functions. To incorporate a-priori knowledge into the design, the asymptotic minimization task is usually constrained on a fixed closed convex set, which is dictated by the available a-priori information. To increase versatility towards the usage of the available information, the present manuscript extends the Adaptive Projected Subgradient Method (APSM) by introducing an algorithmic scheme which incorporates a-priori knowledge in the design via a sequence of strongly attracting quasi-nonexpansive mappings in a real Hilbert space. In such a way, the benefits offered to online learning tasks by the proposed method unfold in two ways: 1) the rich class of quasi-nonexpansive mappings provides a plethora of ways to cast a-priori knowledge, and 2) by introducing a sequence of such mappings, the proposed scheme is able to capture the time-varying nature of a-priori information. The convergence properties of the algorithm are studied, several special cases of the method with wide applicability are shown, and the potential of the proposed scheme is demonstrated by considering an increasingly important, nowadays, online sparse system/signal recovery task.", "source": "arxiv/ml"}
{"id": "arxiv:658", "title": "Inference with Multivariate Heavy-Tails in Linear Models", "text": "Heavy-tailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closed-form in graphical models which involve such heavy-tailed distributions. In this work, we propose a novel simple linear graphical model for independent latent random variables, called linear characteristic model (LCM), defined in the characteristic function domain. Using stable distributions, a heavy-tailed family of distributions which is a generalization of Cauchy, L\\'evy and Gaussian distributions, we show for the first time, how to compute both exact and approximate inference in such a linear multivariate graphical model. LCMs are not limited to stable distributions, in fact LCMs are always defined for any random variables (discrete, continuous or a mixture of both). We provide a realistic problem from the field of computer networks to demonstrate the applicability of our construction. Other potential application is iterative decoding of linear channels with non-Gaussian noise.", "source": "arxiv/ml"}
{"id": "arxiv:659", "title": "Penalty Decomposition Methods for $L0$-Norm Minimization", "text": "In this paper we consider general l0-norm minimization problems, that is, the problems with l0-norm appearing in either objective function or constraint. In particular, we first reformulate the l0-norm constrained problem as an equivalent rank minimization problem and then apply the penalty decomposition (PD) method proposed in [33] to solve the latter problem. By utilizing the special structures, we then transform all matrix operations of this method to vector operations and obtain a PD method that only involves vector operations. Under some suitable assumptions, we establish that any accumulation point of the sequence generated by the PD method satisfies a first-order optimality condition that is generally stronger than one natural optimality condition. We further extend the PD method to solve the problem with the l0-norm appearing in objective function. Finally, we test the performance of our PD methods by applying them to compressed sensing, sparse logistic regression and sparse inverse covariance selection. The computational results demonstrate that our methods generally outperform the existing methods in terms of solution quality and/or speed.", "source": "arxiv/ml"}
{"id": "arxiv:660", "title": "Penalty Decomposition Methods for Rank Minimization", "text": "In this paper we consider general rank minimization problems with rank appearing in either objective function or constraint. We first establish that a class of special rank minimization problems has closed-form solutions. Using this result, we then propose penalty decomposition methods for general rank minimization problems in which each subproblem is solved by a block coordinate descend method. Under some suitable assumptions, we show that any accumulation point of the sequence generated by the penalty decomposition methods satisfies the first-order optimality conditions of a nonlinear reformulation of the problems. Finally, we test the performance of our methods by applying them to the matrix completion and nearest low-rank correlation matrix problems. The computational results demonstrate that our methods are generally comparable or superior to the existing methods in terms of solution quality.", "source": "arxiv/ml"}
{"id": "arxiv:661", "title": "Mixed Cumulative Distribution Networks", "text": "Directed acyclic graphs (DAGs) are a popular framework to express multivariate probability distributions. Acyclic directed mixed graphs (ADMGs) are generalizations of DAGs that can succinctly capture much richer sets of conditional independencies, and are especially useful in modeling the effects of latent variables implicitly. Unfortunately there are currently no good parameterizations of general ADMGs. In this paper, we apply recent work on cumulative distribution networks and copulas to propose one one general construction for ADMG models. We consider a simple parameter estimation approach, and report some encouraging experimental results.", "source": "arxiv/ml"}
{"id": "arxiv:662", "title": "Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism", "text": "Post-genomic research deals with challenging problems in screening genomes of organisms for particular functions or potential for being the targets of genetic engineering for desirable biological features. 'Phenotyping' of wild type and mutants is a time-consuming and costly effort by many individuals. This article is a preliminary progress report in research on large-scale automation of phenotyping steps (imaging, informatics and data analysis) needed to study plant gene-proteins networks that influence growth and development of plants. Our results undermine the significance of phenotypic traits that are implicit in patterns of dynamics in plant root response to sudden changes of its environmental conditions, such as sudden re-orientation of the root tip against the gravity vector. Including dynamic features besides the common morphological ones has paid off in design of robust and accurate machine learning methods to automate a typical phenotyping scenario, i.e. to distinguish the wild type from the mutants.", "source": "arxiv/ml"}
{"id": "arxiv:663", "title": "Exploring Language-Independent Emotional Acoustic Features via Feature Selection", "text": "We propose a novel feature selection strategy to discover language-independent acoustic features that tend to be responsible for emotions regardless of languages, linguistics and other factors. Experimental results suggest that the language-independent feature subset discovered yields the performance comparable to the full feature set on various emotional speech corpora.", "source": "arxiv/ml"}
{"id": "arxiv:664", "title": "Fast Overlapping Group Lasso", "text": "The group Lasso is an extension of the Lasso for feature selection on (predefined) non-overlapping groups of features. The non-overlapping group structure limits its applicability in practice. There have been several recent attempts to study a more general formulation, where groups of features are given, potentially with overlaps between the groups. The resulting optimization is, however, much more challenging to solve due to the group overlaps. In this paper, we consider the efficient optimization of the overlapping group Lasso penalized problem. We reveal several key properties of the proximal operator associated with the overlapping group Lasso, and compute the proximal operator by solving the smooth and convex dual problem, which allows the use of the gradient descent type of algorithms for the optimization. We have performed empirical evaluations using the breast cancer gene expression data set, which consists of 8,141 genes organized into (overlapping) gene sets. Experimental results demonstrate the efficiency and effectiveness of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:665", "title": "A PAC-Bayesian Analysis of Graph Clustering and Pairwise Clustering", "text": "We formulate weighted graph clustering as a prediction problem: given a subset of edge weights we analyze the ability of graph clustering to predict the remaining edge weights. This formulation enables practical and theoretical comparison of different approaches to graph clustering as well as comparison of graph clustering with other possible ways to model the graph. We adapt the PAC-Bayesian analysis of co-clustering (Seldin and Tishby, 2008; Seldin, 2009) to derive a PAC-Bayesian generalization bound for graph clustering. The bound shows that graph clustering should optimize a trade-off between empirical data fit and the mutual information that clusters preserve on the graph nodes. A similar trade-off derived from information-theoretic considerations was already shown to produce state-of-the-art results in practice (Slonim et al., 2005; Yom-Tov and Slonim, 2009). This paper supports the empirical evidence by providing a better theoretical foundation, suggesting formal generalization guarantees, and offering a more accurate way to deal with finite sample issues. We derive a bound minimization algorithm and show that it provides good results in real-life problems and that the derived PAC-Bayesian bound is reasonably tight.", "source": "arxiv/ml"}
{"id": "arxiv:666", "title": "Gaussian Process Bandits for Tree Search: Theory and Application to Planning in Discounted MDPs", "text": "We motivate and analyse a new Tree Search algorithm, GPTS, based on recent theoretical advances in the use of Gaussian Processes for Bandit problems. We consider tree paths as arms and we assume the target/reward function is drawn from a GP distribution. The posterior mean and variance, after observing data, are used to define confidence intervals for the function values, and we sequentially play arms with highest upper confidence bounds. We give an efficient implementation of GPTS and we adapt previous regret bounds by determining the decay rate of the eigenvalues of the kernel matrix on the whole set of tree paths. We consider two kernels in the feature space of binary vectors indexed by the nodes of the tree: linear and Gaussian. The regret grows in square root of the number of iterations T, up to a logarithmic factor, with a constant that improves with bigger Gaussian kernel widths. We focus on practical values of T, smaller than the number of arms. Finally, we apply GPTS to Open Loop Planning in discounted Markov Decision Processes by modelling the reward as a discounted sum of independent Gaussian Processes. We report similar regret bounds to those of the OLOP algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:667", "title": "On the Estimation of Coherence", "text": "Low-rank matrix approximations are often used to help scale standard machine learning algorithms to large-scale problems. Recently, matrix coherence has been used to characterize the ability to extract global information from a subset of matrix entries in the context of these low-rank approximations and other sampling-based algorithms, e.g., matrix com- pletion, robust PCA. Since coherence is defined in terms of the singular vectors of a matrix and is expensive to compute, the practical significance of these results largely hinges on the following question: Can we efficiently and accurately estimate the coherence of a matrix? In this paper we address this question. We propose a novel algorithm for estimating coherence from a small number of columns, formally analyze its behavior, and derive a new coherence-based matrix approximation bound based on this analysis. We then present extensive experimental results on synthetic and real datasets that corroborate our worst-case theoretical analysis, yet provide strong support for the use of our proposed algorithm whenever low-rank approximation is being considered. Our algorithm efficiently and accurately estimates matrix coherence across a wide range of datasets, and these coherence estimates are excellent predictors of the effectiveness of sampling-based matrix approximation on a case-by-case basis.", "source": "arxiv/ml"}
{"id": "arxiv:668", "title": "PhishDef: URL Names Say It All", "text": "Phishing is an increasingly sophisticated method to steal personal user information using sites that pretend to be legitimate. In this paper, we take the following steps to identify phishing URLs. First, we carefully select lexical features of the URLs that are resistant to obfuscation techniques used by attackers. Second, we evaluate the classification accuracy when using only lexical features, both automatically and hand-selected, vs. when using additional features. We show that lexical features are sufficient for all practical purposes. Third, we thoroughly compare several classification algorithms, and we propose to use an online method (AROW) that is able to overcome noisy training data. Based on the insights gained from our analysis, we propose PhishDef, a phishing detection system that uses only URL names and combines the above three elements. PhishDef is a highly accurate method (when compared to state-of-the-art approaches over real datasets), lightweight (thus appropriate for online and client-side deployment), proactive (based on online classification rather than blacklists), and resilient to training data inaccuracies (thus enabling the use of large noisy training data).", "source": "arxiv/ml"}
{"id": "arxiv:669", "title": "Reinforcement Learning by Comparing Immediate Reward", "text": "This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with immediate reward of past move and work accordingly. Relative reward based Q-learning is an approach towards interactive learning. Q-Learning is a model free reinforcement learning method that used to learn the agents. It is observed that under normal circumstances algorithm take more episodes to reach optimal Q-value due to its normal reward or sometime negative reward. In this new form of algorithm agents select only those actions which have a higher immediate reward signal in comparison to previous one. The contribution of this article is the presentation of new Q-Learning Algorithm in order to maximize the performance of algorithm and reduce the number of episode required to reach optimal Q-value. Effectiveness of proposed algorithm is simulated in a 20 x20 Grid world deterministic environment and the result for the two forms of Q-Learning Algorithms is given.", "source": "arxiv/ml"}
{"id": "arxiv:670", "title": "A Unified View of Regularized Dual Averaging and Mirror Descent with Implicit Updates", "text": "We study three families of online convex optimization algorithms: follow-the-proximally-regularized-leader (FTRL-Proximal), regularized dual averaging (RDA), and composite-objective mirror descent. We first prove equivalence theorems that show all of these algorithms are instantiations of a general FTRL update. This provides theoretical insight on previous experimental observations. In particular, even though the FOBOS composite mirror descent algorithm handles L1 regularization explicitly, it has been observed that RDA is even more effective at producing sparsity. Our results demonstrate that FOBOS uses subgradient approximations to the L1 penalty from previous rounds, leading to less sparsity than RDA, which handles the cumulative penalty in closed form. The FTRL-Proximal algorithm can be seen as a hybrid of these two, and outperforms both on a large, real-world dataset. Our second contribution is a unified analysis which produces regret bounds that match (up to logarithmic terms) or improve the best previously known bounds. This analysis also extends these algorithms in two important ways: we support a more general type of composite objective and we analyze implicit updates, which replace the subgradient approximation of the current loss function with an exact optimization.", "source": "arxiv/ml"}
{"id": "arxiv:671", "title": "Conditional Random Fields and Support Vector Machines: A Hybrid Approach", "text": "We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient condition for when the hybrid loss is Fisher consistent for classification. This condition depends on a measure of dominance between labels - specifically, the gap in per observation probabilities between the most likely labels. We also prove Fisher consistency is necessary for parametric consistency when learning models such as CRFs. We demonstrate empirically that the hybrid loss typically performs as least as well as - and often better than - both of its constituent losses on variety of tasks. In doing so we also provide an empirical comparison of the efficacy of probabilistic and margin based approaches to multiclass and structured prediction and the effects of label dominance on these results.", "source": "arxiv/ml"}
{"id": "arxiv:672", "title": "Safe Feature Elimination in Sparse Supervised Learning", "text": "We investigate fast methods that allow to quickly eliminate variables (features) in supervised learning problems involving a convex loss function and a $l_1$-norm penalty, leading to a potentially substantial reduction in the number of variables prior to running the supervised learning algorithm. The methods are not heuristic: they only eliminate features that are {\\em guaranteed} to be absent after solving the learning problem. Our framework applies to a large class of problems, including support vector machine classification, logistic regression and least-squares. The complexity of the feature elimination step is negligible compared to the typical computational effort involved in the sparse supervised learning problem: it grows linearly with the number of features times the number of examples, with much better count if data is sparse. We apply our method to data sets arising in text classification and observe a dramatic reduction of the dimensionality, hence in computational effort required to solve the learning problem, especially when very sparse classifiers are sought. Our method allows to immediately extend the scope of existing algorithms, allowing us to run them on data sets of sizes that were out of their reach before.", "source": "arxiv/ml"}
{"id": "arxiv:673", "title": "Deep Self-Taught Learning for Handwritten Character Recognition", "text": "Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained by composing multiple non-linear transformations. Self-taught learning (exploiting unlabeled examples or examples from other distributions) has already been applied to deep learners, but mostly to show the advantage of unlabeled examples. Here we explore the advantage brought by {\\em out-of-distribution examples}. For this purpose we developed a powerful generator of stochastic variations and noise processes for character images, including not only affine transformations but also slant, local elastic deformations, changes in thickness, background images, grey level changes, contrast, occlusion, and various types of noise. The out-of-distribution examples are obtained from these highly distorted images or by including examples of object classes different from those in the target test set. We show that {\\em deep learners benefit more from out-of-distribution examples than a corresponding shallow learner}, at least in the area of handwritten character recognition. In fact, we show that they beat previously published results and reach human-level performance on both handwritten digit classification and 62-class handwritten character recognition.", "source": "arxiv/ml"}
{"id": "arxiv:674", "title": "Geometric Decision Tree", "text": "In this paper we present a new algorithm for learning oblique decision trees. Most of the current decision tree algorithms rely on impurity measures to assess the goodness of hyperplanes at each node while learning a decision tree in a top-down fashion. These impurity measures do not properly capture the geometric structures in the data. Motivated by this, our algorithm uses a strategy to assess the hyperplanes in such a way that the geometric structure in the data is taken into account. At each node of the decision tree, we find the clustering hyperplanes for both the classes and use their angle bisectors as the split rule at that node. We show through empirical studies that this idea leads to small decision trees and better performance. We also present some analysis to show that the angle bisectors of clustering hyperplanes that we use as the split rules at each node, are solutions of an interesting optimization problem and hence argue that this is a principled method of learning a decision tree.", "source": "arxiv/ml"}
{"id": "arxiv:675", "title": "On the Doubt about Margin Explanation of Boosting", "text": "Margin theory provides one of the most popular explanations to the success of \\texttt{AdaBoost}, where the central point lies in the recognition that \\textit{margin} is the key for characterizing the performance of \\texttt{AdaBoost}. This theory has been very influential, e.g., it has been used to argue that \\texttt{AdaBoost} usually does not overfit since it tends to enlarge the margin even after the training error reaches zero. Previously the \\textit{minimum margin bound} was established for \\texttt{AdaBoost}, however, \\cite{Breiman1999} pointed out that maximizing the minimum margin does not necessarily lead to a better generalization. Later, \\cite{Reyzin:Schapire2006} emphasized that the margin distribution rather than minimum margin is crucial to the performance of \\texttt{AdaBoost}. In this paper, we first present the \\textit{$k$th margin bound} and further study on its relationship to previous work such as the minimum margin bound and Emargin bound. Then, we improve the previous empirical Bernstein bounds \\citep{Maurer:Pontil2009,Audibert:Munos:Szepesvari2009}, and based on such findings, we defend the margin-based explanation against Breiman's doubts by proving a new generalization error bound that considers exactly the same factors as \\cite{Schapire:Freund:Bartlett:Lee1998} but is sharper than \\cite{Breiman1999}'s minimum margin bound. By incorporating factors such as average margin and variance, we present a generalization error bound that is heavily related to the whole margin distribution. We also provide margin distribution bounds for generalization error of voting classifiers in finite VC-dimension space.", "source": "arxiv/ml"}
{"id": "arxiv:676", "title": "Totally Corrective Multiclass Boosting with Binary Weak Learners", "text": "In this work, we propose a new optimization framework for multiclass boosting learning. In the literature, AdaBoost.MO and AdaBoost.ECC are the two successful multiclass boosting algorithms, which can use binary weak learners. We explicitly derive these two algorithms' Lagrange dual problems based on their regularized loss functions. We show that the Lagrange dual formulations enable us to design totally-corrective multiclass algorithms by using the primal-dual optimization technique. Experiments on benchmark data sets suggest that our multiclass boosting can achieve a comparable generalization capability with state-of-the-art, but the convergence speed is much faster than stage-wise gradient descent boosting. In other words, the new totally corrective algorithms can maximize the margin more aggressively.", "source": "arxiv/ml"}
{"id": "arxiv:677", "title": "Structural Learning of Attack Vectors for Generating Mutated XSS Attacks", "text": "Web applications suffer from cross-site scripting (XSS) attacks that resulting from incomplete or incorrect input sanitization. Learning the structure of attack vectors could enrich the variety of manifestations in generated XSS attacks. In this study, we focus on generating more threatening XSS attacks for the state-of-the-art detection approaches that can find potential XSS vulnerabilities in Web applications, and propose a mechanism for structural learning of attack vectors with the aim of generating mutated XSS attacks in a fully automatic way. Mutated XSS attack generation depends on the analysis of attack vectors and the structural learning mechanism. For the kernel of the learning mechanism, we use a Hidden Markov model (HMM) as the structure of the attack vector model to capture the implicit manner of the attack vector, and this manner is benefited from the syntax meanings that are labeled by the proposed tokenizing mechanism. Bayes theorem is used to determine the number of hidden states in the model for generalizing the structure model. The paper has the contributions as following: (1) automatically learn the structure of attack vectors from practical data analysis to modeling a structure model of attack vectors, (2) mimic the manners and the elements of attack vectors to extend the ability of testing tool for identifying XSS vulnerabilities, (3) be helpful to verify the flaws of blacklist sanitization procedures of Web applications. We evaluated the proposed mechanism by Burp Intruder with a dataset collected from public XSS archives. The results show that mutated XSS attack generation can identify potential vulnerabilities.", "source": "arxiv/ml"}
{"id": "arxiv:678", "title": "Robust Low-Rank Subspace Segmentation with Semidefinite Guarantees", "text": "Recently there is a line of research work proposing to employ Spectral Clustering (SC) to segment (group){Throughout the paper, we use segmentation, clustering, and grouping, and their verb forms, interchangeably.} high-dimensional structural data such as those (approximately) lying on subspaces {We follow {liu2010robust} and use the term \"subspace\" to denote both linear subspaces and affine subspaces. There is a trivial conversion between linear subspaces and affine subspaces as mentioned therein.} or low-dimensional manifolds. By learning the affinity matrix in the form of sparse reconstruction, techniques proposed in this vein often considerably boost the performance in subspace settings where traditional SC can fail. Despite the success, there are fundamental problems that have been left unsolved: the spectrum property of the learned affinity matrix cannot be gauged in advance, and there is often one ugly symmetrization step that post-processes the affinity for SC input. Hence we advocate to enforce the symmetric positive semidefinite constraint explicitly during learning (Low-Rank Representation with Positive SemiDefinite constraint, or LRR-PSD), and show that factually it can be solved in an exquisite scheme efficiently instead of general-purpose SDP solvers that usually scale up poorly. We provide rigorous mathematical derivations to show that, in its canonical form, LRR-PSD is equivalent to the recently proposed Low-Rank Representation (LRR) scheme {liu2010robust}, and hence offer theoretic and practical insights to both LRR-PSD and LRR, inviting future research. As per the computational cost, our proposal is at most comparable to that of LRR, if not less. We validate our theoretic analysis and optimization scheme by experiments on both synthetic and real data sets.", "source": "arxiv/ml"}
{"id": "arxiv:679", "title": "Optimistic Rates for Learning with a Smooth Loss", "text": "We establish an excess risk bound of O(H R_n^2 + R_n \\sqrt{H L*}) for empirical risk minimization with an H-smooth loss function and a hypothesis class with Rademacher complexity R_n, where L* is the best risk achievable by the hypothesis class. For typical hypothesis classes where R_n = \\sqrt{R/n}, this translates to a learning rate of O(RH/n) in the separable (L*=0) case and O(RH/n + \\sqrt{L^* RH/n}) more generally. We also provide similar guarantees for online and stochastic convex optimization with a smooth non-negative objective.", "source": "arxiv/ml"}
{"id": "arxiv:680", "title": "Approximate Inference and Stochastic Optimal Control", "text": "We propose a novel reformulation of the stochastic optimal control problem as an approximate inference problem, demonstrating, that such a interpretation leads to new practical methods for the original problem. In particular we characterise a novel class of iterative solutions to the stochastic optimal control problem based on a natural relaxation of the exact dual formulation. These theoretical insights are applied to the Reinforcement Learning problem where they lead to new model free, off policy methods for discrete and continuous problems.", "source": "arxiv/ml"}
{"id": "arxiv:681", "title": "Safe Feature Elimination for the LASSO and Sparse Supervised Learning Problems", "text": "We describe a fast method to eliminate features (variables) in l1 -penalized least-square regression (or LASSO) problems. The elimination of features leads to a potentially substantial reduction in running time, specially for large values of the penalty parameter. Our method is not heuristic: it only eliminates features that are guaranteed to be absent after solving the LASSO problem. The feature elimination step is easy to parallelize and can test each feature for elimination independently. Moreover, the computational effort of our method is negligible compared to that of solving the LASSO problem - roughly it is the same as single gradient step. Our method extends the scope of existing LASSO algorithms to treat larger data sets, previously out of their reach. We show how our method can be extended to general l1 -penalized convex problems and present preliminary results for the Sparse Support Vector Machine and Logistic Regression problems.", "source": "arxiv/ml"}
{"id": "arxiv:682", "title": "A hybrid learning algorithm for text classification", "text": "Text classification is the process of classifying documents into predefined categories based on their content. Existing supervised learning algorithms to automatically classify text need sufficient documents to learn accurately. This paper presents a new algorithm for text classification that requires fewer documents for training. Instead of using words, word relation i.e association rules from these words is used to derive feature set from preclassified text documents. The concept of Naive Bayes classifier is then used on derived features and finally only a single concept of Genetic Algorithm has been added for final classification. Experimental results show that the classifier build this way is more accurate than the existing text classification systems.", "source": "arxiv/ml"}
{"id": "arxiv:683", "title": "Text Classification using the Concept of Association Rule of Data Mining", "text": "As the amount of online text increases, the demand for text classification to aid the analysis and management of text is increasing. Text is cheap, but information, in the form of knowing what classes a text belongs to, is expensive. Automatic classification of text can provide this information at low cost, but the classifiers themselves must be built with expensive human effort, or trained from texts which have themselves been manually classified. In this paper we will discuss a procedure of classifying text using the concept of association rule of data mining. Association rule mining technique has been used to derive feature set from pre-classified text documents. Naive Bayes classifier is then used on derived features for final classification.", "source": "arxiv/ml"}
{"id": "arxiv:684", "title": "A Fast Audio Clustering Using Vector Quantization and Second Order Statistics", "text": "This paper describes an effective unsupervised speaker indexing approach. We suggest a two stage algorithm to speed-up the state-of-the-art algorithm based on the Bayesian Information Criterion (BIC). In the first stage of the merging process a computationally cheap method based on the vector quantization (VQ) is used. Then in the second stage a more computational expensive technique based on the BIC is applied. In the speaker indexing task a turning parameter or a threshold is used. We suggest an on-line procedure to define the value of a turning parameter without using development data. The results are evaluated using 10 hours of audio data.", "source": "arxiv/ml"}
{"id": "arxiv:685", "title": "Efficient L1/Lq Norm Regularization", "text": "Sparse learning has recently received increasing attention in many areas including machine learning, statistics, and applied mathematics. The mixed-norm regularization based on the L1/Lq norm with q > 1 is attractive in many applications of regression and classification in that it facilitates group sparsity in the model. The resulting optimization problem is, however, challenging to solve due to the structure of the L1/Lq -regularization. Existing work deals with special cases including q = 2,infinity, and they cannot be easily extended to the general case. In this paper, we propose an efficient algorithm based on the accelerated gradient method for solving the L1/Lq -regularized problem, which is applicable for all values of q larger than 1, thus significantly extending existing work. One key building block of the proposed algorithm is the L1/Lq -regularized Euclidean projection (EP1q). Our theoretical analysis reveals the key properties of EP1q and illustrates why EP1q for the general q is significantly more challenging to solve than the special cases. Based on our theoretical analysis, we develop an efficient algorithm for EP1q by solving two zero finding problems. Experimental results demonstrate the efficiency of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:686", "title": "Multi-parametric Solution-path Algorithm for Instance-weighted Support Vector Machines", "text": "An instance-weighted variant of the support vector machine (SVM) has attracted considerable attention recently since they are useful in various machine learning tasks such as non-stationary data analysis, heteroscedastic data modeling, transfer learning, learning to rank, and transduction. An important challenge in these scenarios is to overcome the computational bottleneck---instance weights often change dynamically or adaptively, and thus the weighted SVM solutions must be repeatedly computed. In this paper, we develop an algorithm that can efficiently and exactly update the weighted SVM solutions for arbitrary change of instance weights. Technically, this contribution can be regarded as an extension of the conventional solution-path algorithm for a single regularization parameter to multiple instance-weight parameters. However, this extension gives rise to a significant problem that breakpoints (at which the solution path turns) have to be identified in high-dimensional space. To facilitate this, we introduce a parametric representation of instance weights. We also provide a geometric interpretation in weight space using a notion of critical region: a polyhedron in which the current affine solution remains to be optimal. Then we find breakpoints at intersections of the solution path and boundaries of polyhedrons. Through extensive experiments on various practical applications, we demonstrate the usefulness of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:687", "title": "Speaker Identification using MFCC-Domain Support Vector Machine", "text": "Speech recognition and speaker identification are important for authentication and verification in security purpose, but they are difficult to achieve. Speaker identification methods can be divided into text-independent and text-dependent. This paper presents a technique of text-dependent speaker identification using MFCC-domain support vector machine (SVM). In this work, melfrequency cepstrum coefficients (MFCCs) and their statistical distribution properties are used as features, which will be inputs to the neural network. This work firstly used sequential minimum optimization (SMO) learning technique for SVM that improve performance over traditional techniques Chunking, Osuna. The cepstrum coefficients representing the speaker characteristics of a speech segment are computed by nonlinear filter bank analysis and discrete cosine transform. The speaker identification ability and convergence speed of the SVMs are investigated for different combinations of features. Extensive experimental results on several samples show the effectiveness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:688", "title": "Text Classification using Association Rule with a Hybrid Concept of Naive Bayes Classifier and Genetic Algorithm", "text": "Text classification is the automated assignment of natural language texts to predefined categories based on their content. Text classification is the primary requirement of text retrieval systems, which retrieve texts in response to a user query, and text understanding systems, which transform text in some way such as producing summaries, answering questions or extracting data. Now a day the demand of text classification is increasing tremendously. Keeping this demand into consideration, new and updated techniques are being developed for the purpose of automated text classification. This paper presents a new algorithm for text classification. Instead of using words, word relation i.e. association rules is used to derive feature set from pre-classified text documents. The concept of Naive Bayes Classifier is then used on derived features and finally a concept of Genetic Algorithm has been added for final classification. A system based on the proposed algorithm has been implemented and tested. The experimental results show that the proposed system works as a successful text classifier.", "source": "arxiv/ml"}
{"id": "arxiv:689", "title": "Portfolio Allocation for Bayesian Optimization", "text": "Bayesian optimization with Gaussian processes has become an increasingly popular tool in the machine learning community. It is efficient and can be used when very little is known about the objective function, making it popular in expensive black-box optimization scenarios. It uses Bayesian methods to sample the objective efficiently using an acquisition function which incorporates the model's estimate of the objective and the uncertainty at any given point. However, there are several different parameterized acquisition functions in the literature, and it is often unclear which one to use. Instead of using a single acquisition function, we adopt a portfolio of acquisition functions governed by an online multi-armed bandit strategy. We propose several portfolio strategies, the best of which we call GP-Hedge, and show that this method outperforms the best individual acquisition function. We also provide a theoretical bound on the algorithm's performance.", "source": "arxiv/ml"}
{"id": "arxiv:690", "title": "Approximate Maximum A Posteriori Inference with Entropic Priors", "text": "In certain applications it is useful to fit multinomial distributions to observed data with a penalty term that encourages sparsity. For example, in probabilistic latent audio source decomposition one may wish to encode the assumption that only a few latent sources are active at any given time. The standard heuristic of applying an L1 penalty is not an option when fitting the parameters to a multinomial distribution, which are constrained to sum to 1. An alternative is to use a penalty term that encourages low-entropy solutions, which corresponds to maximum a posteriori (MAP) parameter estimation with an entropic prior. The lack of conjugacy between the entropic prior and the multinomial distribution complicates this approach. In this report I propose a simple iterative algorithm for MAP estimation of multinomial distributions with sparsity-inducing entropic priors.", "source": "arxiv/ml"}
{"id": "arxiv:691", "title": "Fast Reinforcement Learning for Energy-Efficient Wireless Communications", "text": "We consider the problem of energy-efficient point-to-point transmission of delay-sensitive data (e.g. multimedia data) over a fading channel. Existing research on this topic utilizes either physical-layer centric solutions, namely power-control and adaptive modulation and coding (AMC), or system-level solutions based on dynamic power management (DPM); however, there is currently no rigorous and unified framework for simultaneously utilizing both physical-layer centric and system-level techniques to achieve the minimum possible energy consumption, under delay constraints, in the presence of stochastic and a priori unknown traffic and channel conditions. In this report, we propose such a framework. We formulate the stochastic optimization problem as a Markov decision process (MDP) and solve it online using reinforcement learning. The advantages of the proposed online method are that (i) it does not require a priori knowledge of the traffic arrival and channel statistics to determine the jointly optimal power-control, AMC, and DPM policies; (ii) it exploits partial information about the system so that less information needs to be learned than when using conventional reinforcement learning algorithms; and (iii) it obviates the need for action exploration, which severely limits the adaptation speed and run-time performance of conventional reinforcement learning algorithms. Our results show that the proposed learning algorithms can converge up to two orders of magnitude faster than a state-of-the-art learning algorithm for physical layer power-control and up to three orders of magnitude faster than conventional reinforcement learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:692", "title": "The Attentive Perceptron", "text": "We propose a focus of attention mechanism to speed up the Perceptron algorithm. Focus of attention speeds up the Perceptron algorithm by lowering the number of features evaluated throughout training and prediction. Whereas the traditional Perceptron evaluates all the features of each example, the Attentive Perceptron evaluates less features for easy to classify examples, thereby achieving significant speedups and small losses in prediction accuracy. Focus of attention allows the Attentive Perceptron to stop the evaluation of features at any interim point and filter the example. This creates an attentive filter which concentrates computation at examples that are hard to classify, and quickly filters examples that are easy to classify.", "source": "arxiv/ml"}
{"id": "arxiv:693", "title": "Online Learning in Opportunistic Spectrum Access: A Restless Bandit Approach", "text": "We consider an opportunistic spectrum access (OSA) problem where the time-varying condition of each channel (e.g., as a result of random fading or certain primary users' activities) is modeled as an arbitrary finite-state Markov chain. At each instance of time, a (secondary) user probes a channel and collects a certain reward as a function of the state of the channel (e.g., good channel condition results in higher data rate for the user). Each channel has potentially different state space and statistics, both unknown to the user, who tries to learn which one is the best as it goes and maximizes its usage of the best channel. The objective is to construct a good online learning algorithm so as to minimize the difference between the user's performance in total rewards and that of using the best channel (on average) had it known which one is the best from a priori knowledge of the channel statistics (also known as the regret). This is a classic exploration and exploitation problem and results abound when the reward processes are assumed to be iid. Compared to prior work, the biggest difference is that in our case the reward process is assumed to be Markovian, of which iid is a special case. In addition, the reward processes are restless in that the channel conditions will continue to evolve independent of the user's actions. This leads to a restless bandit problem, for which there exists little result on either algorithms or performance bounds in this learning context to the best of our knowledge. In this paper we introduce an algorithm that utilizes regenerative cycles of a Markov chain and computes a sample-mean based index policy, and show that under mild conditions on the state transition probabilities of the Markov chains this algorithm achieves logarithmic regret uniformly over time, and that this regret bound is also optimal.", "source": "arxiv/ml"}
{"id": "arxiv:694", "title": "Queue-Aware Distributive Resource Control for Delay-Sensitive Two-Hop MIMO Cooperative Systems", "text": "In this paper, we consider a queue-aware distributive resource control algorithm for two-hop MIMO cooperative systems. We shall illustrate that relay buffering is an effective way to reduce the intrinsic half-duplex penalty in cooperative systems. The complex interactions of the queues at the source node and the relays are modeled as an average-cost infinite horizon Markov Decision Process (MDP). The traditional approach solving this MDP problem involves centralized control with huge complexity. To obtain a distributive and low complexity solution, we introduce a linear structure which approximates the value function of the associated Bellman equation by the sum of per-node value functions. We derive a distributive two-stage two-winner auction-based control policy which is a function of the local CSI and local QSI only. Furthermore, to estimate the best fit approximation parameter, we propose a distributive online stochastic learning algorithm using stochastic approximation theory. Finally, we establish technical conditions for almost-sure convergence and show that under heavy traffic, the proposed low complexity distributive control is global optimal.", "source": "arxiv/ml"}
{"id": "arxiv:695", "title": "Hidden Markov Models with Multiple Observation Processes", "text": "We consider a hidden Markov model with multiple observation processes, one of which is chosen at each point in time by a policy---a deterministic function of the information state---and attempt to determine which policy minimises the limiting expected entropy of the information state. Focusing on a special case, we prove analytically that the information state always converges in distribution, and derive a formula for the limiting entropy which can be used for calculations with high precision. Using this fomula, we find computationally that the optimal policy is always a threshold policy, allowing it to be easily found. We also find that the greedy policy is almost optimal.", "source": "arxiv/ml"}
{"id": "arxiv:696", "title": "Time Series Classification by Class-Specific Mahalanobis Distance Measures", "text": "To classify time series by nearest neighbors, we need to specify or learn one or several distance measures. We consider variations of the Mahalanobis distance measures which rely on the inverse covariance matrix of the data. Unfortunately --- for time series data --- the covariance matrix has often low rank. To alleviate this problem we can either use a pseudoinverse, covariance shrinking or limit the matrix to its diagonal. We review these alternatives and benchmark them against competitive methods such as the related Large Margin Nearest Neighbor Classification (LMNN) and the Dynamic Time Warping (DTW) distance. As we expected, we find that the DTW is superior, but the Mahalanobis distance measures are one to two orders of magnitude faster. To get best results with Mahalanobis distance measures, we recommend learning one distance measure per class using either covariance shrinking or the diagonal approach.", "source": "arxiv/ml"}
{"id": "arxiv:697", "title": "Algorithms for nonnegative matrix factorization with the beta-divergence", "text": "This paper describes algorithms for nonnegative matrix factorization (NMF) with the beta-divergence (beta-NMF). The beta-divergence is a family of cost functions parametrized by a single shape parameter beta that takes the Euclidean distance, the Kullback-Leibler divergence and the Itakura-Saito divergence as special cases (beta = 2,1,0, respectively). The proposed algorithms are based on a surrogate auxiliary function (a local majorization of the criterion function). We first describe a majorization-minimization (MM) algorithm that leads to multiplicative updates, which differ from standard heuristic multiplicative updates by a beta-dependent power exponent. The monotonicity of the heuristic algorithm can however be proven for beta in (0,1) using the proposed auxiliary function. Then we introduce the concept of majorization-equalization (ME) algorithm which produces updates that move along constant level sets of the auxiliary function and lead to larger steps than MM. Simulations on synthetic and real data illustrate the faster convergence of the ME approach. The paper also describes how the proposed algorithms can be adapted to two common variants of NMF : penalized NMF (i.e., when a penalty function of the factors is added to the criterion function) and convex-NMF (when the dictionary is assumed to belong to a known subspace).", "source": "arxiv/ml"}
{"id": "arxiv:698", "title": "Multi-Objective Genetic Programming Projection Pursuit for Exploratory Data Modeling", "text": "For classification problems, feature extraction is a crucial process which aims to find a suitable data representation that increases the performance of the machine learning algorithm. According to the curse of dimensionality theorem, the number of samples needed for a classification task increases exponentially as the number of dimensions (variables, features) increases. On the other hand, it is costly to collect, store and process data. Moreover, irrelevant and redundant features might hinder classifier performance. In exploratory analysis settings, high dimensionality prevents the users from exploring the data visually. Feature extraction is a two-step process: feature construction and feature selection. Feature construction creates new features based on the original features and feature selection is the process of selecting the best features as in filter, wrapper and embedded methods. In this work, we focus on feature construction methods that aim to decrease data dimensionality for visualization tasks. Various linear (such as principal components analysis (PCA), multiple discriminants analysis (MDA), exploratory projection pursuit) and non-linear (such as multidimensional scaling (MDS), manifold learning, kernel PCA/LDA, evolutionary constructive induction) techniques have been proposed for dimensionality reduction. Our algorithm is an adaptive feature extraction method which consists of evolutionary constructive induction for feature construction and a hybrid filter/wrapper method for feature selection.", "source": "arxiv/ml"}
{"id": "arxiv:699", "title": "Robust Recovery of Subspace Structures by Low-Rank Representation", "text": "In this work we address the subspace recovery problem. Given a set of data samples (vectors) approximately drawn from a union of multiple subspaces, our goal is to segment the samples into their respective subspaces and correct the possible errors as well. To this end, we propose a novel method termed Low-Rank Representation (LRR), which seeks the lowest-rank representation among all the candidates that can represent the data samples as linear combinations of the bases in a given dictionary. It is shown that LRR well solves the subspace recovery problem: when the data is clean, we prove that LRR exactly captures the true subspace structures; for the data contaminated by outliers, we prove that under certain conditions LRR can exactly recover the row space of the original data and detect the outlier as well; for the data corrupted by arbitrary errors, LRR can also approximately recover the row space with theoretical guarantees. Since the subspace membership is provably determined by the row space, these further imply that LRR can perform robust subspace segmentation and error correction, in an efficient way.", "source": "arxiv/ml"}
{"id": "arxiv:700", "title": "Near-Optimal Bayesian Active Learning with Noisy Observations", "text": "We tackle the fundamental problem of Bayesian active learning with noise, where we need to adaptively select from a number of expensive tests in order to identify an unknown hypothesis sampled from a known prior distribution. In the case of noise-free observations, a greedy algorithm called generalized binary search (GBS) is known to perform near-optimally. We show that if the observations are noisy, perhaps surprisingly, GBS can perform very poorly. We develop EC2, a novel, greedy active learning algorithm and prove that it is competitive with the optimal policy, thus obtaining the first competitiveness guarantees for Bayesian active learning with noisy observations. Our bounds rely on a recently discovered diminishing returns property called adaptive submodularity, generalizing the classical notion of submodular set functions to adaptive policies. Our results hold even if the tests have non-uniform cost and their noise is correlated. We also propose EffECXtive, a particularly fast approximation of EC2, and evaluate it on a Bayesian experimental design problem involving human subjects, intended to tease apart competing economic theories of how people make decisions under uncertainty.", "source": "arxiv/ml"}
{"id": "arxiv:701", "title": "Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition", "text": "Adaptive sparse coding methods learn a possibly overcomplete set of basis functions, such that natural image patches can be reconstructed by linearly combining a small subset of these bases. The applicability of these methods to visual object recognition tasks has been limited because of the prohibitive cost of the optimization algorithms required to compute the sparse representation. In this work we propose a simple and efficient algorithm to learn basis functions. After training, this model also provides a fast and smooth approximator to the optimal representation, achieving even better accuracy than exact sparse coding algorithms on visual object recognition tasks.", "source": "arxiv/ml"}
{"id": "arxiv:702", "title": "Hardness Results for Agnostically Learning Low-Degree Polynomial Threshold Functions", "text": "Hardness results for maximum agreement problems have close connections to hardness results for proper learning in computational learning theory. In this paper we prove two hardness results for the problem of finding a low degree polynomial threshold function (PTF) which has the maximum possible agreement with a given set of labeled examples in $\\R^n \\times \\{-1,1\\}.$ We prove that for any constants $d\\geq 1, \\eps > 0$, {itemize} Assuming the Unique Games Conjecture, no polynomial-time algorithm can find a degree-$d$ PTF that is consistent with a $(\\half + \\eps)$ fraction of a given set of labeled examples in $\\R^n \\times \\{-1,1\\}$, even if there exists a degree-$d$ PTF that is consistent with a $1-\\eps$ fraction of the examples. It is $\\NP$-hard to find a degree-2 PTF that is consistent with a $(\\half + \\eps)$ fraction of a given set of labeled examples in $\\R^n \\times \\{-1,1\\}$, even if there exists a halfspace (degree-1 PTF) that is consistent with a $1 - \\eps$ fraction of the examples. {itemize} These results immediately imply the following hardness of learning results: (i) Assuming the Unique Games Conjecture, there is no better-than-trivial proper learning algorithm that agnostically learns degree-$d$ PTFs under arbitrary distributions; (ii) There is no better-than-trivial learning algorithm that outputs degree-2 PTFs and agnostically learns halfspaces (i.e. degree-1 PTFs) under arbitrary distributions.", "source": "arxiv/ml"}
{"id": "arxiv:703", "title": "Efficient Matrix Completion with Gaussian Models", "text": "A general framework based on Gaussian models and a MAP-EM algorithm is introduced in this paper for solving matrix/table completion problems. The numerical experiments with the standard and challenging movie ratings data show that the proposed approach, based on probably one of the simplest probabilistic models, leads to the results in the same ballpark as the state-of-the-art, at a lower computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:704", "title": "Convex Analysis and Optimization with Submodular Functions: a Tutorial", "text": "Set-functions appear in many areas of computer science and applied mathematics, such as machine learning, computer vision, operations research or electrical networks. Among these set-functions, submodular functions play an important role, similar to convex functions on vector spaces. In this tutorial, the theory of submodular functions is presented, in a self-contained way, with all results shown from first principles. A good knowledge of convex analysis is assumed.", "source": "arxiv/ml"}
{"id": "arxiv:705", "title": "Robust PCA via Outlier Pursuit", "text": "Singular Value Decomposition (and Principal Component Analysis) is one of the most widely used techniques for dimensionality reduction: successful and efficiently computable, it is nevertheless plagued by a well-known, well-documented sensitivity to outliers. Recent work has considered the setting where each point has a few arbitrarily corrupted components. Yet, in applications of SVD or PCA such as robust collaborative filtering or bioinformatics, malicious agents, defective genes, or simply corrupted or contaminated experiments may effectively yield entire points that are completely corrupted. We present an efficient convex optimization-based algorithm we call Outlier Pursuit, that under some mild assumptions on the uncorrupted points (satisfied, e.g., by the standard generative assumption in PCA problems) recovers the exact optimal low-dimensional subspace, and identifies the corrupted points. Such identification of corrupted points that do not conform to the low-dimensional approximation, is of paramount interest in bioinformatics and financial applications, and beyond. Our techniques involve matrix decomposition using nuclear norm minimization, however, our results, setup, and approach, necessarily differ considerably from the existing line of work in matrix completion and matrix decomposition, since we develop an approach to recover the correct column space of the uncorrupted matrix, rather than the exact matrix itself. In any problem where one seeks to recover a structure rather than the exact initial matrices, techniques developed thus far relying on certificates of optimality, will fail. We present an important extension of these methods, that allows the treatment of such problems.", "source": "arxiv/ml"}
{"id": "arxiv:706", "title": "Large-Scale Clustering Based on Data Compression", "text": "This paper considers the clustering problem for large data sets. We propose an approach based on distributed optimization. The clustering problem is formulated as an optimization problem of maximizing the classification gain. We show that the optimization problem can be reformulated and decomposed into small-scale sub optimization problems by using the Dantzig-Wolfe decomposition method. Generally speaking, the Dantzig-Wolfe method can only be used for convex optimization problems, where the duality gaps are zero. Even though, the considered optimization problem in this paper is non-convex, we prove that the duality gap goes to zero, as the problem size goes to infinity. Therefore, the Dantzig-Wolfe method can be applied here. In the proposed approach, the clustering problem is iteratively solved by a group of computers coordinated by one center processor, where each computer solves one independent small-scale sub optimization problem during each iteration, and only a small amount of data communication is needed between the computers and center processor. Numerical results show that the proposed approach is effective and efficient.", "source": "arxiv/ml"}
{"id": "arxiv:707", "title": "Sublinear Optimization for Machine Learning", "text": "We give sublinear-time approximation algorithms for some optimization problems arising in machine learning, such as training linear classifiers and finding minimum enclosing balls. Our algorithms can be extended to some kernelized versions of these problems, such as SVDD, hard margin SVM, and L2-SVM, for which sublinear-time algorithms were not known before. These new algorithms use a combination of a novel sampling techniques and a new multiplicative update algorithm. We give lower bounds which show the running times of many of our algorithms to be nearly best possible in the unit-cost RAM model. We also give implementations of our algorithms in the semi-streaming setting, obtaining the first low pass polylogarithmic space and sublinear time algorithms achieving arbitrary approximation factor.", "source": "arxiv/ml"}
{"id": "arxiv:708", "title": "On the Foundations of Adversarial Single-Class Classification", "text": "Motivated by authentication, intrusion and spam detection applications we consider single-class classification (SCC) as a two-person game between the learner and an adversary. In this game the learner has a sample from a target distribution and the goal is to construct a classifier capable of distinguishing observations from the target distribution from observations emitted from an unknown other distribution. The ideal SCC classifier must guarantee a given tolerance for the false-positive error (false alarm rate) while minimizing the false negative error (intruder pass rate). Viewing SCC as a two-person zero-sum game we identify both deterministic and randomized optimal classification strategies for different game variants. We demonstrate that randomized classification can provide a significant advantage. In the deterministic setting we show how to reduce SCC to two-class classification where in the two-class problem the other class is a synthetically generated distribution. We provide an efficient and practical algorithm for constructing and solving the two class problem. The algorithm distinguishes low density regions of the target distribution and is shown to be consistent.", "source": "arxiv/ml"}
{"id": "arxiv:709", "title": "Local Component Analysis for Nonparametric Bayes Classifier", "text": "The decision boundaries of Bayes classifier are optimal because they lead to maximum probability of correct decision. It means if we knew the prior probabilities and the class-conditional densities, we could design a classifier which gives the lowest probability of error. However, in classification based on nonparametric density estimation methods such as Parzen windows, the decision regions depend on the choice of parameters such as window width. Moreover, these methods suffer from curse of dimensionality of the feature space and small sample size problem which severely restricts their practical applications. In this paper, we address these problems by introducing a novel dimension reduction and classification method based on local component analysis. In this method, by adopting an iterative cross-validation algorithm, we simultaneously estimate the optimal transformation matrices (for dimension reduction) and classifier parameters based on local information. The proposed method can classify the data with complicated boundary and also alleviate the course of dimensionality dilemma. Experiments on real data show the superiority of the proposed algorithm in term of classification accuracies for pattern classification applications like age, facial expression and character recognition. Keywords: Bayes classifier, curse of dimensionality dilemma, Parzen window, pattern classification, subspace learning.", "source": "arxiv/ml"}
{"id": "arxiv:710", "title": "Converged Algorithms for Orthogonal Nonnegative Matrix Factorizations", "text": "This paper proposes uni-orthogonal and bi-orthogonal nonnegative matrix factorization algorithms with robust convergence proofs. We design the algorithms based on the work of Lee and Seung [1], and derive the converged versions by utilizing ideas from the work of Lin [2]. The experimental results confirm the theoretical guarantees of the convergences.", "source": "arxiv/ml"}
{"id": "arxiv:711", "title": "Resource-bounded Dimension in Computational Learning Theory", "text": "This paper focuses on the relation between computational learning theory and resource-bounded dimension. We intend to establish close connections between the learnability/nonlearnability of a concept class and its corresponding size in terms of effective dimension, which will allow the use of powerful dimension techniques in computational learning and viceversa, the import of learning results into complexity via dimension. Firstly, we obtain a tight result on the dimension of online mistake-bound learnable classes. Secondly, in relation with PAC learning, we show that the polynomial-space dimension of PAC learnable classes of concepts is zero. This provides a hypothesis on effective dimension that implies the inherent unpredictability of concept classes (the classes that verify this property are classes not efficiently PAC learnable using any hypothesis). Thirdly, in relation to space dimension of classes that are learnable by membership query algorithms, the main result proves that polynomial-space dimension of concept classes learnable by a membership-query algorithm is zero.", "source": "arxiv/ml"}
{"id": "arxiv:712", "title": "Efficient Minimization of Decomposable Submodular Functions", "text": "Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing a submodular function. Submodular functions are a natural discrete analog of convex functions, and can be minimized in strongly polynomial time. Unfortunately, state-of-the-art algorithms for general submodular minimization are intractable for larger problems. In this paper, we introduce a novel subclass of submodular minimization problems that we call decomposable. Decomposable submodular functions are those that can be represented as sums of concave functions applied to modular functions. We develop an algorithm, SLG, that can efficiently minimize decomposable submodular functions with tens of thousands of variables. Our algorithm exploits recent results in smoothed convex minimization. We apply SLG to synthetic benchmarks and a joint classification-and-segmentation task, and show that it outperforms the state-of-the-art general purpose submodular minimization algorithms by several orders of magnitude.", "source": "arxiv/ml"}
{"id": "arxiv:713", "title": "Analysing the behaviour of robot teams through relational sequential pattern mining", "text": "This report outlines the use of a relational representation in a Multi-Agent domain to model the behaviour of the whole system. A desired property in this systems is the ability of the team members to work together to achieve a common goal in a cooperative manner. The aim is to define a systematic method to verify the effective collaboration among the members of a team and comparing the different multi-agent behaviours. Using external observations of a Multi-Agent System to analyse, model, recognize agent behaviour could be very useful to direct team actions. In particular, this report focuses on the challenge of autonomous unsupervised sequential learning of the team's behaviour from observations. Our approach allows to learn a symbolic sequence (a relational representation) to translate raw multi-agent, multi-variate observations of a dynamic, complex environment, into a set of sequential behaviours that are characteristic of the team in question, represented by a set of sequences expressed in first-order logic atoms. We propose to use a relational learning algorithm to mine meaningful frequent patterns among the relational sequences to characterise team behaviours. We compared the performance of two teams in the RoboCup four-legged league environment, that have a very different approach to the game. One uses a Case Based Reasoning approach, the other uses a pure reactive behaviour.", "source": "arxiv/ml"}
{"id": "arxiv:714", "title": "Predictive State Temporal Difference Learning", "text": "We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications, reinforcement learning (RL) is complicated by the fact that state is either high-dimensional or partially observable. Therefore, RL methods are designed to work with features of state rather than state itself, and the success or failure of learning is often determined by the suitability of the selected features. By comparison, subspace identification (SSID) methods are designed to select a feature set which preserves as much information as possible about state. In this paper we connect the two approaches, looking at the problem of reinforcement learning with a large set of features, each of which may only be marginally useful for value function approximation. We introduce a new algorithm for this situation, called Predictive State Temporal Difference (PSTD) learning. As in SSID for predictive state representations, PSTD finds a linear compression operator that projects a large set of features down to a small set that preserves the maximum amount of predictive information. As in RL, PSTD then uses a Bellman recursion to estimate a value function. We discuss the connection between PSTD and prior approaches in RL and SSID. We prove that PSTD is statistically consistent, perform several experiments that illustrate its properties, and demonstrate its potential on a difficult optimal stopping problem.", "source": "arxiv/ml"}
{"id": "arxiv:715", "title": "Sparse Inverse Covariance Selection via Alternating Linearization Methods", "text": "Gaussian graphical models are of great interest in statistical learning. Because the conditional independencies between different nodes correspond to zero entries in the inverse covariance matrix of the Gaussian distribution, one can learn the structure of the graph by estimating a sparse inverse covariance matrix from sample data, by solving a convex maximum likelihood problem with an $\\ell_1$-regularization term. In this paper, we propose a first-order method based on an alternating linearization technique that exploits the problem's special structure; in particular, the subproblems solved in each iteration have closed-form solutions. Moreover, our algorithm obtains an $\\epsilon$-optimal solution in $O(1/\\epsilon)$ iterations. Numerical experiments on both synthetic and real data from gene association networks show that a practical version of this algorithm outperforms other competitive algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:716", "title": "Developing courses with HoloRena, a framework for scenario- and game based e-learning environments", "text": "However utilizing rich, interactive solutions can make learning more effective and attractive, scenario- and game-based educational resources on the web are not widely used. Creating these applications is a complex, expensive and challenging process. Development frameworks and authoring tools hardly support reusable components, teamwork and learning management system-independent courseware architecture. In this article we initiate the concept of a low-level, thick-client solution addressing these problems. With some example applications we try to demonstrate, how a framework, based on this concept can be useful for developing scenario- and game-based e-learning environments.", "source": "arxiv/ml"}
{"id": "arxiv:717", "title": "Learning Networks of Stochastic Differential Equations", "text": "We consider linear models for stochastic dynamics. To any such model can be associated a network (namely a directed graph) describing which degrees of freedom interact under the dynamics. We tackle the problem of learning such a network from observation of the system trajectory over a time interval $T$. We analyze the $\\ell_1$-regularized least squares algorithm and, in the setting in which the underlying network is sparse, we prove performance guarantees that are \\emph{uniform in the sampling rate} as long as this is sufficiently high. This result substantiates the notion of a well defined `time complexity' for the network inference problem.", "source": "arxiv/ml"}
{"id": "arxiv:718", "title": "From Sparse Signals to Sparse Residuals for Robust Sensing", "text": "One of the key challenges in sensor networks is the extraction of information by fusing data from a multitude of distinct, but possibly unreliable sensors. Recovering information from the maximum number of dependable sensors while specifying the unreliable ones is critical for robust sensing. This sensing task is formulated here as that of finding the maximum number of feasible subsystems of linear equations, and proved to be NP-hard. Useful links are established with compressive sampling, which aims at recovering vectors that are sparse. In contrast, the signals here are not sparse, but give rise to sparse residuals. Capitalizing on this form of sparsity, four sensing schemes with complementary strengths are developed. The first scheme is a convex relaxation of the original problem expressed as a second-order cone program (SOCP). It is shown that when the involved sensing matrices are Gaussian and the reliable measurements are sufficiently many, the SOCP can recover the optimal solution with overwhelming probability. The second scheme is obtained by replacing the initial objective function with a concave one. The third and fourth schemes are tailored for noisy sensor data. The noisy case is cast as a combinatorial problem that is subsequently surrogated by a (weighted) SOCP. Interestingly, the derived cost functions fall into the framework of robust multivariate linear regression, while an efficient block-coordinate descent algorithm is developed for their minimization. The robust sensing capabilities of all schemes are verified by simulated tests.", "source": "arxiv/ml"}
{"id": "arxiv:719", "title": "Regularized Risk Minimization by Nesterov's Accelerated Gradient Methods: Algorithmic Extensions and Empirical Studies", "text": "Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this paper, we first extend AGM to strongly convex and composite objective functions with Bregman style prox-functions. Our unifying framework covers both the $\\infty$-memory and 1-memory styles of AGM, tunes the Lipschiz constant adaptively, and bounds the duality gap. Then we demonstrate various ways to apply this framework of methods to a wide range of machine learning problems. Emphasis will be given on their rate of convergence and how to efficiently compute the gradient and optimize the models. The experimental results show that with our extensions AGM outperforms state-of-the-art solvers on max-margin models.", "source": "arxiv/ml"}
{"id": "arxiv:720", "title": "A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning", "text": "Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting. We show that any such no regret algorithm, combined with additional reduction assumptions, must find a policy with good performance under the distribution of observations it induces in such sequential settings. We demonstrate that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.", "source": "arxiv/ml"}
{"id": "arxiv:721", "title": "Multiarmed Bandit Problems with Delayed Feedback", "text": "In this paper we initiate the study of optimization of bandit type problems in scenarios where the feedback of a play is not immediately known. This arises naturally in allocation problems which have been studied extensively in the literature, albeit in the absence of delays in the feedback. We study this problem in the Bayesian setting. In presence of delays, no solution with provable guarantees is known to exist with sub-exponential running time. We show that bandit problems with delayed feedback that arise in allocation settings can be forced to have significant structure, with a slight loss in optimality. This structure gives us the ability to reason about the relationship of single arm policies to the entangled optimum policy, and eventually leads to a O(1) approximation for a significantly general class of priors. The structural insights we develop are of key interest and carry over to the setting where the feedback of an action is available instantaneously, and we improve all previous results in this setting as well.", "source": "arxiv/ml"}
{"id": "arxiv:722", "title": "Privately Releasing Conjunctions and the Statistical Query Barrier", "text": "Suppose we would like to know all answers to a set of statistical queries C on a data set up to small error, but we can only access the data itself using statistical queries. A trivial solution is to exhaustively ask all queries in C. Can we do any better? + We show that the number of statistical queries necessary and sufficient for this task is---up to polynomial factors---equal to the agnostic learning complexity of C in Kearns' statistical query (SQ) model. This gives a complete answer to the question when running time is not a concern. + We then show that the problem can be solved efficiently (allowing arbitrary error on a small fraction of queries) whenever the answers to C can be described by a submodular function. This includes many natural concept classes, such as graph cuts and Boolean disjunctions and conjunctions. While interesting from a learning theoretic point of view, our main applications are in privacy-preserving data analysis: Here, our second result leads to the first algorithm that efficiently releases differentially private answers to of all Boolean conjunctions with 1% average error. This presents significant progress on a key open problem in privacy-preserving data analysis. Our first result on the other hand gives unconditional lower bounds on any differentially private algorithm that admits a (potentially non-privacy-preserving) implementation using only statistical queries. Not only our algorithms, but also most known private algorithms can be implemented using only statistical queries, and hence are constrained by these lower bounds. Our result therefore isolates the complexity of agnostic learning in the SQ-model as a new barrier in the design of differentially private algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:723", "title": "Robust Matrix Decomposition with Outliers", "text": "Suppose a given observation matrix can be decomposed as the sum of a low-rank matrix and a sparse matrix (outliers), and the goal is to recover these individual components from the observed sum. Such additive decompositions have applications in a variety of numerical problems including system identification, latent variable graphical modeling, and principal components analysis. We study conditions under which recovering such a decomposition is possible via a combination of $\\ell_1$ norm and trace norm minimization. We are specifically interested in the question of how many outliers are allowed so that convex programming can still achieve accurate recovery, and we obtain stronger recovery guarantees than previous studies. Moreover, we do not assume that the spatial pattern of outliers is random, which stands in contrast to related analyses under such assumptions via matrix completion.", "source": "arxiv/ml"}
{"id": "arxiv:724", "title": "Online Importance Weight Aware Updates", "text": "An importance weight quantifies the relative importance of one example over another, coming up in applications of boosting, asymmetric classification costs, reductions, and active learning. The standard approach for dealing with importance weights in gradient descent is via multiplication of the gradient. We first demonstrate the problems of this approach when importance weights are large, and argue in favor of more sophisticated ways for dealing with them. We then develop an approach which enjoys an invariance property: that updating twice with importance weight $h$ is equivalent to updating once with importance weight $2h$. For many important losses this has a closed form update which satisfies standard regret guarantees when all examples have $h=1$. We also briefly discuss two other reasonable approaches for handling large importance weights. Empirically, these approaches yield substantially superior prediction with similar computational performance while reducing the sensitivity of the algorithm to the exact setting of the learning rate. We apply these to online active learning yielding an extraordinarily fast active learning algorithm that works even in the presence of adversarial noise.", "source": "arxiv/ml"}
{"id": "arxiv:725", "title": "Least Squares Ranking on Graphs", "text": "Given a set of alternatives to be ranked, and some pairwise comparison data, ranking is a least squares computation on a graph. The vertices are the alternatives, and the edge values comprise the comparison data. The basic idea is very simple and old: come up with values on vertices such that their differences match the given edge data. Since an exact match will usually be impossible, one settles for matching in a least squares sense. This formulation was first described by Leake in 1976 for rankingfootball teams and appears as an example in Professor Gilbert Strang's classic linear algebra textbook. If one is willing to look into the residual a little further, then the problem really comes alive, as shown effectively by the remarkable recent paper of Jiang et al. With or without this twist, the humble least squares problem on graphs has far-reaching connections with many current areas ofresearch. These connections are to theoretical computer science (spectral graph theory, and multilevel methods for graph Laplacian systems); numerical analysis (algebraic multigrid, and finite element exterior calculus); other mathematics (Hodge decomposition, and random clique complexes); and applications (arbitrage, and ranking of sports teams). Not all of these connections are explored in this paper, but many are. The underlying ideas are easy to explain, requiring only the four fundamental subspaces from elementary linear algebra. One of our aims is to explain these basic ideas and connections, to get researchers in many fields interested in this topic. Another aim is to use our numerical experiments for guidance on selecting methods and exposing the need for further development.", "source": "arxiv/ml"}
{"id": "arxiv:726", "title": "Blackwell Approachability and Low-Regret Learning are Equivalent", "text": "We consider the celebrated Blackwell Approachability Theorem for two-player games with vector payoffs. We show that Blackwell's result is equivalent, via efficient reductions, to the existence of \"no-regret\" algorithms for Online Linear Optimization. Indeed, we show that any algorithm for one such problem can be efficiently converted into an algorithm for the other. We provide a useful application of this reduction: the first efficient algorithm for calibrated forecasting.", "source": "arxiv/ml"}
{"id": "arxiv:727", "title": "Extended Active Learning Method", "text": "Active Learning Method (ALM) is a soft computing method which is used for modeling and control, based on fuzzy logic. Although ALM has shown that it acts well in dynamic environments, its operators cannot support it very well in complex situations due to losing data. Thus ALM can find better membership functions if more appropriate operators be chosen for it. This paper substituted two new operators instead of ALM original ones; which consequently renewed finding membership functions in a way superior to conventional ALM. This new method is called Extended Active Learning Method (EALM).", "source": "arxiv/ml"}
{"id": "arxiv:728", "title": "Clustering using Unsupervised Binary Trees: CUBT", "text": "We herein introduce a new method of interpretable clustering that uses unsupervised binary trees. It is a three-stage procedure, the first stage of which entails a series of recursive binary splits to reduce the heterogeneity of the data within the new subsamples. During the second stage (pruning), consideration is given to whether adjacent nodes can be aggregated. Finally, during the third stage (joining), similar clusters are joined together, even if they do not share the same parent originally. Consistency results are obtained, and the procedure is used on simulated and real data sets.", "source": "arxiv/ml"}
{"id": "arxiv:729", "title": "Regularization Strategies and Empirical Bayesian Learning for MKL", "text": "Multiple kernel learning (MKL), structured sparsity, and multi-task learning have recently received considerable attention. In this paper, we show how different MKL algorithms can be understood as applications of either regularization on the kernel weights or block-norm-based regularization, which is more common in structured sparsity and multi-task learning. We show that these two regularization strategies can be systematically mapped to each other through a concave conjugate operation. When the kernel-weight-based regularizer is separable into components, we can naturally consider a generative probabilistic model behind MKL. Based on this model, we propose learning algorithms for the kernel weights through the maximization of marginal likelihood. We show through numerical experiments that $\\ell_2$-norm MKL and Elastic-net MKL achieve comparable accuracy to uniform kernel combination. Although uniform kernel combination might be preferable from its simplicity, $\\ell_2$-norm MKL and Elastic-net MKL can learn the usefulness of the information sources represented as kernels. In particular, Elastic-net MKL achieves sparsity in the kernel weights.", "source": "arxiv/ml"}
{"id": "arxiv:730", "title": "Online Learning: Beyond Regret", "text": "We study online learnability of a wide class of problems, extending the results of (Rakhlin, Sridharan, Tewari, 2010) to general notions of performance measure well beyond external regret. Our framework simultaneously captures such well-known notions as internal and general Phi-regret, learning with non-additive global cost functions, Blackwell's approachability, calibration of forecasters, adaptive regret, and more. We show that learnability in all these situations is due to control of the same three quantities: a martingale convergence term, a term describing the ability to perform well if future is known, and a generalization of sequential Rademacher complexity, studied in (Rakhlin, Sridharan, Tewari, 2010). Since we directly study complexity of the problem instead of focusing on efficient algorithms, we are able to improve and extend many known results which have been previously derived via an algorithmic construction.", "source": "arxiv/ml"}
{"id": "arxiv:731", "title": "A Probabilistic Approach for Learning Folksonomies from Structured Data", "text": "Learning structured representations has emerged as an important problem in many domains, including document and Web data mining, bioinformatics, and image analysis. One approach to learning complex structures is to integrate many smaller, incomplete and noisy structure fragments. In this work, we present an unsupervised probabilistic approach that extends affinity propagation to combine the small ontological fragments into a collection of integrated, consistent, and larger folksonomies. This is a challenging task because the method must aggregate similar structures while avoiding structural inconsistencies and handling noise. We validate the approach on a real-world social media dataset, comprised of shallow personal hierarchies specified by many individual users, collected from the photosharing website Flickr. Our empirical results show that our proposed approach is able to construct deeper and denser structures, compared to an approach using only the standard affinity propagation algorithm. Additionally, the approach yields better overall integration quality than a state-of-the-art approach based on incremental relational clustering.", "source": "arxiv/ml"}
{"id": "arxiv:732", "title": "PADDLE: Proximal Algorithm for Dual Dictionaries LEarning", "text": "Recently, considerable research efforts have been devoted to the design of methods to learn from data overcomplete dictionaries for sparse coding. However, learned dictionaries require the solution of an optimization problem for coding new data. In order to overcome this drawback, we propose an algorithm aimed at learning both a dictionary and its dual: a linear mapping directly performing the coding. By leveraging on proximal methods, our algorithm jointly minimizes the reconstruction error of the dictionary and the coding error of its dual; the sparsity of the representation is induced by an $\\ell_1$-based penalty on its coefficients. The results obtained on synthetic data and real images show that the algorithm is capable of recovering the expected dictionaries. Furthermore, on a benchmark dataset, we show that the image features obtained from the dual matrix yield state-of-the-art classification performance while being much less computational intensive.", "source": "arxiv/ml"}
{"id": "arxiv:733", "title": "Clustering and Latent Semantic Indexing Aspects of the Singular Value Decomposition", "text": "This paper discusses clustering and latent semantic indexing (LSI) aspects of the singular value decomposition (SVD). The purpose of this paper is twofold. The first is to give an explanation on how and why the singular vectors can be used in clustering. And the second is to show that the two seemingly unrelated SVD aspects actually originate from the same source: related vertices tend to be more clustered in the graph representation of lower rank approximate matrix using the SVD than in the original semantic graph. Accordingly, the SVD can improve retrieval performance of an information retrieval system since queries made to the approximate matrix can retrieve more relevant documents and filter out more irrelevant documents than the same queries made to the original matrix. By utilizing this fact, we will devise an LSI algorithm that mimicks SVD capability in clustering related vertices. Convergence analysis shows that the algorithm is convergent and produces a unique solution for each input. Experimental results using some standard datasets in LSI research show that retrieval performances of the algorithm are comparable to the SVD's. In addition, the algorithm is more practical and easier to use because there is no need to determine decomposition rank which is crucial in driving retrieval performance of the SVD.", "source": "arxiv/ml"}
{"id": "arxiv:734", "title": "Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards", "text": "In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected total reward accumulated by an omniscient player that knows the reward means for each arm, and the expected total reward accumulated by the given policy. The policies presented in prior work have storage, computation and regret all growing linearly with the number of arms, which is not scalable when the number of arms is large. We consider in this work a broad class of multi-armed bandits with dependent arms that yield rewards as a linear combination of a set of unknown parameters. For this general framework, we present efficient policies that are shown to achieve regret that grows logarithmically with time, and polynomially in the number of unknown parameters (even though the number of dependent arms may grow exponentially). Furthermore, these policies only require storage that grows linearly in the number of unknown parameters. We show that this generalization is broadly applicable and useful for many interesting tasks in networks that can be formulated as tractable combinatorial optimization problems with linear objective functions, such as maximum weight matching, shortest path, and minimum spanning tree computations.", "source": "arxiv/ml"}
{"id": "arxiv:735", "title": "The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret", "text": "In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \\geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \\emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie), which leads to the same average reward that can be achieved by the optimal policy under a known model. This is the first such result in the literature for a non-Bayesian RMAB.", "source": "arxiv/ml"}
{"id": "arxiv:736", "title": "Learning in A Changing World: Restless Multi-Armed Bandit with Unknown Dynamics", "text": "We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics in which a player chooses M out of N arms to play at each time. The reward state of each arm transits according to an unknown Markovian rule when it is played and evolves according to an arbitrary unknown random process when it is passive. The performance of an arm selection policy is measured by regret, defined as the reward loss with respect to the case where the player knows which M arms are the most rewarding and always plays the M best arms. We construct a policy with an interleaving exploration and exploitation epoch structure that achieves a regret with logarithmic order when arbitrary (but nontrivial) bounds on certain system parameters are known. When no knowledge about the system is available, we show that the proposed policy achieves a regret arbitrarily close to the logarithmic order. We further extend the problem to a decentralized setting where multiple distributed players share the arms without information exchange. Under both an exogenous restless model and an endogenous restless model, we show that a decentralized extension of the proposed policy preserves the logarithmic regret order as in the centralized setting. The results apply to adaptive learning in various dynamic systems and communication networks, as well as financial investment.", "source": "arxiv/ml"}
{"id": "arxiv:737", "title": "Tight Sample Complexity of Large-Margin Learning", "text": "We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the \\gamma-adapted-dimension, which is a simple function of the spectrum of a distribution's covariance matrix, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the \\gamma-adapted-dimension of the source distribution. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification. The bounds hold for a rich family of sub-Gaussian distributions.", "source": "arxiv/ml"}
{"id": "arxiv:738", "title": "Classifying Clustering Schemes", "text": "Many clustering schemes are defined by optimizing an objective function defined on the partitions of the underlying set of a finite metric space. In this paper, we construct a framework for studying what happens when we instead impose various structural conditions on the clustering schemes, under the general heading of functoriality. Functoriality refers to the idea that one should be able to compare the results of clustering algorithms as one varies the data set, for example by adding points or by applying functions to it. We show that within this framework, one can prove a theorems analogous to one of J. Kleinberg, in which for example one obtains an existence and uniqueness theorem instead of a non-existence result. We obtain a full classification of all clustering schemes satisfying a condition we refer to as excisiveness. The classification can be changed by varying the notion of maps of finite metric spaces. The conditions occur naturally when one considers clustering as the statistical version of the geometric notion of connected components. By varying the degree of functoriality that one requires from the schemes it is possible to construct richer families of clustering schemes that exhibit sensitivity to density.", "source": "arxiv/ml"}
{"id": "arxiv:739", "title": "The Sample Complexity of Dictionary Learning", "text": "A large set of signals can sometimes be described sparsely using a dictionary, that is, every element can be represented as a linear combination of few elements from the dictionary. Algorithms for various signal processing applications, including classification, denoising and signal separation, learn a dictionary from a set of signals to be represented. Can we expect that the representation found by such a dictionary for a previously unseen example from the same source will have L_2 error of the same magnitude as those for the given examples? We assume signals are generated from a fixed distribution, and study this questions from a statistical learning theory perspective. We develop generalization bounds on the quality of the learned dictionary for two types of constraints on the coefficient selection, as measured by the expected L_2 error in representation when the dictionary is used. For the case of l_1 regularized coefficient selection we provide a generalization bound of the order of O(sqrt(np log(m lambda)/m)), where n is the dimension, p is the number of elements in the dictionary, lambda is a bound on the l_1 norm of the coefficient vector and m is the number of samples, which complements existing results. For the case of representing a new signal as a combination of at most k dictionary elements, we provide a bound of the order O(sqrt(np log(m k)/m)) under an assumption on the level of orthogonality of the dictionary (low Babel function). We further show that this assumption holds for most dictionaries in high dimensions in a strong probabilistic sense. Our results further yield fast rates of order 1/m as opposed to 1/sqrt(m) using localized Rademacher complexity. We provide similar results in a general setting using kernels with weak smoothness requirements.", "source": "arxiv/ml"}
{"id": "arxiv:740", "title": "On Theorem 2.3 in \"Prediction, Learning, and Games\" by Cesa-Bianchi and Lugosi", "text": "The note presents a modified proof of a loss bound for the exponentially weighted average forecaster with time-varying potential. The regret term of the algorithm is upper-bounded by sqrt{n ln(N)} (uniformly in n), where N is the number of experts and n is the number of steps.", "source": "arxiv/ml"}
{"id": "arxiv:741", "title": "In All Likelihood, Deep Belief Is Not Enough", "text": "Statistical models of natural stimuli provide an important tool for researchers in the fields of machine learning and computational neuroscience. A canonical way to quantitatively assess and compare the performance of statistical models is given by the likelihood. One class of statistical models which has recently gained increasing popularity and has been applied to a variety of complex data are deep belief networks. Analyses of these models, however, have been typically limited to qualitative analyses based on samples due to the computationally intractable nature of the model likelihood. Motivated by these circumstances, the present article provides a consistent estimator for the likelihood that is both computationally tractable and simple to apply in practice. Using this estimator, a deep belief network which has been suggested for the modeling of natural image patches is quantitatively investigated and compared to other models of natural image patches. Contrary to earlier claims based on qualitative results, the results presented in this article provide evidence that the model under investigation is not a particularly good model for natural images", "source": "arxiv/ml"}
{"id": "arxiv:742", "title": "Classifying extremely imbalanced data sets", "text": "Imbalanced data sets containing much more background than signal instances are very common in particle physics, and will also be characteristic for the upcoming analyses of LHC data. Following up the work presented at ACAT 2008, we use the multivariate technique presented there (a rule growing algorithm with the meta-methods bagging and instance weighting) on much more imbalanced data sets, especially a selection of D0 decays without the use of particle identification. It turns out that the quality of the result strongly depends on the number of background instances used for training. We discuss methods to exploit this in order to improve the results significantly, and how to handle and reduce the size of large training sets without loss of result quality in general. We will also comment on how to take into account statistical fluctuation in receiver operation characteristic curves (ROC) for comparing classifier methods.", "source": "arxiv/ml"}
{"id": "arxiv:743", "title": "Estimating Probabilities in Recommendation Systems", "text": "Recommendation systems are emerging as an important business application with significant economic impact. Currently popular systems include Amazon's book recommendations, Netflix's movie recommendations, and Pandora's music recommendations. In this paper we address the problem of estimating probabilities associated with recommendation system data using non-parametric kernel smoothing. In our estimation we interpret missing items as randomly censored observations and obtain efficient computation schemes using combinatorial properties of generating functions. We demonstrate our approach with several case studies involving real world movie recommendation data. The results are comparable with state-of-the-art techniques while also providing probabilistic preference estimates outside the scope of traditional recommender systems.", "source": "arxiv/ml"}
{"id": "arxiv:744", "title": "Agnostic Learning of Monomials by Halfspaces is Hard", "text": "We prove the following strong hardness result for learning: Given a distribution of labeled examples from the hypercube such that there exists a monomial consistent with $(1-\\eps)$ of the examples, it is NP-hard to find a halfspace that is correct on $(1/2+\\eps)$ of the examples, for arbitrary constants $\\eps > 0$. In learning theory terms, weak agnostic learning of monomials is hard, even if one is allowed to output a hypothesis from the much bigger concept class of halfspaces. This hardness result subsumes a long line of previous results, including two recent hardness results for the proper learning of monomials and halfspaces. As an immediate corollary of our result we show that weak agnostic learning of decision lists is NP-hard. Our techniques are quite different from previous hardness proofs for learning. We define distributions on positive and negative examples for monomials whose first few moments match. We use the invariance principle to argue that regular halfspaces (all of whose coefficients have small absolute value relative to the total $\\ell_2$ norm) cannot distinguish between distributions whose first few moments match. For highly non-regular subspaces, we use a structural lemma from recent work on fooling halfspaces to argue that they are ``junta-like'' and one can zero out all but the top few coefficients without affecting the performance of the halfspace. The top few coefficients form the natural list decoding of a halfspace in the context of dictatorship tests/Label Cover reductions. We note that unlike previous invariance principle based proofs which are only known to give Unique-Games hardness, we are able to reduce from a version of Label Cover problem that is known to be NP-hard. This has inspired follow-up work on bypassing the Unique Games conjecture in some optimal geometric inapproximability results.", "source": "arxiv/ml"}
{"id": "arxiv:745", "title": "Closed-set-based Discovery of Bases of Association Rules", "text": "The output of an association rule miner is often huge in practice. This is why several concise lossless representations have been proposed, such as the \"essential\" or \"representative\" rules. We revisit the algorithm given by Kryszkiewicz (Int. Symp. Intelligent Data Analysis 2001, Springer-Verlag LNCS 2189, 350-359) for mining representative rules. We show that its output is sometimes incomplete, due to an oversight in its mathematical validation. We propose alternative complete generators and we extend the approach to an existing closure-aware basis similar to, and often smaller than, the representative rules, namely the basis B*.", "source": "arxiv/ml"}
{"id": "arxiv:746", "title": "Border Algorithms for Computing Hasse Diagrams of Arbitrary Lattices", "text": "The Border algorithm and the iPred algorithm find the Hasse diagrams of FCA lattices. We show that they can be generalized to arbitrary lattices. In the case of iPred, this requires the identification of a join-semilattice homomorphism into a distributive lattice.", "source": "arxiv/ml"}
{"id": "arxiv:747", "title": "An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA", "text": "Many problems in machine learning and statistics can be formulated as (generalized) eigenproblems. In terms of the associated optimization problem, computing linear eigenvectors amounts to finding critical points of a quadratic function subject to quadratic constraints. In this paper we show that a certain class of constrained optimization problems with nonquadratic objective and constraints can be understood as nonlinear eigenproblems. We derive a generalization of the inverse power method which is guaranteed to converge to a nonlinear eigenvector. We apply the inverse power method to 1-spectral clustering and sparse PCA which can naturally be formulated as nonlinear eigenproblems. In both applications we achieve state-of-the-art results in terms of solution quality and runtime. Moving beyond the standard eigenproblem should be useful also in many other applications and our inverse power method can be easily adapted to new problems.", "source": "arxiv/ml"}
{"id": "arxiv:748", "title": "Automated Query Learning with Wikipedia and Genetic Programming", "text": "Most of the existing information retrieval systems are based on bag of words model and are not equipped with common world knowledge. Work has been done towards improving the efficiency of such systems by using intelligent algorithms to generate search queries, however, not much research has been done in the direction of incorporating human-and-society level knowledge in the queries. This paper is one of the first attempts where such information is incorporated into the search queries using Wikipedia semantics. The paper presents an essential shift from conventional token based queries to concept based queries, leading to an enhanced efficiency of information retrieval systems. To efficiently handle the automated query learning problem, we propose Wikipedia-based Evolutionary Semantics (Wiki-ES) framework where concept based queries are learnt using a co-evolving evolutionary procedure. Learning concept based queries using an intelligent evolutionary procedure yields significant improvement in performance which is shown through an extensive study using Reuters newswire documents. Comparison of the proposed framework is performed with other information retrieval systems. Concept based approach has also been implemented on other information retrieval systems to justify the effectiveness of a transition from token based queries to concept based queries.", "source": "arxiv/ml"}
{"id": "arxiv:749", "title": "Generalized Species Sampling Priors with Latent Beta reinforcements", "text": "Many popular Bayesian nonparametric priors can be characterized in terms of exchangeable species sampling sequences. However, in some applications, exchangeability may not be appropriate. We introduce a {novel and probabilistically coherent family of non-exchangeable species sampling sequences characterized by a tractable predictive probability function with weights driven by a sequence of independent Beta random variables. We compare their theoretical clustering properties with those of the Dirichlet Process and the two parameters Poisson-Dirichlet process. The proposed construction provides a complete characterization of the joint process, differently from existing work. We then propose the use of such process as prior distribution in a hierarchical Bayes modeling framework, and we describe a Markov Chain Monte Carlo sampler for posterior inference. We evaluate the performance of the prior and the robustness of the resulting inference in a simulation study, providing a comparison with popular Dirichlet Processes mixtures and Hidden Markov Models. Finally, we develop an application to the detection of chromosomal aberrations in breast cancer by leveraging array CGH data.", "source": "arxiv/ml"}
{"id": "arxiv:750", "title": "Efficient Optimization of Performance Measures by Classifier Adaptation", "text": "In practical applications, machine learning algorithms are often needed to learn classifiers that optimize domain specific performance measures. Previously, the research has focused on learning the needed classifier in isolation, yet learning nonlinear classifier for nonlinear and nonsmooth performance measures is still hard. In this paper, rather than learning the needed classifier by optimizing specific performance measure directly, we circumvent this problem by proposing a novel two-step approach called as CAPO, namely to first train nonlinear auxiliary classifiers with existing learning methods, and then to adapt auxiliary classifiers for specific performance measures. In the first step, auxiliary classifiers can be obtained efficiently by taking off-the-shelf learning algorithms. For the second step, we show that the classifier adaptation problem can be reduced to a quadratic program problem, which is similar to linear SVMperf and can be efficiently solved. By exploiting nonlinear auxiliary classifiers, CAPO can generate nonlinear classifier which optimizes a large variety of performance measures including all the performance measure based on the contingency table and AUC, whilst keeping high computational efficiency. Empirical studies show that CAPO is effective and of high computational efficiency, and even it is more efficient than linear SVMperf.", "source": "arxiv/ml"}
{"id": "arxiv:751", "title": "Split Bregman Method for Sparse Inverse Covariance Estimation with Matrix Iteration Acceleration", "text": "We consider the problem of estimating the inverse covariance matrix by maximizing the likelihood function with a penalty added to encourage the sparsity of the resulting matrix. We propose a new approach based on the split Bregman method to solve the regularized maximum likelihood estimation problem. We show that our method is significantly faster than the widely used graphical lasso method, which is based on blockwise coordinate descent, on both artificial and real-world data. More importantly, different from the graphical lasso, the split Bregman based method is much more general, and can be applied to a class of regularization terms other than the $\\ell_1$ norm", "source": "arxiv/ml"}
{"id": "arxiv:752", "title": "Optimal Distributed Online Prediction using Mini-Batches", "text": "Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly common to encounter situations where a single processor cannot keep up with the high rate at which inputs arrive. In this work, we present the \\emph{distributed mini-batch} algorithm, a method of converting many serial gradient-based online prediction algorithms into distributed algorithms. We prove a regret bound for this method that is asymptotically optimal for smooth convex loss functions and stochastic inputs. Moreover, our analysis explicitly takes into account communication latencies between nodes in the distributed environment. We show how our method can be used to solve the closely-related distributed stochastic optimization problem, achieving an asymptotically linear speed-up over multiple processors. Finally, we demonstrate the merits of our approach on a web-scale online prediction problem.", "source": "arxiv/ml"}
{"id": "arxiv:753", "title": "Robust Distributed Online Prediction", "text": "The standard model of online prediction deals with serial processing of inputs by a single processor. However, in large-scale online prediction problems, where inputs arrive at a high rate, an increasingly common necessity is to distribute the computation across several processors. A non-trivial challenge is to design distributed algorithms for online prediction, which maintain good regret guarantees. In \\cite{DMB}, we presented the DMB algorithm, which is a generic framework to convert any serial gradient-based online prediction algorithm into a distributed algorithm. Moreover, its regret guarantee is asymptotically optimal for smooth convex loss functions and stochastic inputs. On the flip side, it is fragile to many types of failures that are common in distributed environments. In this companion paper, we present variants of the DMB algorithm, which are resilient to many types of network failures, and tolerant to varying performance of the computing nodes.", "source": "arxiv/ml"}
{"id": "arxiv:754", "title": "Shaping Level Sets with Submodular Functions", "text": "We consider a class of sparsity-inducing regularization terms based on submodular functions. While previous work has focused on non-decreasing functions, we explore symmetric submodular functions and their \\lova extensions. We show that the Lovasz extension may be seen as the convex envelope of a function that depends on level sets (i.e., the set of indices whose corresponding components of the underlying predictor are greater than a given constant): this leads to a class of convex structured regularization terms that impose prior knowledge on the level sets, and not only on the supports of the underlying predictors. We provide a unified set of optimization algorithms, such as proximal operators, and theoretical guarantees (allowed level sets and recovery conditions). By selecting specific submodular functions, we give a new interpretation to known norms, such as the total variation; we also define new norms, in particular ones that are based on order statistics with application to clustering and outlier detection, and on noisy cuts in graphs with application to change point detection in the presence of outliers.", "source": "arxiv/ml"}
{"id": "arxiv:755", "title": "Bridging the Gap between Reinforcement Learning and Knowledge Representation: A Logical Off- and On-Policy Framework", "text": "Knowledge Representation is important issue in reinforcement learning. In this paper, we bridge the gap between reinforcement learning and knowledge representation, by providing a rich knowledge representation framework, based on normal logic programs with answer set semantics, that is capable of solving model-free reinforcement learning problems for more complex do-mains and exploits the domain-specific knowledge. We prove the correctness of our approach. We show that the complexity of finding an offline and online policy for a model-free reinforcement learning problem in our approach is NP-complete. Moreover, we show that any model-free reinforcement learning problem in MDP environment can be encoded as a SAT problem. The importance of that is model-free reinforcement", "source": "arxiv/ml"}
{"id": "arxiv:756", "title": "Low-Rank Structure Learning via Log-Sum Heuristic Recovery", "text": "Recovering intrinsic data structure from corrupted observations plays an important role in various tasks in the communities of machine learning and signal processing. In this paper, we propose a novel model, named log-sum heuristic recovery (LHR), to learn the essential low-rank structure from corrupted data. Different from traditional approaches, which directly utilize $\\ell_1$ norm to measure the sparseness, LHR introduces a more reasonable log-sum measurement to enhance the sparsity in both the intrinsic low-rank structure and in the sparse corruptions. Although the proposed LHR optimization is no longer convex, it still can be effectively solved by a majorization-minimization (MM) type algorithm, with which the non-convex objective function is iteratively replaced by its convex surrogate and LHR finally falls into the general framework of reweighed approaches. We prove that the MM-type algorithm can converge to a stationary point after successive iteration. We test the performance of our proposed model by applying it to solve two typical problems: robust principal component analysis (RPCA) and low-rank representation (LRR). For RPCA, we compare LHR with the benchmark Principal Component Pursuit (PCP) method from both the perspectives of simulations and practical applications. For LRR, we apply LHR to compute the low-rank representation matrix for motion segmentation and stock clustering. Experimental results on low rank structure learning demonstrate that the proposed Log-sum based model performs much better than the $\\ell_1$-based method on for data with higher rank and with denser corruptions.", "source": "arxiv/ml"}
{"id": "arxiv:757", "title": "Context Aware End-to-End Connectivity Management", "text": "In a dynamic heterogeneous environment, such as pervasive and ubiquitous computing, context-aware adaptation is a key concept to meet the varying requirements of different users. Connectivity is an important context source that can be utilized for optimal management of diverse networking resources. Application QoS (Quality of service) is another important issue that should be taken into consideration for design of a context-aware system. This paper presents connectivity from the view point of context awareness, identifies various relevant raw connectivity contexts, and discusses how high-level context information can be abstracted from the raw context information. Further, rich context information is utilized in various policy representation with respect to user profile and preference, application characteristics, device capability, and network QoS conditions. Finally, a context-aware end-to-end evaluation algorithm is presented for adaptive connectivity management in a multi-access wireless network. Unlike the currently existing algorithms, the proposed algorithm takes into account user QoS parameters, and therefore, it is more practical.", "source": "arxiv/ml"}
{"id": "arxiv:758", "title": "A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning", "text": "We present a tutorial on Bayesian optimization, a method of finding the maximum of expensive cost functions. Bayesian optimization employs the Bayesian technique of setting a prior over the objective function and combining it with evidence to get a posterior function. This permits a utility-based selection of the next observation to make on the objective function, which must take into account both exploration (sampling from areas of high uncertainty) and exploitation (sampling areas likely to offer improvement over the current best observation). We also present two detailed extensions of Bayesian optimization, with experiments---active user modelling with preferences, and hierarchical reinforcement learning---and a discussion of the pros and cons of Bayesian optimization based on our experiences.", "source": "arxiv/ml"}
{"id": "arxiv:759", "title": "Inverse-Category-Frequency based supervised term weighting scheme for text categorization", "text": "Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs. The widely used term weighting scheme in text categorization, i.e., tf.idf, is originated from information retrieval (IR) field. The intuition behind idf for text categorization seems less reasonable than IR. In this paper, we introduce inverse category frequency (icf) into term weighting scheme and propose two novel approaches, i.e., tf.icf and icf-based supervised term weighting schemes. The tf.icf adopts icf to substitute idf factor and favors terms occurring in fewer categories, rather than fewer documents. And the icf-based approach combines icf and relevance frequency (rf) to weight terms in a supervised way. Our cross-classifier and cross-corpus experiments have shown that our proposed approaches are superior or comparable to six supervised term weighting schemes and three traditional schemes in terms of macro-F1 and micro-F1.", "source": "arxiv/ml"}
{"id": "arxiv:760", "title": "On the Combinatorial Multi-Armed Bandit Problem with Markovian Rewards", "text": "We consider a combinatorial generalization of the classical multi-armed bandit problem that is defined as follows. There is a given bipartite graph of $M$ users and $N \\geq M$ resources. For each user-resource pair $(i,j)$, there is an associated state that evolves as an aperiodic irreducible finite-state Markov chain with unknown parameters, with transitions occurring each time the particular user $i$ is allocated resource $j$. The user $i$ receives a reward that depends on the corresponding state each time it is allocated the resource $j$. The system objective is to learn the best matching of users to resources so that the long-term sum of the rewards received by all users is maximized. This corresponds to minimizing regret, defined here as the gap between the expected total reward that can be obtained by the best-possible static matching and the expected total reward that can be achieved by a given algorithm. We present a polynomial-storage and polynomial-complexity-per-step matching-learning algorithm for this problem. We show that this algorithm can achieve a regret that is uniformly arbitrarily close to logarithmic in time and polynomial in the number of users and resources. This formulation is broadly applicable to scheduling and switching problems in networks and significantly extends prior results in the area.", "source": "arxiv/ml"}
{"id": "arxiv:761", "title": "Analysis of Agglomerative Clustering", "text": "The diameter $k$-clustering problem is the problem of partitioning a finite subset of $\\mathbb{R}^d$ into $k$ subsets called clusters such that the maximum diameter of the clusters is minimized. One early clustering algorithm that computes a hierarchy of approximate solutions to this problem (for all values of $k$) is the agglomerative clustering algorithm with the complete linkage strategy. For decades, this algorithm has been widely used by practitioners. However, it is not well studied theoretically. In this paper, we analyze the agglomerative complete linkage clustering algorithm. Assuming that the dimension $d$ is a constant, we show that for any $k$ the solution computed by this algorithm is an $O(\\log k)$-approximation to the diameter $k$-clustering problem. Our analysis does not only hold for the Euclidean distance but for any metric that is based on a norm. Furthermore, we analyze the closely related $k$-center and discrete $k$-center problem. For the corresponding agglomerative algorithms, we deduce an approximation factor of $O(\\log k)$ as well.", "source": "arxiv/ml"}
{"id": "arxiv:762", "title": "Queue-Aware Dynamic Clustering and Power Allocation for Network MIMO Systems via Distributive Stochastic Learning", "text": "In this paper, we propose a two-timescale delay-optimal dynamic clustering and power allocation design for downlink network MIMO systems. The dynamic clustering control is adaptive to the global queue state information (GQSI) only and computed at the base station controller (BSC) over a longer time scale. On the other hand, the power allocations of all the BSs in one cluster are adaptive to both intra-cluster channel state information (CCSI) and intra-cluster queue state information (CQSI), and computed at the cluster manager (CM) over a shorter time scale. We show that the two-timescale delay-optimal control can be formulated as an infinite-horizon average cost Constrained Partially Observed Markov Decision Process (CPOMDP). By exploiting the special problem structure, we shall derive an equivalent Bellman equation in terms of Pattern Selection Q-factor to solve the CPOMDP. To address the distributive requirement and the issue of exponential memory requirement and computational complexity, we approximate the Pattern Selection Q-factor by the sum of Per-cluster Potential functions and propose a novel distributive online learning algorithm to estimate the Per-cluster Potential functions (at each CM) as well as the Lagrange multipliers (LM) (at each BS). We show that the proposed distributive online learning algorithm converges almost surely (with probability 1). By exploiting the birth-death structure of the queue dynamics, we further decompose the Per-cluster Potential function into sum of Per-cluster Per-user Potential functions and formulate the instantaneous power allocation as a Per-stage QSI-aware Interference Game played among all the CMs. We also propose a QSI-aware Simultaneous Iterative Water-filling Algorithm (QSIWFA) and show that it can achieve the Nash Equilibrium (NE).", "source": "arxiv/ml"}
{"id": "arxiv:763", "title": "Survey & Experiment: Towards the Learning Accuracy", "text": "To attain the best learning accuracy, people move on with difficulties and frustrations. Though one can optimize the empirical objective using a given set of samples, its generalization ability to the entire sample distribution remains questionable. Even if a fair generalization guarantee is offered, one still wants to know what is to happen if the regularizer is removed, and/or how well the artificial loss (like the hinge loss) relates to the accuracy. For such reason, this report surveys four different trials towards the learning accuracy, embracing the major advances in supervised learning theory in the past four years. Starting from the generic setting of learning, the first two trials introduce the best optimization and generalization bounds for convex learning, and the third trial gets rid of the regularizer. As an innovative attempt, the fourth trial studies the optimization when the objective is exactly the accuracy, in the special case of binary classification. This report also analyzes the last trial through experiments.", "source": "arxiv/ml"}
{"id": "arxiv:764", "title": "Travel Time Estimation Using Floating Car Data", "text": "This report explores the use of machine learning techniques to accurately predict travel times in city streets and highways using floating car data (location information of user vehicles on a road network). The aim of this report is twofold, first we present a general architecture of solving this problem, then present and evaluate few techniques on real floating car data gathered over a month on a 5 Km highway in New Delhi.", "source": "arxiv/ml"}
{"id": "arxiv:765", "title": "How I won the \"Chess Ratings - Elo vs the Rest of the World\" Competition", "text": "This article discusses in detail the rating system that won the kaggle competition \"Chess Ratings: Elo vs the rest of the world\". The competition provided a historical dataset of outcomes for chess games, and aimed to discover whether novel approaches can predict the outcomes of future games, more accurately than the well-known Elo rating system. The winning rating system, called Elo++ in the rest of the article, builds upon the Elo rating system. Like Elo, Elo++ uses a single rating per player and predicts the outcome of a game, by using a logistic curve over the difference in ratings of the players. The major component of Elo++ is a regularization technique that avoids overfitting these ratings. The dataset of chess games and outcomes is relatively small and one has to be careful not to draw \"too many conclusions\" out of the limited data. Many approaches tested in the competition showed signs of such an overfitting. The leader-board was dominated by attempts that did a very good job on a small test dataset, but couldn't generalize well on the private hold-out dataset. The Elo++ regularization takes into account the number of games per player, the recency of these games and the ratings of the opponents. Finally, Elo++ employs a stochastic gradient descent scheme for training the ratings, and uses only two global parameters (white's advantage and regularization constant) that are optimized using cross-validation.", "source": "arxiv/ml"}
{"id": "arxiv:766", "title": "Calibration Using Matrix Completion with Application to Ultrasound Tomography", "text": "We study the calibration process in circular ultrasound tomography devices where the sensor positions deviate from the circumference of a perfect circle. This problem arises in a variety of applications in signal processing ranging from breast imaging to sensor network localization. We introduce a novel method of calibration/localization based on the time-of-flight (ToF) measurements between sensors when the enclosed medium is homogeneous. In the presence of all the pairwise ToFs, one can easily estimate the sensor positions using multi-dimensional scaling (MDS) method. In practice however, due to the transitional behaviour of the sensors and the beam form of the transducers, the ToF measurements for close-by sensors are unavailable. Further, random malfunctioning of the sensors leads to random missing ToF measurements. On top of the missing entries, in practice an unknown time delay is also added to the measurements. In this work, we incorporate the fact that a matrix defined from all the ToF measurements is of rank at most four. In order to estimate the missing ToFs, we apply a state-of-the-art low-rank matrix completion algorithm, OPTSPACE . To find the correct positions of the sensors (our ultimate goal) we then apply MDS. We show analytic bounds on the overall error of the whole process in the presence of noise and hence deduce its robustness. Finally, we confirm the functionality of our method in practice by simulations mimicking the measurements of a circular ultrasound tomography device.", "source": "arxiv/ml"}
{"id": "arxiv:767", "title": "Conditional information and definition of neighbor in categorical random fields", "text": "We show that the definition of neighbor in Markov random fields as defined by Besag (1974) when the joint distribution of the sites is not positive is not well-defined. In a random field with finite number of sites we study the conditions under which giving the value at extra sites will change the belief of an agent about one site. Also the conditions under which the information from some sites is equivalent to giving the value at all other sites is studied. These concepts provide an alternative to the concept of neighbor for general case where the positivity condition of the joint does not hold.", "source": "arxiv/ml"}
{"id": "arxiv:768", "title": "The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning", "text": "In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must be learnt over the whole of state space. It is also proven that policy-gradient learning applied to a greedy policy on a value-function produces a weight update equivalent to a value-gradient weight update, which provides a surprising connection between these two alternative paradigms of reinforcement learning, and a convergence proof for control problems with a value function represented by a general smooth function approximator.", "source": "arxiv/ml"}
{"id": "arxiv:769", "title": "Sparsity regret bounds for individual sequences in online linear regression", "text": "We consider the problem of online linear regression on arbitrary deterministic sequences when the ambient dimension d can be much larger than the number of time rounds T. We introduce the notion of sparsity regret bound, which is a deterministic online counterpart of recent risk bounds derived in the stochastic setting under a sparsity scenario. We prove such regret bounds for an online-learning algorithm called SeqSEW and based on exponential weighting and data-driven truncation. In a second part we apply a parameter-free version of this algorithm to the stochastic setting (regression model with random design). This yields risk bounds of the same flavor as in Dalalyan and Tsybakov (2011) but which solve two questions left open therein. In particular our risk bounds are adaptive (up to a logarithmic factor) to the unknown variance of the noise if the latter is Gaussian. We also address the regression model with fixed design.", "source": "arxiv/ml"}
{"id": "arxiv:770", "title": "Review and Evaluation of Feature Selection Algorithms in Synthetic Problems", "text": "The main purpose of Feature Subset Selection is to find a reduced subset of attributes from a data set described by a feature set. The task of a feature selection algorithm (FSA) is to provide with a computational solution motivated by a certain definition of relevance or by a reliable evaluation measure. In this paper several fundamental algorithms are studied to assess their performance in a controlled experimental scenario. A measure to evaluate FSAs is devised that computes the degree of matching between the output given by a FSA and the known optimal solutions. An extensive experimental study on synthetic problems is carried out to assess the behaviour of the algorithms in terms of solution accuracy and size as a function of the relevance, irrelevance, redundancy and size of the data samples. The controlled experimental conditions facilitate the derivation of better-supported and meaningful conclusions.", "source": "arxiv/ml"}
{"id": "arxiv:771", "title": "Support vector machines/relevance vector machine for remote sensing classification: A review", "text": "Kernel-based machine learning algorithms are based on mapping data from the original input feature space to a kernel feature space of higher dimensionality to solve a linear problem in that space. Over the last decade, kernel based classification and regression approaches such as support vector machines have widely been used in remote sensing as well as in various civil engineering applications. In spite of their better performance with different datasets, support vector machines still suffer from shortcomings such as visualization/interpretation of model, choice of kernel and kernel specific parameter as well as the regularization parameter. Relevance vector machines are another kernel based approach being explored for classification and regression with in last few years. The advantages of the relevance vector machines over the support vector machines is the availability of probabilistic predictions, using arbitrary kernel functions and not requiring setting of the regularization parameter. This paper presents a state-of-the-art review of SVM and RVM in remote sensing and provides some details of their use in other civil engineering application also.", "source": "arxiv/ml"}
{"id": "arxiv:772", "title": "Classification under Data Contamination with Application to Remote Sensing Image Mis-registration", "text": "This work is motivated by the problem of image mis-registration in remote sensing and we are interested in determining the resulting loss in the accuracy of pattern classification. A statistical formulation is given where we propose to use data contamination to model and understand the phenomenon of image mis-registration. This model is widely applicable to many other types of errors as well, for example, measurement errors and gross errors etc. The impact of data contamination on classification is studied under a statistical learning theoretical framework. A closed-form asymptotic bound is established for the resulting loss in classification accuracy, which is less than $\\epsilon/(1-\\epsilon)$ for data contamination of an amount of $\\epsilon$. Our bound is sharper than similar bounds in the domain adaptation literature and, unlike such bounds, it applies to classifiers with an infinite Vapnik-Chervonekis (VC) dimension. Extensive simulations have been conducted on both synthetic and real datasets under various types of data contamination, including label flipping, feature swapping and the replacement of feature values with data generated from a random source such as a Gaussian or Cauchy distribution. Our simulation results show that the bound we derive is fairly tight.", "source": "arxiv/ml"}
{"id": "arxiv:773", "title": "Dyna-H: a heuristic planning reinforcement learning algorithm applied to role-playing-game strategy decision systems", "text": "In a Role-Playing Game, finding optimal trajectories is one of the most important tasks. In fact, the strategy decision system becomes a key component of a game engine. Determining the way in which decisions are taken (online, batch or simulated) and the consumed resources in decision making (e.g. execution time, memory) will influence, in mayor degree, the game performance. When classical search algorithms such as A* can be used, they are the very first option. Nevertheless, such methods rely on precise and complete models of the search space, and there are many interesting scenarios where their application is not possible. Then, model free methods for sequential decision making under uncertainty are the best choice. In this paper, we propose a heuristic planning strategy to incorporate the ability of heuristic-search in path-finding into a Dyna agent. The proposed Dyna-H algorithm, as A* does, selects branches more likely to produce outcomes than other branches. Besides, it has the advantages of being a model-free online reinforcement learning algorithm. The proposal was evaluated against the one-step Q-Learning and Dyna-Q algorithms obtaining excellent experimental results: Dyna-H significantly overcomes both methods in all experiments. We suggest also, a functional analogy between the proposed sampling from worst trajectories heuristic and the role of dreams (e.g. nightmares) in human behavior.", "source": "arxiv/ml"}
{"id": "arxiv:774", "title": "The Role of Normalization in the Belief Propagation Algorithm", "text": "An important part of problems in statistical physics and computer science can be expressed as the computation of marginal probabilities over a Markov Random Field. The belief propagation algorithm, which is an exact procedure to compute these marginals when the underlying graph is a tree, has gained its popularity as an efficient way to approximate them in the more general case. In this paper, we focus on an aspect of the algorithm that did not get that much attention in the literature, which is the effect of the normalization of the messages. We show in particular that, for a large class of normalization strategies, it is possible to focus only on belief convergence. Following this, we express the necessary and sufficient conditions for local stability of a fixed point in terms of the graph structure and the beliefs values at the fixed point. We also explicit some connexion between the normalization constants and the underlying Bethe Free Energy.", "source": "arxiv/ml"}
{"id": "arxiv:775", "title": "Statistical Mechanics of Semi-Supervised Clustering in Sparse Graphs", "text": "We theoretically study semi-supervised clustering in sparse graphs in the presence of pairwise constraints on the cluster assignments of nodes. We focus on bi-cluster graphs, and study the impact of semi-supervision for varying constraint density and overlap between the clusters. Recent results for unsupervised clustering in sparse graphs indicate that there is a critical ratio of within-cluster and between-cluster connectivities below which clusters cannot be recovered with better than random accuracy. The goal of this paper is to examine the impact of pairwise constraints on the clustering accuracy. Our results suggests that the addition of constraints does not provide automatic improvement over the unsupervised case. When the density of the constraints is sufficiently small, their only impact is to shift the detection threshold while preserving the criticality. Conversely, if the density of (hard) constraints is above the percolation threshold, the criticality is suppressed and the detection threshold disappears.", "source": "arxiv/ml"}
{"id": "arxiv:776", "title": "Reproducing Kernel Banach Spaces with the l1 Norm", "text": "Targeting at sparse learning, we construct Banach spaces B of functions on an input space X with the properties that (1) B possesses an l1 norm in the sense that it is isometrically isomorphic to the Banach space of integrable functions on X with respect to the counting measure; (2) point evaluations are continuous linear functionals on B and are representable through a bilinear form with a kernel function; (3) regularized learning schemes on B satisfy the linear representer theorem. Examples of kernel functions admissible for the construction of such spaces are given.", "source": "arxiv/ml"}
{"id": "arxiv:777", "title": "Reproducing Kernel Banach Spaces with the l1 Norm II: Error Analysis for Regularized Least Square Regression", "text": "A typical approach in estimating the learning rate of a regularized learning scheme is to bound the approximation error by the sum of the sampling error, the hypothesis error and the regularization error. Using a reproducing kernel space that satisfies the linear representer theorem brings the advantage of discarding the hypothesis error from the sum automatically. Following this direction, we illustrate how reproducing kernel Banach spaces with the l1 norm can be applied to improve the learning rate estimate of l1-regularization in machine learning.", "source": "arxiv/ml"}
{"id": "arxiv:778", "title": "Close the Gaps: A Learning-while-Doing Algorithm for a Class of Single-Product Revenue Management Problems", "text": "We consider a retailer selling a single product with limited on-hand inventory over a finite selling season. Customer demand arrives according to a Poisson process, the rate of which is influenced by a single action taken by the retailer (such as price adjustment, sales commission, advertisement intensity, etc.). The relationship between the action and the demand rate is not known in advance. However, the retailer is able to learn the optimal action \"on the fly\" as she maximizes her total expected revenue based on the observed demand reactions. Using the pricing problem as an example, we propose a dynamic \"learning-while-doing\" algorithm that only involves function value estimation to achieve a near-optimal performance. Our algorithm employs a series of shrinking price intervals and iteratively tests prices within that interval using a set of carefully chosen parameters. We prove that the convergence rate of our algorithm is among the fastest of all possible algorithms in terms of asymptotic \"regret\" (the relative loss comparing to the full information optimal solution). Our result closes the performance gaps between parametric and non-parametric learning and between a post-price mechanism and a customer-bidding mechanism. Important managerial insight from this research is that the values of information on both the parametric form of the demand function as well as each customer's exact reservation price are less important than prior literature suggests. Our results also suggest that firms would be better off to perform dynamic learning and action concurrently rather than sequentially.", "source": "arxiv/ml"}
{"id": "arxiv:779", "title": "Online Adaptive Decision Fusion Framework Based on Entropic Projections onto Convex Sets with Application to Wildfire Detection in Video", "text": "In this paper, an Entropy functional based online Adaptive Decision Fusion (EADF) framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several sub-algorithms each of which yielding its own decision as a real number centered around zero, representing the confidence level of that particular sub-algorithm. Decision values are linearly combined with weights which are updated online according to an active fusion method based on performing entropic projections onto convex sets describing sub-algorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video based wildfire detection system is developed to evaluate the performance of the algorithm in handling the problems where data arrives sequentially. In this case, the oracle is the security guard of the forest lookout tower verifying the decision of the combined algorithm. Simulation results are presented. The EADF framework is also tested with a standard dataset.", "source": "arxiv/ml"}
{"id": "arxiv:780", "title": "A Primal-Dual Convergence Analysis of Boosting", "text": "Boosting combines weak learners into a predictor with low empirical risk. Its dual constructs a high entropy distribution upon which weak learners and training labels are uncorrelated. This manuscript studies this primal-dual relationship under a broad family of losses, including the exponential loss of AdaBoost and the logistic loss, revealing: - Weak learnability aids the whole loss family: for any {\\epsilon}>0, O(ln(1/{\\epsilon})) iterations suffice to produce a predictor with empirical risk {\\epsilon}-close to the infimum; - The circumstances granting the existence of an empirical risk minimizer may be characterized in terms of the primal and dual problems, yielding a new proof of the known rate O(ln(1/{\\epsilon})); - Arbitrary instances may be decomposed into the above two, granting rate O(1/{\\epsilon}), with a matching lower bound provided for the logistic loss.", "source": "arxiv/ml"}
{"id": "arxiv:781", "title": "Using Feature Weights to Improve Performance of Neural Networks", "text": "Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant features using feature selection, an algorithm can be given this knowledge of feature importance based on expert opinion or prior learning. Learning can be faster and more accurate if learners take feature importance into account. Correlation aided Neural Networks (CANN) is presented which is such an algorithm. CANN treats feature importance as the correlation coefficient between the target attribute and the features. CANN modifies normal feed-forward Neural Network to fit both correlation values and training data. Empirical evaluation shows that CANN is faster and more accurate than applying the two step approach of feature selection and then using normal learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:782", "title": "A Generalized Method for Integrating Rule-based Knowledge into Inductive Methods Through Virtual Sample Creation", "text": "Hybrid learning methods use theoretical knowledge of a domain and a set of classified examples to develop a method for classification. Methods that use domain knowledge have been shown to perform better than inductive learners. However, there is no general method to include domain knowledge into all inductive learning algorithms as all hybrid methods are highly specialized for a particular algorithm. We present an algorithm that will take domain knowledge in the form of propositional rules, generate artificial examples from the rules and also remove instances likely to be flawed. This enriched dataset then can be used by any learning algorithm. Experimental results of different scenarios are shown that demonstrate this method to be more effective than simple inductive learning.", "source": "arxiv/ml"}
{"id": "arxiv:783", "title": "A Novel Template-Based Learning Model", "text": "This article presents a model which is capable of learning and abstracting new concepts based on comparing observations and finding the resemblance between the observations. In the model, the new observations are compared with the templates which have been derived from the previous experiences. In the first stage, the objects are first represented through a geometric description which is used for finding the object boundaries and a descriptor which is inspired by the human visual system and then they are fed into the model. Next, the new observations are identified through comparing them with the previously-learned templates and are used for producing new templates. The comparisons are made based on measures like Euclidean or correlation distance. The new template is created by applying onion-pealing algorithm. The algorithm consecutively uses convex hulls which are made by the points representing the objects. If the new observation is remarkably similar to one of the observed categories, it is no longer utilized in creating a new template. The existing templates are used to provide a description of the new observation. This description is provided in the templates space. Each template represents a dimension of the feature space. The degree of the resemblance each template bears to each object indicates the value associated with the object in that dimension of the templates space. In this way, the description of the new observation becomes more accurate and detailed as the time passes and the experiences increase. We have used this model for learning and recognizing the new polygons in the polygon space. Representing the polygons was made possible through employing a geometric method and a method inspired by human visual system. Various implementations of the model have been compared. The evaluation results of the model prove its efficiency in learning and deriving new templates.", "source": "arxiv/ml"}
{"id": "arxiv:784", "title": "Infinite Multiple Membership Relational Modeling for Complex Networks", "text": "Learning latent structure in complex networks has become an important problem fueled by many types of networked data originating from practically all fields of science. In this paper, we propose a new non-parametric Bayesian multiple-membership latent feature model for networks. Contrary to existing multiple-membership models that scale quadratically in the number of vertices the proposed model scales linearly in the number of links admitting multiple-membership analysis in large scale networks. We demonstrate a connection between the single membership relational model and multiple membership models and show on \"real\" size benchmark network data that accounting for multiple memberships improves the learning of latent structure as measured by link prediction while explicitly accounting for multiple membership result in a more compact representation of the latent structure of networks.", "source": "arxiv/ml"}
{"id": "arxiv:785", "title": "A Complex Networks Approach for Data Clustering", "text": "Many methods have been developed for data clustering, such as k-means, expectation maximization and algorithms based on graph theory. In this latter case, graphs are generally constructed by taking into account the Euclidian distance as a similarity measure, and partitioned using spectral methods. However, these methods are not accurate when the clusters are not well separated. In addition, it is not possible to automatically determine the number of clusters. These limitations can be overcome by taking into account network community identification algorithms. In this work, we propose a methodology for data clustering based on complex networks theory. We compare different metrics for quantifying the similarity between objects and take into account three community finding techniques. This approach is applied to two real-world databases and to two sets of artificially generated data. By comparing our method with traditional clustering approaches, we verify that the proximity measures given by the Chebyshev and Manhattan distances are the most suitable metrics to quantify the similarity between objects. In addition, the community identification method based on the greedy optimization provides the smallest misclassification rates.", "source": "arxiv/ml"}
{"id": "arxiv:786", "title": "Active Markov Information-Theoretic Path Planning for Robotic Environmental Sensing", "text": "Recent research in multi-robot exploration and mapping has focused on sampling environmental fields, which are typically modeled using the Gaussian process (GP). Existing information-theoretic exploration strategies for learning GP-based environmental field maps adopt the non-Markovian problem structure and consequently scale poorly with the length of history of observations. Hence, it becomes computationally impractical to use these strategies for in situ, real-time active sampling. To ease this computational burden, this paper presents a Markov-based approach to efficient information-theoretic path planning for active sampling of GP-based fields. We analyze the time complexity of solving the Markov-based path planning problem, and demonstrate analytically that it scales better than that of deriving the non-Markovian strategies with increasing length of planning horizon. For a class of exploration tasks called the transect sampling task, we provide theoretical guarantees on the active sampling performance of our Markov-based policy, from which ideal environmental field conditions and sampling task settings can be established to limit its performance degradation due to violation of the Markov assumption. Empirical evaluation on real-world temperature and plankton density field data shows that our Markov-based policy can generally achieve active sampling performance comparable to that of the widely-used non-Markovian greedy policies under less favorable realistic field conditions and task settings while enjoying significant computational gain over them.", "source": "arxiv/ml"}
{"id": "arxiv:787", "title": "On the Local Correctness of L^1 Minimization for Dictionary Learning", "text": "The idea that many important classes of signals can be well-represented by linear combinations of a small set of atoms selected from a given dictionary has had dramatic impact on the theory and practice of signal processing. For practical problems in which an appropriate sparsifying dictionary is not known ahead of time, a very popular and successful heuristic is to search for a dictionary that minimizes an appropriate sparsity surrogate over a given set of sample data. While this idea is appealing, the behavior of these algorithms is largely a mystery; although there is a body of empirical evidence suggesting they do learn very effective representations, there is little theory to guarantee when they will behave correctly, or when the learned dictionary can be expected to generalize. In this paper, we take a step towards such a theory. We show that under mild hypotheses, the dictionary learning problem is locally well-posed: the desired solution is indeed a local minimum of the $\\ell^1$ norm. Namely, if $\\mb A \\in \\Re^{m \\times n}$ is an incoherent (and possibly overcomplete) dictionary, and the coefficients $\\mb X \\in \\Re^{n \\times p}$ follow a random sparse model, then with high probability $(\\mb A,\\mb X)$ is a local minimum of the $\\ell^1$ norm over the manifold of factorizations $(\\mb A',\\mb X')$ satisfying $\\mb A' \\mb X' = \\mb Y$, provided the number of samples $p = \\Omega(n^3 k)$. For overcomplete $\\mb A$, this is the first result showing that the dictionary learning problem is locally solvable. Our analysis draws on tools developed for the problem of completing a low-rank matrix from a small subset of its entries, which allow us to overcome a number of technical obstacles; in particular, the absence of the restricted isometry property.", "source": "arxiv/ml"}
{"id": "arxiv:788", "title": "Statistical Compressed Sensing of Gaussian Mixture Models", "text": "A novel framework of compressed sensing, namely statistical compressed sensing (SCS), that aims at efficiently sampling a collection of signals that follow a statistical distribution, and achieving accurate reconstruction on average, is introduced. SCS based on Gaussian models is investigated in depth. For signals that follow a single Gaussian model, with Gaussian or Bernoulli sensing matrices of O(k) measurements, considerably smaller than the O(k log(N/k)) required by conventional CS based on sparse models, where N is the signal dimension, and with an optimal decoder implemented via linear filtering, significantly faster than the pursuit decoders applied in conventional CS, the error of SCS is shown tightly upper bounded by a constant times the best k-term approximation error, with overwhelming probability. The failure probability is also significantly smaller than that of conventional sparsity-oriented CS. Stronger yet simpler results further show that for any sensing matrix, the error of Gaussian SCS is upper bounded by a constant times the best k-term approximation with probability one, and the bound constant can be efficiently calculated. For Gaussian mixture models (GMMs), that assume multiple Gaussian distributions and that each signal follows one of them with an unknown index, a piecewise linear estimator is introduced to decode SCS. The accuracy of model selection, at the heart of the piecewise linear decoder, is analyzed in terms of the properties of the Gaussian distributions and the number of sensing measurements. A maximum a posteriori expectation-maximization algorithm that iteratively estimates the Gaussian models parameters, the signals model selection, and decodes the signals, is presented for GMM-based SCS. In real image sensing applications, GMM-based SCS is shown to lead to improved results compared to conventional CS, at a considerably lower computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:789", "title": "The VC-Dimension of Queries and Selectivity Estimation Through Sampling", "text": "We develop a novel method, based on the statistical concept of the Vapnik-Chervonenkis dimension, to evaluate the selectivity (output cardinality) of SQL queries - a crucial step in optimizing the execution of large scale database and data-mining operations. The major theoretical contribution of this work, which is of independent interest, is an explicit bound to the VC-dimension of a range space defined by all possible outcomes of a collection (class) of queries. We prove that the VC-dimension is a function of the maximum number of Boolean operations in the selection predicate and of the maximum number of select and join operations in any individual query in the collection, but it is neither a function of the number of queries in the collection nor of the size (number of tuples) of the database. We leverage on this result and develop a method that, given a class of queries, builds a concise random sample of a database, such that with high probability the execution of any query in the class on the sample provides an accurate estimate for the selectivity of the query on the original large database. The error probability holds simultaneously for the selectivity estimates of all queries in the collection, thus the same sample can be used to evaluate the selectivity of multiple queries, and the sample needs to be refreshed only following major changes in the database. The sample representation computed by our method is typically sufficiently small to be stored in main memory. We present extensive experimental results, validating our theoretical analysis and demonstrating the advantage of our technique when compared to complex selectivity estimation techniques used in PostgreSQL and the Microsoft SQL Server.", "source": "arxiv/ml"}
{"id": "arxiv:790", "title": "Spatially-Aware Comparison and Consensus for Clusterings", "text": "This paper proposes a new distance metric between clusterings that incorporates information about the spatial distribution of points and clusters. Our approach builds on the idea of a Hilbert space-based representation of clusters as a combination of the representations of their constituent points. We use this representation and the underlying metric to design a spatially-aware consensus clustering procedure. This consensus procedure is implemented via a novel reduction to Euclidean clustering, and is both simple and efficient. All of our results apply to both soft and hard clusterings. We accompany these algorithms with a detailed experimental evaluation that demonstrates the efficiency and quality of our techniques.", "source": "arxiv/ml"}
{"id": "arxiv:791", "title": "Statistical methods for tissue array images - algorithmic scoring and co-training", "text": "Recent advances in tissue microarray technology have allowed immunohistochemistry to become a powerful medium-to-high throughput analysis tool, particularly for the validation of diagnostic and prognostic biomarkers. However, as study size grows, the manual evaluation of these assays becomes a prohibitive limitation; it vastly reduces throughput and greatly increases variability and expense. We propose an algorithm - Tissue Array Co-Occurrence Matrix Analysis (TACOMA) - for quantifying cellular phenotypes based on textural regularity summarized by local inter-pixel relationships. The algorithm can be easily trained for any staining pattern, is absent of sensitive tuning parameters and has the ability to report salient pixels in an image that contribute to its score. Pathologists' input via informative training patches is an important aspect of the algorithm that allows the training for any specific marker or cell type. With co-training, the error rate of TACOMA can be reduced substantially for a very small training sample (e.g., with size 30). We give theoretical insights into the success of co-training via thinning of the feature set in a high-dimensional setting when there is \"sufficient\" redundancy among the features. TACOMA is flexible, transparent and provides a scoring process that can be evaluated with clarity and confidence. In a study based on an estrogen receptor (ER) marker, we show that TACOMA is comparable to, or outperforms, pathologists' performance in terms of accuracy and repeatability.", "source": "arxiv/ml"}
{"id": "arxiv:792", "title": "EigenNet: A Bayesian hybrid of generative and conditional models for sparse learning", "text": "It is a challenging task to select correlated variables in a high dimensional space. To address this challenge, the elastic net has been developed and successfully applied to many applications. Despite its great success, the elastic net does not explicitly use correlation information embedded in data to select correlated variables. To overcome this limitation, we present a novel Bayesian hybrid model, the EigenNet, that uses the eigenstructures of data to guide variable selection. Specifically, it integrates a sparse conditional classification model with a generative model capturing variable correlations in a principled Bayesian framework. We reparameterize the hybrid model in the eigenspace to avoid overfiting and to increase the computational efficiency of its MCMC sampler. Furthermore, we provide an alternative view to the EigenNet from a regularization perspective: the EigenNet has an adaptive eigenspace-based composite regularizer, which naturally generalizes the $l_{1/2}$ regularizer used by the elastic net. Experiments on synthetic and real data show that the EigenNet significantly outperforms the lasso, the elastic net, and the Bayesian lasso in terms of prediction accuracy, especially when the number of training samples is smaller than the number of variables.", "source": "arxiv/ml"}
{"id": "arxiv:793", "title": "Evidence Feed Forward Hidden Markov Model: A New Type of Hidden Markov Model", "text": "The ability to predict the intentions of people based solely on their visual actions is a skill only performed by humans and animals. The intelligence of current computer algorithms has not reached this level of complexity, but there are several research efforts that are working towards it. With the number of classification algorithms available, it is hard to determine which algorithm works best for a particular situation. In classification of visual human intent data, Hidden Markov Models (HMM), and their variants, are leading candidates. The inability of HMMs to provide a probability in the observation to observation linkages is a big downfall in this classification technique. If a person is visually identifying an action of another person, they monitor patterns in the observations. By estimating the next observation, people have the ability to summarize the actions, and thus determine, with pretty good accuracy, the intention of the person performing the action. These visual cues and linkages are important in creating intelligent algorithms for determining human actions based on visual observations. The Evidence Feed Forward Hidden Markov Model is a newly developed algorithm which provides observation to observation linkages. The following research addresses the theory behind Evidence Feed Forward HMMs, provides mathematical proofs of their learning of these parameters to optimize the likelihood of observations with a Evidence Feed Forwards HMM, which is important in all computational intelligence algorithm, and gives comparative examples with standard HMMs in classification of both visual action data and measurement data; thus providing a strong base for Evidence Feed Forward HMMs in classification of many types of problems.", "source": "arxiv/ml"}
{"id": "arxiv:794", "title": "Collective Classification of Textual Documents by Guided Self-Organization in T-Cell Cross-Regulation Dynamics", "text": "We present and study an agent-based model of T-Cell cross-regulation in the adaptive immune system, which we apply to binary classification. Our method expands an existing analytical model of T-cell cross-regulation (Carneiro et al. in Immunol Rev 216(1):48-68, 2007) that was used to study the self-organizing dynamics of a single population of T-Cells in interaction with an idealized antigen presenting cell capable of presenting a single antigen. With agent-based modeling we are able to study the self-organizing dynamics of multiple populations of distinct T-cells which interact via antigen presenting cells that present hundreds of distinct antigens. Moreover, we show that such self-organizing dynamics can be guided to produce an effective binary classification of antigens, which is competitive with existing machine learning methods when applied to biomedical text classification. More specifically, here we test our model on a dataset of publicly available full-text biomedical articles provided by the BioCreative challenge (Krallinger in The biocreative ii. 5 challenge overview, p 19, 2009). We study the robustness of our model's parameter configurations, and show that it leads to encouraging results comparable to state-of-the-art classifiers. Our results help us understand both T-cell cross-regulation as a general principle of guided self-organization, as well as its applicability to document classification. Therefore, we show that our bio-inspired algorithm is a promising novel method for biomedical article classification and for binary document classification in general.", "source": "arxiv/ml"}
{"id": "arxiv:795", "title": "Phase transition in the detection of modules in sparse networks", "text": "We present an asymptotically exact analysis of the problem of detecting communities in sparse random networks. Our results are also applicable to detection of functional modules, partitions, and colorings in noisy planted models. Using a cavity method analysis, we unveil a phase transition from a region where the original group assignment is undetectable to one where detection is possible. In some cases, the detectable region splits into an algorithmically hard region and an easy one. Our approach naturally translates into a practical algorithm for detecting modules in sparse networks, and learning the parameters of the underlying model.", "source": "arxiv/ml"}
{"id": "arxiv:796", "title": "Refinement of Operator-valued Reproducing Kernels", "text": "This paper studies the construction of a refinement kernel for a given operator-valued reproducing kernel such that the vector-valued reproducing kernel Hilbert space of the refinement kernel contains that of the given one as a subspace. The study is motivated from the need of updating the current operator-valued reproducing kernel in multi-task learning when underfitting or overfitting occurs. Numerical simulations confirm that the established refinement kernel method is able to meet this need. Various characterizations are provided based on feature maps and vector-valued integral representations of operator-valued reproducing kernels. Concrete examples of refining translation invariant and finite Hilbert-Schmidt operator-valued reproducing kernels are provided. Other examples include refinement of Hessian of scalar-valued translation-invariant kernels and transformation kernels. Existence and properties of operator-valued reproducing kernels preserved during the refinement process are also investigated.", "source": "arxiv/ml"}
{"id": "arxiv:797", "title": "An Introduction to Artificial Prediction Markets for Classification", "text": "Prediction markets are used in real life to predict outcomes of interest such as presidential elections. This paper presents a mathematical theory of artificial prediction markets for supervised learning of conditional probability estimators. The artificial prediction market is a novel method for fusing the prediction information of features or trained classifiers, where the fusion result is the contract price on the possible outcomes. The market can be trained online by updating the participants' budgets using training examples. Inspired by the real prediction markets, the equations that govern the market are derived from simple and reasonable assumptions. Efficient numerical algorithms are presented for solving these equations. The obtained artificial prediction market is shown to be a maximum likelihood estimator. It generalizes linear aggregation, existent in boosting and random forest, as well as logistic regression and some kernel methods. Furthermore, the market mechanism allows the aggregation of specialized classifiers that participate only on specific instances. Experimental comparisons show that the artificial prediction markets often outperform random forest and implicit online learning on synthetic data and real UCI datasets. Moreover, an extensive evaluation for pelvic and abdominal lymph node detection in CT data shows that the prediction market improves adaboost's detection rate from 79.6% to 81.2% at 3 false positives/volume.", "source": "arxiv/ml"}
{"id": "arxiv:798", "title": "From Machine Learning to Machine Reasoning", "text": "A plausible definition of \"reasoning\" could be \"algebraically manipulating previously acquired knowledge in order to answer a new question\". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be viewed as an algebraic operation in a space of models. The resulting model answers a new question, that is, converting the image of a text page into a computer readable text. This observation suggests a conceptual continuity between algebraically rich inference systems, such as logical or probabilistic inference, and simple manipulations, such as the mere concatenation of trainable learning systems. Therefore, instead of trying to bridge the gap between machine learning systems and sophisticated \"all-purpose\" inference mechanisms, we can instead algebraically enrich the set of manipulations applicable to training systems, and build reasoning capabilities from the ground up.", "source": "arxiv/ml"}
{"id": "arxiv:799", "title": "Universal Learning Theory", "text": "This encyclopedic article gives a mini-introduction into the theory of universal learning, founded by Ray Solomonoff in the 1960s and significantly developed and extended in the last decade. It explains the spirit of universal learning, but necessarily glosses over technical subtleties.", "source": "arxiv/ml"}
{"id": "arxiv:800", "title": "The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond", "text": "This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a uniformly better regret bound than UCB or UCB2; second, in the special case of Bernoulli rewards, it reaches the lower bound of Lai and Robbins. Furthermore, we show that simple adaptations of the KL-UCB algorithm are also optimal for specific classes of (possibly unbounded) rewards, including those generated from exponential families of distributions. A large-scale numerical study comparing KL-UCB with its main competitors (UCB, UCB2, UCB-Tuned, UCB-V, DMED) shows that KL-UCB is remarkably efficient and stable, including for short time horizons. KL-UCB is also the only method that always performs better than the basic UCB policy. Our regret bounds rely on deviations results of independent interest which are stated and proved in the Appendix. As a by-product, we also obtain an improved regret bound for the standard UCB algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:801", "title": "A General Framework for Development of the Cortex-like Visual Object Recognition System: Waves of Spikes, Predictive Coding and Universal Dictionary of Features", "text": "This study is focused on the development of the cortex-like visual object recognition system. We propose a general framework, which consists of three hierarchical levels (modules). These modules functionally correspond to the V1, V4 and IT areas. Both bottom-up and top-down connections between the hierarchical levels V4 and IT are employed. The higher the degree of matching between the input and the preferred stimulus, the shorter the response time of the neuron. Therefore information about a single stimulus is distributed in time and is transmitted by the waves of spikes. The reciprocal connections and waves of spikes implement predictive coding: an initial hypothesis is generated on the basis of information delivered by the first wave of spikes and is tested with the information carried by the consecutive waves. The development is considered as extraction and accumulation of features in V4 and objects in IT. Once stored a feature can be disposed, if rarely activated. This cause update of feature repository. Consequently, objects in IT are also updated. This illustrates the growing process and dynamical change of topological structures of V4, IT and connections between these areas.", "source": "arxiv/ml"}
{"id": "arxiv:802", "title": "Transductive Ordinal Regression", "text": "Ordinal regression is commonly formulated as a multi-class problem with ordinal constraints. The challenge of designing accurate classifiers for ordinal regression generally increases with the number of classes involved, due to the large number of labeled patterns that are needed. The availability of ordinal class labels, however, is often costly to calibrate or difficult to obtain. Unlabeled patterns, on the other hand, often exist in much greater abundance and are freely available. To take benefits from the abundance of unlabeled patterns, we present a novel transductive learning paradigm for ordinal regression in this paper, namely Transductive Ordinal Regression (TOR). The key challenge of the present study lies in the precise estimation of both the ordinal class label of the unlabeled data and the decision functions of the ordinal classes, simultaneously. The core elements of the proposed TOR include an objective function that caters to several commonly used loss functions casted in transductive settings, for general ordinal regression. A label swapping scheme that facilitates a strictly monotonic decrease in the objective function value is also introduced. Extensive numerical studies on commonly used benchmark datasets including the real world sentiment prediction problem are then presented to showcase the characteristics and efficacies of the proposed transductive ordinal regression. Further, comparisons to recent state-of-the-art ordinal regression methods demonstrate the introduced transductive learning paradigm for ordinal regression led to the robust and improved performance.", "source": "arxiv/ml"}
{"id": "arxiv:803", "title": "Decentralized Restless Bandit with Multiple Players and Unknown Dynamics", "text": "We consider decentralized restless multi-armed bandit problems with unknown dynamics and multiple players. The reward state of each arm transits according to an unknown Markovian rule when it is played and evolves according to an arbitrary unknown random process when it is passive. Players activating the same arm at the same time collide and suffer from reward loss. The objective is to maximize the long-term reward by designing a decentralized arm selection policy to address unknown reward models and collisions among players. A decentralized policy is constructed that achieves a regret with logarithmic order when an arbitrary nontrivial bound on certain system parameters is known. When no knowledge about the system is available, we extend the policy to achieve a regret arbitrarily close to the logarithmic order. The result finds applications in communication networks, financial investment, and industrial engineering.", "source": "arxiv/ml"}
{"id": "arxiv:804", "title": "Selecting the rank of truncated SVD by Maximum Approximation Capacity", "text": "Truncated Singular Value Decomposition (SVD) calculates the closest rank-$k$ approximation of a given input matrix. Selecting the appropriate rank $k$ defines a critical model order choice in most applications of SVD. To obtain a principled cut-off criterion for the spectrum, we convert the underlying optimization problem into a noisy channel coding problem. The optimal approximation capacity of this channel controls the appropriate strength of regularization to suppress noise. In simulation experiments, this information theoretic method to determine the optimal rank competes with state-of-the art model selection techniques.", "source": "arxiv/ml"}
{"id": "arxiv:805", "title": "Adaptive Cluster Expansion for Inferring Boltzmann Machines with Noisy Data", "text": "We introduce a procedure to infer the interactions among a set of binary variables, based on their sampled frequencies and pairwise correlations. The algorithm builds the clusters of variables contributing most to the entropy of the inferred Ising model, and rejects the small contributions due to the sampling noise. Our procedure successfully recovers benchmark Ising models even at criticality and in the low temperature phase, and is applied to neurobiological data.", "source": "arxiv/ml"}
{"id": "arxiv:806", "title": "Online Learning of Rested and Restless Bandits", "text": "In this paper we study the online learning problem involving rested and restless multiarmed bandits with multiple plays. The system consists of a single player/user and a set of K finite-state discrete-time Markov chains (arms) with unknown state spaces and statistics. At each time step the player can play M arms. The objective of the user is to decide for each step which M of the K arms to play over a sequence of trials so as to maximize its long term reward. The restless multiarmed bandit is particularly relevant to the application of opportunistic spectrum access (OSA), where a (secondary) user has access to a set of K channels, each of time-varying condition as a result of random fading and/or certain primary users' activities.", "source": "arxiv/ml"}
{"id": "arxiv:807", "title": "Active Clustering: Robust and Efficient Hierarchical Clustering using Adaptively Selected Similarities", "text": "Hierarchical clustering based on pairwise similarities is a common tool used in a broad range of scientific applications. However, in many problems it may be expensive to obtain or compute similarities between the items to be clustered. This paper investigates the hierarchical clustering of N items based on a small subset of pairwise similarities, significantly less than the complete set of N(N-1)/2 similarities. First, we show that if the intracluster similarities exceed intercluster similarities, then it is possible to correctly determine the hierarchical clustering from as few as 3N log N similarities. We demonstrate this order of magnitude savings in the number of pairwise similarities necessitates sequentially selecting which similarities to obtain in an adaptive fashion, rather than picking them at random. We then propose an active clustering method that is robust to a limited fraction of anomalous similarities, and show how even in the presence of these noisy similarity values we can resolve the hierarchical clustering using only O(N log^2 N) pairwise similarities.", "source": "arxiv/ml"}
{"id": "arxiv:808", "title": "Inferring Disease and Gene Set Associations with Rank Coherence in Networks", "text": "A computational challenge to validate the candidate disease genes identified in a high-throughput genomic study is to elucidate the associations between the set of candidate genes and disease phenotypes. The conventional gene set enrichment analysis often fails to reveal associations between disease phenotypes and the gene sets with a short list of poorly annotated genes, because the existing annotations of disease causative genes are incomplete. We propose a network-based computational approach called rcNet to discover the associations between gene sets and disease phenotypes. Assuming coherent associations between the genes ranked by their relevance to the query gene set, and the disease phenotypes ranked by their relevance to the hidden target disease phenotypes of the query gene set, we formulate a learning framework maximizing the rank coherence with respect to the known disease phenotype-gene associations. An efficient algorithm coupling ridge regression with label propagation, and two variants are introduced to find the optimal solution of the framework. We evaluated the rcNet algorithms and existing baseline methods with both leave-one-out cross-validation and a task of predicting recently discovered disease-gene associations in OMIM. The experiments demonstrated that the rcNet algorithms achieved the best overall rankings compared to the baselines. To further validate the reproducibility of the performance, we applied the algorithms to identify the target diseases of novel candidate disease genes obtained from recent studies of GWAS, DNA copy number variation analysis, and gene expression profiling. The algorithms ranked the target disease of the candidate genes at the top of the rank list in many cases across all the three case studies. The rcNet algorithms are available as a webtool for disease and gene set association analysis at http://compbio.cs.umn.edu/dgsa_rcNet.", "source": "arxiv/ml"}
{"id": "arxiv:809", "title": "Concentration-Based Guarantees for Low-Rank Matrix Reconstruction", "text": "We consider the problem of approximately reconstructing a partially-observed, approximately low-rank matrix. This problem has received much attention lately, mostly using the trace-norm as a surrogate to the rank. Here we study low-rank matrix reconstruction using both the trace-norm, as well as the less-studied max-norm, and present reconstruction guarantees based on existing analysis on the Rademacher complexity of the unit balls of these norms. We show how these are superior in several ways to recently published guarantees based on specialized analysis.", "source": "arxiv/ml"}
{"id": "arxiv:810", "title": "Sparse Signal Recovery with Temporally Correlated Source Vectors Using Sparse Bayesian Learning", "text": "We address the sparse signal recovery problem in the context of multiple measurement vectors (MMV) when elements in each nonzero row of the solution matrix are temporally correlated. Existing algorithms do not consider such temporal correlations and thus their performance degrades significantly with the correlations. In this work, we propose a block sparse Bayesian learning framework which models the temporal correlations. In this framework we derive two sparse Bayesian learning (SBL) algorithms, which have superior recovery performance compared to existing algorithms, especially in the presence of high temporal correlations. Furthermore, our algorithms are better at handling highly underdetermined problems and require less row-sparsity on the solution matrix. We also provide analysis of the global and local minima of their cost function, and show that the SBL cost function has the very desirable property that the global minimum is at the sparsest solution to the MMV problem. Extensive experiments also provide some interesting results that motivate future theoretical research on the MMV model.", "source": "arxiv/ml"}
{"id": "arxiv:811", "title": "Privacy Preserving Spam Filtering", "text": "Email is a private medium of communication, and the inherent privacy constraints form a major obstacle in developing effective spam filtering methods which require access to a large amount of email data belonging to multiple users. To mitigate this problem, we envision a privacy preserving spam filtering system, where the server is able to train and evaluate a logistic regression based spam classifier on the combined email data of all users without being able to observe any emails using primitives such as homomorphic encryption and randomization. We analyze the protocols for correctness and security, and perform experiments of a prototype system on a large scale spam filtering task. State of the art spam filters often use character n-grams as features which result in large sparse data representation, which is not feasible to be used directly with our training and evaluation protocols. We explore various data independent dimensionality reduction which decrease the running time of the protocol making it feasible to use in practice while achieving high accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:812", "title": "Sparse neural networks with large learning diversity", "text": "Coded recurrent neural networks with three levels of sparsity are introduced. The first level is related to the size of messages, much smaller than the number of available neurons. The second one is provided by a particular coding rule, acting as a local constraint in the neural activity. The third one is a characteristic of the low final connection density of the network after the learning phase. Though the proposed network is very simple since it is based on binary neurons and binary connections, it is able to learn a large number of messages and recall them, even in presence of strong erasures. The performance of the network is assessed as a classifier and as an associative memory.", "source": "arxiv/ml"}
{"id": "arxiv:813", "title": "Link Prediction by De-anonymization: How We Won the Kaggle Social Network Challenge", "text": "This paper describes the winning entry to the IJCNN 2011 Social Network Challenge run by Kaggle.com. The goal of the contest was to promote research on real-world link prediction, and the dataset was a graph obtained by crawling the popular Flickr social photo sharing website, with user identities scrubbed. By de-anonymizing much of the competition test set using our own Flickr crawl, we were able to effectively game the competition. Our attack represents a new application of de-anonymization to gaming machine learning contests, suggesting changes in how future competitions should be run. We introduce a new simulated annealing-based weighted graph matching algorithm for the seeding step of de-anonymization. We also show how to combine de-anonymization with link prediction---the latter is required to achieve good performance on the portion of the test set not de-anonymized---for example by training the predictor on the de-anonymized portion of the test set, and combining probabilistic predictions from de-anonymization and link prediction.", "source": "arxiv/ml"}
{"id": "arxiv:814", "title": "Internal Regret with Partial Monitoring. Calibration-Based Optimal Algorithms", "text": "We provide consistent random algorithms for sequential decision under partial monitoring, i.e. when the decision maker does not observe the outcomes but receives instead random feedback signals. Those algorithms have no internal regret in the sense that, on the set of stages where the decision maker chose his action according to a given law, the average payoff could not have been improved in average by using any other fixed law. They are based on a generalization of calibration, no longer defined in terms of a Voronoi diagram but instead of a Laguerre diagram (a more general concept). This allows us to bound, for the first time in this general framework, the expected average internal -- as well as the usual external -- regret at stage $n$ by $O(n^{-1/3})$, which is known to be optimal.", "source": "arxiv/ml"}
{"id": "arxiv:815", "title": "Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions", "text": "We analyze a class of estimators based on convex relaxation for solving high-dimensional matrix decomposition problems. The observations are noisy realizations of a linear transformation $\\mathfrak{X}$ of the sum of an approximately) low rank matrix $\\Theta^\\star$ with a second matrix $\\Gamma^\\star$ endowed with a complementary form of low-dimensional structure; this set-up includes many statistical models of interest, including factor analysis, multi-task regression, and robust covariance estimation. We derive a general theorem that bounds the Frobenius norm error for an estimate of the pair $(\\Theta^\\star, \\Gamma^\\star)$ obtained by solving a convex optimization problem that combines the nuclear norm with a general decomposable regularizer. Our results utilize a \"spikiness\" condition that is related to but milder than singular vector incoherence. We specialize our general result to two cases that have been studied in past work: low rank plus an entrywise sparse matrix, and low rank plus a columnwise sparse matrix. For both models, our theory yields non-asymptotic Frobenius error bounds for both deterministic and stochastic noise matrices, and applies to matrices $\\Theta^\\star$ that can be exactly or approximately low rank, and matrices $\\Gamma^\\star$ that can be exactly or approximately sparse. Moreover, for the case of stochastic noise matrices and the identity observation operator, we establish matching lower bounds on the minimax error. The sharpness of our predictions is confirmed by numerical simulations.", "source": "arxiv/ml"}
{"id": "arxiv:816", "title": "Sparse Bayesian Methods for Low-Rank Matrix Estimation", "text": "Recovery of low-rank matrices has recently seen significant activity in many areas of science and engineering, motivated by recent theoretical results for exact reconstruction guarantees and interesting practical applications. A number of methods have been developed for this recovery problem. However, a principled method for choosing the unknown target rank is generally not provided. In this paper, we present novel recovery algorithms for estimating low-rank matrices in matrix completion and robust principal component analysis based on sparse Bayesian learning (SBL) principles. Starting from a matrix factorization formulation and enforcing the low-rank constraint in the estimates as a sparsity constraint, we develop an approach that is very effective in determining the correct rank while providing high recovery performance. We provide connections with existing methods in other similar problems and empirical results and comparisons with current state-of-the-art methods that illustrate the effectiveness of this approach.", "source": "arxiv/ml"}
{"id": "arxiv:817", "title": "Deformed Statistics Free Energy Model for Source Separation using Unsupervised Learning", "text": "A generalized-statistics variational principle for source separation is formulated by recourse to Tsallis' entropy subjected to the additive duality and employing constraints described by normal averages. The variational principle is amalgamated with Hopfield-like learning rules resulting in an unsupervised learning model. The update rules are formulated with the aid of q-deformed calculus. Numerical examples exemplify the efficacy of this model.", "source": "arxiv/ml"}
{"id": "arxiv:818", "title": "Decision Making Agent Searching for Markov Models in Near-Deterministic World", "text": "Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illustrate the properties of architecture in the near deterministic Ms. Pac-Man game. We analyze the architecture from the point of view of evolutionary, individual, and social learning.", "source": "arxiv/ml"}
{"id": "arxiv:819", "title": "Low Complexity Kolmogorov-Smirnov Modulation Classification", "text": "Kolmogorov-Smirnov (K-S) test-a non-parametric method to measure the goodness of fit, is applied for automatic modulation classification (AMC) in this paper. The basic procedure involves computing the empirical cumulative distribution function (ECDF) of some decision statistic derived from the received signal, and comparing it with the CDFs of the signal under each candidate modulation format. The K-S-based modulation classifier is first developed for AWGN channel, then it is applied to OFDM-SDMA systems to cancel multiuser interference. Regarding the complexity issue of K-S modulation classification, we propose a low-complexity method based on the robustness of the K-S classifier. Extensive simulation results demonstrate that compared with the traditional cumulant-based classifiers, the proposed K-S classifier offers superior classification performance and requires less number of signal samples (thus is fast).", "source": "arxiv/ml"}
{"id": "arxiv:820", "title": "Fast and Faster: A Comparison of Two Streamed Matrix Decomposition Algorithms", "text": "With the explosion of the size of digital dataset, the limiting factor for decomposition algorithms is the \\emph{number of passes} over the input, as the input is often stored out-of-core or even off-site. Moreover, we're only interested in algorithms that operate in \\emph{constant memory} w.r.t. to the input size, so that arbitrarily large input can be processed. In this paper, we present a practical comparison of two such algorithms: a distributed method that operates in a single pass over the input vs. a streamed two-pass stochastic algorithm. The experiments track the effect of distributed computing, oversampling and memory trade-offs on the accuracy and performance of the two algorithms. To ensure meaningful results, we choose the input to be a real dataset, namely the whole of the English Wikipedia, in the application settings of Latent Semantic Analysis.", "source": "arxiv/ml"}
{"id": "arxiv:821", "title": "Named Entity Recognition Using Web Document Corpus", "text": "This paper introduces a named entity recognition approach in textual corpus. This Named Entity (NE) can be a named: location, person, organization, date, time, etc., characterized by instances. A NE is found in texts accompanied by contexts: words that are left or right of the NE. The work mainly aims at identifying contexts inducing the NE's nature. As such, The occurrence of the word \"President\" in a text, means that this word or context may be followed by the name of a president as President \"Obama\". Likewise, a word preceded by the string \"footballer\" induces that this is the name of a footballer. NE recognition may be viewed as a classification method, where every word is assigned to a NE class, regarding the context. The aim of this study is then to identify and classify the contexts that are most relevant to recognize a NE, those which are frequently found with the NE. A learning approach using training corpus: web documents, constructed from learning examples is then suggested. Frequency representations and modified tf-idf representations are used to calculate the context weights associated to context frequency, learning example frequency, and document frequency in the corpus.", "source": "arxiv/ml"}
{"id": "arxiv:822", "title": "Neyman-Pearson classification, convexity and stochastic constraints", "text": "Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss. Given a finite collection of classifiers, we combine them and obtain a new classifier that satisfies simultaneously the two following properties with high probability: (i) its probability of type I error is below a pre-specified level and (ii), it has probability of type II error close to the minimum possible. The proposed classifier is obtained by solving an optimization problem with an empirical objective and an empirical constraint. New techniques to handle such problems are developed and have consequences on chance constrained programming.", "source": "arxiv/ml"}
{"id": "arxiv:823", "title": "A generic trust framework for large-scale open systems using machine learning", "text": "In many large scale distributed systems and on the web, agents need to interact with other unknown agents to carry out some tasks or transactions. The ability to reason about and assess the potential risks in carrying out such transactions is essential for providing a safe and reliable environment. A traditional approach to reason about the trustworthiness of a transaction is to determine the trustworthiness of the specific agent involved, derived from the history of its behavior. As a departure from such traditional trust models, we propose a generic, machine learning approach based trust framework where an agent uses its own previous transactions (with other agents) to build a knowledge base, and utilize this to assess the trustworthiness of a transaction based on associated features, which are capable of distinguishing successful transactions from unsuccessful ones. These features are harnessed using appropriate machine learning algorithms to extract relationships between the potential transaction and previous transactions. The trace driven experiments using real auction dataset show that this approach provides good accuracy and is highly efficient compared to other trust mechanisms, especially when historical information of the specific agent is rare, incomplete or inaccurate.", "source": "arxiv/ml"}
{"id": "arxiv:824", "title": "Multi-label Learning via Structured Decomposition and Group Sparsity", "text": "In multi-label learning, each sample is associated with several labels. Existing works indicate that exploring correlations between labels improve the prediction performance. However, embedding the label correlations into the training process significantly increases the problem size. Moreover, the mapping of the label structure in the feature space is not clear. In this paper, we propose a novel multi-label learning method \"Structured Decomposition + Group Sparsity (SDGS)\". In SDGS, we learn a feature subspace for each label from the structured decomposition of the training data, and predict the labels of a new sample from its group sparse representation on the multi-subspace obtained from the structured decomposition. In particular, in the training stage, we decompose the data matrix $X\\in R^{n\\times p}$ as $X=\\sum_{i=1}^kL^i+S$, wherein the rows of $L^i$ associated with samples that belong to label $i$ are nonzero and consist a low-rank matrix, while the other rows are all-zeros, the residual $S$ is a sparse matrix. The row space of $L_i$ is the feature subspace corresponding to label $i$. This decomposition can be efficiently obtained via randomized optimization. In the prediction stage, we estimate the group sparse representation of a new sample on the multi-subspace via group \\emph{lasso}. The nonzero representation coefficients tend to concentrate on the subspaces of labels that the sample belongs to, and thus an effective prediction can be obtained. We evaluate SDGS on several real datasets and compare it with popular methods. Results verify the effectiveness and efficiency of SDGS.", "source": "arxiv/ml"}
{"id": "arxiv:825", "title": "Natural Language Processing (almost) from Scratch", "text": "We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.", "source": "arxiv/ml"}
{"id": "arxiv:826", "title": "Learning transformed product distributions", "text": "We consider the problem of learning an unknown product distribution $X$ over $\\{0,1\\}^n$ using samples $f(X)$ where $f$ is a \\emph{known} transformation function. Each choice of a transformation function $f$ specifies a learning problem in this framework. Information-theoretic arguments show that for every transformation function $f$ the corresponding learning problem can be solved to accuracy $\\eps$, using $\\tilde{O}(n/\\eps^2)$ examples, by a generic algorithm whose running time may be exponential in $n.$ We show that this learning problem can be computationally intractable even for constant $\\eps$ and rather simple transformation functions. Moreover, the above sample complexity bound is nearly optimal for the general problem, as we give a simple explicit linear transformation function $f(x)=w \\cdot x$ with integer weights $w_i \\leq n$ and prove that the corresponding learning problem requires $\\Omega(n)$ samples. As our main positive result we give a highly efficient algorithm for learning a sum of independent unknown Bernoulli random variables, corresponding to the transformation function $f(x)= \\sum_{i=1}^n x_i$. Our algorithm learns to $\\eps$-accuracy in poly$(n)$ time, using a surprising poly$(1/\\eps)$ number of samples that is independent of $n.$ We also give an efficient algorithm that uses $\\log n \\cdot \\poly(1/\\eps)$ samples but has running time that is only $\\poly(\\log n, 1/\\eps).$", "source": "arxiv/ml"}
{"id": "arxiv:827", "title": "Sparse Volterra and Polynomial Regression Models: Recoverability and Estimation", "text": "Volterra and polynomial regression models play a major role in nonlinear system identification and inference tasks. Exciting applications ranging from neuroscience to genome-wide association analysis build on these models with the additional requirement of parsimony. This requirement has high interpretative value, but unfortunately cannot be met by least-squares based or kernel regression methods. To this end, compressed sampling (CS) approaches, already successful in linear regression settings, can offer a viable alternative. The viability of CS for sparse Volterra and polynomial models is the core theme of this work. A common sparse regression task is initially posed for the two models. Building on (weighted) Lasso-based schemes, an adaptive RLS-type algorithm is developed for sparse polynomial regressions. The identifiability of polynomial models is critically challenged by dimensionality. However, following the CS principle, when these models are sparse, they could be recovered by far fewer measurements. To quantify the sufficient number of measurements for a given level of sparsity, restricted isometry properties (RIP) are investigated in commonly met polynomial regression settings, generalizing known results for their linear counterparts. The merits of the novel (weighted) adaptive CS algorithms to sparse polynomial modeling are verified through synthetic as well as real data tests for genotype-phenotype analysis.", "source": "arxiv/ml"}
{"id": "arxiv:828", "title": "Efficient Multi-Template Learning for Structured Prediction", "text": "Conditional random field (CRF) and Structural Support Vector Machine (Structural SVM) are two state-of-the-art methods for structured prediction which captures the interdependencies among output variables. The success of these methods is attributed to the fact that their discriminative models are able to account for overlapping features on the whole input observations. These features are usually generated by applying a given set of templates on labeled data, but improper templates may lead to degraded performance. To alleviate this issue, in this paper, we propose a novel multiple template learning paradigm to learn structured prediction and the importance of each template simultaneously, so that hundreds of arbitrary templates could be added into the learning model without caution. This paradigm can be formulated as a special multiple kernel learning problem with exponential number of constraints. Then we introduce an efficient cutting plane algorithm to solve this problem in the primal, and its convergence is presented. We also evaluate the proposed learning paradigm on two widely-studied structured prediction tasks, \\emph{i.e.} sequence labeling and dependency parsing. Extensive experimental results show that the proposed method outperforms CRFs and Structural SVMs due to exploiting the importance of each template. Our complexity analysis and empirical results also show that our proposed method is more efficient than OnlineMKL on very sparse and high-dimensional data. We further extend this paradigm for structured prediction using generalized $p$-block norm regularization with $p>1$, and experiments show competitive performances when $p \\in [1,2)$.", "source": "arxiv/ml"}
{"id": "arxiv:829", "title": "Estimating $\\beta$-mixing coefficients", "text": "The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the $\\beta$-mixing rate based on a single stationary sample path and show it is $L_1$-risk consistent.", "source": "arxiv/ml"}
{"id": "arxiv:830", "title": "Generalization error bounds for stationary autoregressive models", "text": "We derive generalization error bounds for stationary univariate autoregressive (AR) models. We show that imposing stationarity is enough to control the Gaussian complexity without further regularization. This lets us use structural risk minimization for model selection. We demonstrate our methods by predicting interest rate movements.", "source": "arxiv/ml"}
{"id": "arxiv:831", "title": "Adapting to Non-stationarity with Growing Expert Ensembles", "text": "When dealing with time series with complex non-stationarities, low retrospective regret on individual realizations is a more appropriate goal than low prospective risk in expectation. Online learning algorithms provide powerful guarantees of this form, and have often been proposed for use with non-stationary processes because of their ability to switch between different forecasters or ``experts''. However, existing methods assume that the set of experts whose forecasts are to be combined are all given at the start, which is not plausible when dealing with a genuinely historical or evolutionary system. We show how to modify the ``fixed shares'' algorithm for tracking the best expert to cope with a steadily growing set of experts, obtained by fitting new models to new data as it becomes available, and obtain regret bounds for the growing ensemble.", "source": "arxiv/ml"}
{"id": "arxiv:832", "title": "A Feature Selection Method for Multivariate Performance Measures", "text": "Feature selection with specific multivariate performance measures is the key to the success of many applications, such as image retrieval and text classification. The existing feature selection methods are usually designed for classification error. In this paper, we propose a generalized sparse regularizer. Based on the proposed regularizer, we present a unified feature selection framework for general loss functions. In particular, we study the novel feature selection paradigm by optimizing multivariate performance measures. The resultant formulation is a challenging problem for high-dimensional data. Hence, a two-layer cutting plane algorithm is proposed to solve this problem, and the convergence is presented. In addition, we adapt the proposed method to optimize multivariate measures for multiple instance learning problems. The analyses by comparing with the state-of-the-art feature selection methods show that the proposed method is superior to others. Extensive experiments on large-scale and high-dimensional real world datasets show that the proposed method outperforms $l_1$-SVM and SVM-RFE when choosing a small subset of features, and achieves significantly improved performances over SVM$^{perf}$ in terms of $F_1$-score.", "source": "arxiv/ml"}
{"id": "arxiv:833", "title": "Localization from Incomplete Noisy Distance Measurements", "text": "We consider the problem of positioning a cloud of points in the Euclidean space $\\mathbb{R}^d$, using noisy measurements of a subset of pairwise distances. This task has applications in various areas, such as sensor network localization and reconstruction of protein conformations from NMR measurements. Also, it is closely related to dimensionality reduction problems and manifold learning, where the goal is to learn the underlying global geometry of a data set using local (or partial) metric information. Here we propose a reconstruction algorithm based on semidefinite programming. For a random geometric graph model and uniformly bounded noise, we provide a precise characterization of the algorithm's performance: In the noiseless case, we find a radius $r_0$ beyond which the algorithm reconstructs the exact positions (up to rigid transformations). In the presence of noise, we obtain upper and lower bounds on the reconstruction error that match up to a factor that depends only on the dimension $d$, and the average degree of the nodes in the graph.", "source": "arxiv/ml"}
{"id": "arxiv:834", "title": "A Gentle Introduction to the Kernel Distance", "text": "This document reviews the definition of the kernel distance, providing a gentle introduction tailored to a reader with background in theoretical computer science, but limited exposure to technology more common to machine learning, functional analysis and geometric measure theory. The key aspect of the kernel distance developed here is its interpretation as an L_2 distance between probability measures or various shapes (e.g. point sets, curves, surfaces) embedded in a vector space (specifically an RKHS). This structure enables several elegant and efficient solutions to data analysis problems. We conclude with a glimpse into the mathematical underpinnings of this measure, highlighting its recent independent evolution in two separate fields.", "source": "arxiv/ml"}
{"id": "arxiv:835", "title": "Information Theoretic Limits on Learning Stochastic Differential Equations", "text": "Consider the problem of learning the drift coefficient of a stochastic differential equation from a sample path. In this paper, we assume that the drift is parametrized by a high dimensional vector. We address the question of how long the system needs to be observed in order to learn this vector of parameters. We prove a general lower bound on this time complexity by using a characterization of mutual information as time integral of conditional variance, due to Kadota, Zakai, and Ziv. This general lower bound is applied to specific classes of linear and non-linear stochastic differential equations. In the linear case, the problem under consideration is the one of learning a matrix of interaction coefficients. We evaluate our lower bound for ensembles of sparse and dense random matrices. The resulting estimates match the qualitative behavior of upper bounds achieved by computationally efficient procedures.", "source": "arxiv/ml"}
{"id": "arxiv:836", "title": "COMET: A Recipe for Learning and Using Large Ensembles on Massive Data", "text": "COMET is a single-pass MapReduce algorithm for learning on large-scale data. It builds multiple random forest ensembles on distributed blocks of data and merges them into a mega-ensemble. This approach is appropriate when learning from massive-scale data that is too large to fit on a single machine. To get the best accuracy, IVoting should be used instead of bagging to generate the training subset for each decision tree in the random forest. Experiments with two large datasets (5GB and 50GB compressed) show that COMET compares favorably (in both accuracy and training time) to learning on a subsample of data using a serial algorithm. Finally, we propose a new Gaussian approach for lazy ensemble evaluation which dynamically decides how many ensemble members to evaluate per data point; this can reduce evaluation cost by 100X or more.", "source": "arxiv/ml"}
{"id": "arxiv:837", "title": "Heterogeneous Learning in Zero-Sum Stochastic Games with Incomplete Information", "text": "Learning algorithms are essential for the applications of game theory in a networking environment. In dynamic and decentralized settings where the traffic, topology and channel states may vary over time and the communication between agents is impractical, it is important to formulate and study games of incomplete information and fully distributed learning algorithms which for each agent requires a minimal amount of information regarding the remaining agents. In this paper, we address this major challenge and introduce heterogeneous learning schemes in which each agent adopts a distinct learning pattern in the context of games with incomplete information. We use stochastic approximation techniques to show that the heterogeneous learning schemes can be studied in terms of their deterministic ordinary differential equation (ODE) counterparts. Depending on the learning rates of the players, these ODEs could be different from the standard replicator dynamics, (myopic) best response (BR) dynamics, logit dynamics, and fictitious play dynamics. We apply the results to a class of security games in which the attacker and the defender adopt different learning schemes due to differences in their rationality levels and the information they acquire.", "source": "arxiv/ml"}
{"id": "arxiv:838", "title": "Autotagging music with conditional restricted Boltzmann machines", "text": "This paper describes two applications of conditional restricted Boltzmann machines (CRBMs) to the task of autotagging music. The first consists of training a CRBM to predict tags that a user would apply to a clip of a song based on tags already applied by other users. By learning the relationships between tags, this model is able to pre-process training data to significantly improve the performance of a support vector machine (SVM) autotagging. The second is the use of a discriminative RBM, a type of CRBM, to autotag music. By simultaneously exploiting the relationships among tags and between tags and audio-based features, this model is able to significantly outperform SVMs, logistic regression, and multi-layer perceptrons. In order to be applied to this problem, the discriminative RBM was generalized to the multi-label setting and four different learning algorithms for it were evaluated, the first such in-depth analysis of which we are aware.", "source": "arxiv/ml"}
{"id": "arxiv:839", "title": "A note on active learning for smooth problems", "text": "We show that the disagreement coefficient of certain smooth hypothesis classes is $O(m)$, where $m$ is the dimension of the hypothesis space, thereby answering a question posed in \\cite{friedman09}.", "source": "arxiv/ml"}
{"id": "arxiv:840", "title": "Distributed Learning Policies for Power Allocation in Multiple Access Channels", "text": "We analyze the problem of distributed power allocation for orthogonal multiple access channels by considering a continuous non-cooperative game whose strategy space represents the users' distribution of transmission power over the network's channels. When the channels are static, we find that this game admits an exact potential function and this allows us to show that it has a unique equilibrium almost surely. Furthermore, using the game's potential property, we derive a modified version of the replicator dynamics of evolutionary game theory which applies to this continuous game, and we show that if the network's users employ a distributed learning scheme based on these dynamics, then they converge to equilibrium exponentially quickly. On the other hand, a major challenge occurs if the channels do not remain static but fluctuate stochastically over time, following a stationary ergodic process. In that case, the associated ergodic game still admits a unique equilibrium, but the learning analysis becomes much more complicated because the replicator dynamics are no longer deterministic. Nonetheless, by employing results from the theory of stochastic approximation, we show that users still converge to the game's unique equilibrium. Our analysis hinges on a game-theoretical result which is of independent interest: in finite player games which admit a (possibly nonlinear) convex potential function, the replicator dynamics (suitably modified to account for nonlinear payoffs) converge to an eps-neighborhood of an equilibrium at time of order O(log(1/eps)).", "source": "arxiv/ml"}
{"id": "arxiv:841", "title": "Refining Recency Search Results with User Click Feedback", "text": "Traditional machine-learned ranking systems for web search are often trained to capture stationary relevance of documents to queries, which has limited ability to track non-stationary user intention in a timely manner. In recency search, for instance, the relevance of documents to a query on breaking news often changes significantly over time, requiring effective adaptation to user intention. In this paper, we focus on recency search and study a number of algorithms to improve ranking results by leveraging user click feedback. Our contributions are three-fold. First, we use real search sessions collected in a random exploration bucket for \\emph{reliable} offline evaluation of these algorithms, which provides an unbiased comparison across algorithms without online bucket tests. Second, we propose a re-ranking approach to improve search results for recency queries using user clicks. Third, our empirical comparison of a dozen algorithms on real-life search data suggests importance of a few algorithmic choices in these applications, including generalization across different query-document pairs, specialization to popular queries, and real-time adaptation of user clicks.", "source": "arxiv/ml"}
{"id": "arxiv:842", "title": "Pattern-recalling processes in quantum Hopfield networks far from saturation", "text": "As a mathematical model of associative memories, the Hopfield model was now well-established and a lot of studies to reveal the pattern-recalling process have been done from various different approaches. As well-known, a single neuron is itself an uncertain, noisy unit with a finite unnegligible error in the input-output relation. To model the situation artificially, a kind of 'heat bath' that surrounds neurons is introduced. The heat bath, which is a source of noise, is specified by the 'temperature'. Several studies concerning the pattern-recalling processes of the Hopfield model governed by the Glauber-dynamics at finite temperature were already reported. However, we might extend the 'thermal noise' to the quantum-mechanical variant. In this paper, in terms of the stochastic process of quantum-mechanical Markov chain Monte Carlo method (the quantum MCMC), we analytically derive macroscopically deterministic equations of order parameters such as 'overlap' in a quantum-mechanical variant of the Hopfield neural networks (let us call \"quantum Hopfield model\" or \"quantum Hopfield networks\"). For the case in which non-extensive number $p$ of patterns are embedded via asymmetric Hebbian connections, namely, $p/N \\to 0$ for the number of neuron $N \\to \\infty$ ('far from saturation'), we evaluate the recalling processes for one of the built-in patterns under the influence of quantum-mechanical noise.", "source": "arxiv/ml"}
{"id": "arxiv:843", "title": "A Linear Classifier Based on Entity Recognition Tools and a Statistical Approach to Method Extraction in the Protein-Protein Interaction Literature", "text": "We participated, in the Article Classification and the Interaction Method subtasks (ACT and IMT, respectively) of the Protein-Protein Interaction task of the BioCreative III Challenge. For the ACT, we pursued an extensive testing of available Named Entity Recognition and dictionary tools, and used the most promising ones to extend our Variable Trigonometric Threshold linear classifier. For the IMT, we experimented with a primarily statistical approach, as opposed to employing a deeper natural language processing strategy. Finally, we also studied the benefits of integrating the method extraction approach that we have used for the IMT into the ACT pipeline. For the ACT, our linear article classifier leads to a ranking and classification performance significantly higher than all the reported submissions. For the IMT, our results are comparable to those of other systems, which took very different approaches. For the ACT, we show that the use of named entity recognition tools leads to a substantial improvement in the ranking and classification of articles relevant to protein-protein interaction. Thus, we show that our substantially expanded linear classifier is a very competitive classifier in this domain. Moreover, this classifier produces interpretable surfaces that can be understood as \"rules\" for human understanding of the classification. In terms of the IMT task, in contrast to other participants, our approach focused on identifying sentences that are likely to bear evidence for the application of a PPI detection method, rather than on classifying a document as relevant to a method. As BioCreative III did not perform an evaluation of the evidence provided by the system, we have conducted a separate assessment; the evaluators agree that our tool is indeed effective in detecting relevant evidence for PPI detection methods.", "source": "arxiv/ml"}
{"id": "arxiv:844", "title": "Parallel Online Learning", "text": "In this work we study parallelization of online learning, a core primitive in machine learning. In a parallel environment all known approaches for parallel online learning lead to delayed updates, where the model is updated using out-of-date information. In the worst case, or when examples are temporally correlated, delay can have a very adverse effect on the learning algorithm. Here, we analyze and present preliminary empirical results on a set of learning architectures based on a feature sharding approach that present various tradeoffs between delay, degree of parallelism, representation power and empirical performance.", "source": "arxiv/ml"}
{"id": "arxiv:845", "title": "Clustered regression with unknown clusters", "text": "We consider a collection of prediction experiments, which are clustered in the sense that groups of experiments ex- hibit similar relationship between the predictor and response variables. The experiment clusters as well as the regres- sion relationships are unknown. The regression relation- ships define the experiment clusters, and in general, the predictor and response variables may not exhibit any clus- tering. We call this prediction problem clustered regres- sion with unknown clusters (CRUC) and in this paper we focus on linear regression. We study and compare several methods for CRUC, demonstrate their applicability to the Yahoo Learning-to-rank Challenge (YLRC) dataset, and in- vestigate an associated mathematical model. CRUC is at the crossroads of many prior works and we study several prediction algorithms with diverse origins: an adaptation of the expectation-maximization algorithm, an approach in- spired by K-means clustering, the singular value threshold- ing approach to matrix rank minimization under quadratic constraints, an adaptation of the Curds and Whey method in multiple regression, and a local regression (LoR) scheme reminiscent of neighborhood methods in collaborative filter- ing. Based on empirical evaluation on the YLRC dataset as well as simulated data, we identify the LoR method as a good practical choice: it yields best or near-best prediction performance at a reasonable computational load, and it is less sensitive to the choice of the algorithm parameter. We also provide some analysis of the LoR method for an asso- ciated mathematical model, which sheds light on optimal parameter choice and prediction performance.", "source": "arxiv/ml"}
{"id": "arxiv:846", "title": "Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs", "text": "The competitive MNIST handwritten digit recognition benchmark has a long history of broken records since 1998. The most recent substantial improvement by others dates back 7 years (error rate 0.4%) . Recently we were able to significantly improve this result, using graphics cards to greatly speed up training of simple but deep MLPs, which achieved 0.35%, outperforming all the previous more complex methods. Here we report another substantial improvement: 0.31% obtained using a committee of MLPs.", "source": "arxiv/ml"}
{"id": "arxiv:847", "title": "Doubly Robust Policy Evaluation and Learning", "text": "We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of applications including health-care policy and Internet advertising. A central task is evaluation of a new policy given historic data consisting of contexts, actions and received rewards. The key challenge is that the past data typically does not faithfully represent proportions of actions taken by a new policy. Previous approaches rely either on models of rewards or models of the past policy. The former are plagued by a large bias whereas the latter have a large variance. In this work, we leverage the strength and overcome the weaknesses of the two approaches by applying the doubly robust technique to the problems of policy evaluation and optimization. We prove that this approach yields accurate value estimates when we have either a good (but not necessarily consistent) model of rewards or a good (but not necessarily consistent) model of past policy. Extensive empirical comparison demonstrates that the doubly robust approach uniformly improves over existing techniques, achieving both lower variance in value estimation and better policies. As such, we expect the doubly robust approach to become common practice.", "source": "arxiv/ml"}
{"id": "arxiv:848", "title": "Classification of Sets using Restricted Boltzmann Machines", "text": "We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations of the restricted Boltzmann machine (RBM) that are appropriate in this context and explore how to incorporate different assumptions about the relationship between the input sets and the target class within the RBM. In experiments on standard multiple-instance learning datasets, we demonstrate the competitiveness of approaches based on RBMs and apply the proposed variants to the problem of incoming mail classification.", "source": "arxiv/ml"}
{"id": "arxiv:849", "title": "Distribution-Independent Evolvability of Linear Threshold Functions", "text": "Valiant's (2007) model of evolvability models the evolutionary process of acquiring useful functionality as a restricted form of learning from random examples. Linear threshold functions and their various subclasses, such as conjunctions and decision lists, play a fundamental role in learning theory and hence their evolvability has been the primary focus of research on Valiant's framework (2007). One of the main open problems regarding the model is whether conjunctions are evolvable distribution-independently (Feldman and Valiant, 2008). We show that the answer is negative. Our proof is based on a new combinatorial parameter of a concept class that lower-bounds the complexity of learning from correlations. We contrast the lower bound with a proof that linear threshold functions having a non-negligible margin on the data points are evolvable distribution-independently via a simple mutation algorithm. Our algorithm relies on a non-linear loss function being used to select the hypotheses instead of 0-1 loss in Valiant's (2007) original definition. The proof of evolvability requires that the loss function satisfies several mild conditions that are, for example, satisfied by the quadratic loss function studied in several other works (Michael, 2007; Feldman, 2009; Valiant, 2010). An important property of our evolution algorithm is monotonicity, that is the algorithm guarantees evolvability without any decreases in performance. Previously, monotone evolvability was only shown for conjunctions with quadratic loss (Feldman, 2009) or when the distribution on the domain is severely restricted (Michael, 2007; Feldman, 2009; Kanade et al., 2010)", "source": "arxiv/ml"}
{"id": "arxiv:850", "title": "On Empirical Entropy", "text": "We propose a compression-based version of the empirical entropy of a finite string over a finite alphabet. Whereas previously one considers the naked entropy of (possibly higher order) Markov processes, we consider the sum of the description of the random variable involved plus the entropy it induces. We assume only that the distribution involved is computable. To test the new notion we compare the Normalized Information Distance (the similarity metric) with a related measure based on Mutual Information in Shannon's framework. This way the similarities and differences of the last two concepts are exposed.", "source": "arxiv/ml"}
{"id": "arxiv:851", "title": "Decentralized Online Learning Algorithms for Opportunistic Spectrum Access", "text": "The fundamental problem of multiple secondary users contending for opportunistic spectrum access over multiple channels in cognitive radio networks has been formulated recently as a decentralized multi-armed bandit (D-MAB) problem. In a D-MAB problem there are $M$ users and $N$ arms (channels) that each offer i.i.d. stochastic rewards with unknown means so long as they are accessed without collision. The goal is to design a decentralized online learning policy that incurs minimal regret, defined as the difference between the total expected rewards accumulated by a model-aware genie, and that obtained by all users applying the policy. We make two contributions in this paper. First, we consider the setting where the users have a prioritized ranking, such that it is desired for the $K$-th-ranked user to learn to access the arm offering the $K$-th highest mean reward. For this problem, we present the first distributed policy that yields regret that is uniformly logarithmic over time without requiring any prior assumption about the mean rewards. Second, we consider the case when a fair access policy is required, i.e., it is desired for all users to experience the same mean reward. For this problem, we present a distributed policy that yields order-optimal regret scaling with respect to the number of users and arms, better than previously proposed policies in the literature. Both of our distributed policies make use of an innovative modification of the well known UCB1 policy for the classic multi-armed bandit problem that allows a single user to learn how to play the arm that yields the $K$-th largest mean reward.", "source": "arxiv/ml"}
{"id": "arxiv:852", "title": "Gaussian Robust Classification", "text": "Supervised learning is all about the ability to generalize knowledge. Specifically, the goal of the learning is to train a classifier using training data, in such a way that it will be capable of classifying new unseen data correctly. In order to acheive this goal, it is important to carefully design the learner, so it will not overfit the training data. The later can is done usually by adding a regularization term. The statistical learning theory explains the success of this method by claiming that it restricts the complexity of the learned model. This explanation, however, is rather abstract and does not have a geometric intuition. The generalization error of a classifier may be thought of as correlated with its robustness to perturbations of the data: a classifier that copes with disturbance is expected to generalize well. Indeed, Xu et al. [2009] have shown that the SVM formulation is equivalent to a robust optimization (RO) formulation, in which an adversary displaces the training and testing points within a ball of pre-determined radius. In this work we explore a different kind of robustness, namely changing each data point with a Gaussian cloud centered at the sample. Loss is evaluated as the expectation of an underlying loss function on the cloud. This setup fits the fact that in many applications, the data is sampled along with noise. We develop an RO framework, in which the adversary chooses the covariance of the noise. In our algorithm named GURU, the tuning parameter is a spectral bound on the noise, thus it can be estimated using physical or applicative considerations. Our experiments show that this framework performs as well as SVM and even slightly better in some cases. Generalizations for Mercer kernels and for the multiclass case are presented as well. We also show that our framework may be further generalized, using the technique of convex perspective functions.", "source": "arxiv/ml"}
{"id": "arxiv:853", "title": "Meaningful Clustered Forest: an Automatic and Robust Clustering Algorithm", "text": "We propose a new clustering technique that can be regarded as a numerical method to compute the proximity gestalt. The method analyzes edge length statistics in the MST of the dataset and provides an a contrario cluster detection criterion. The approach is fully parametric on the chosen distance and can detect arbitrarily shaped clusters. The method is also automatic, in the sense that only a single parameter is left to the user. This parameter has an intuitive interpretation as it controls the expected number of false detections. We show that the iterative application of our method can (1) provide robustness to noise and (2) solve a masking phenomenon in which a highly populated and salient cluster dominates the scene and inhibits the detection of less-populated, but still salient, clusters.", "source": "arxiv/ml"}
{"id": "arxiv:854", "title": "Online and Batch Learning Algorithms for Data with Missing Features", "text": "We introduce new online and batch algorithms that are robust to data with missing features, a situation that arises in many practical applications. In the online setup, we allow for the comparison hypothesis to change as a function of the subset of features that is observed on any given round, extending the standard setting where the comparison hypothesis is fixed throughout. In the batch setup, we present a convex relation of a non-convex problem to jointly estimate an imputation function, used to fill in the values of missing features, along with the classification hypothesis. We prove regret bounds in the online setting and Rademacher complexity bounds for the batch i.i.d. setting. The algorithms are tested on several UCI datasets, showing superior performance over baselines.", "source": "arxiv/ml"}
{"id": "arxiv:855", "title": "Efficient First Order Methods for Linear Composite Regularizers", "text": "A wide class of regularization problems in machine learning and statistics employ a regularization term which is obtained by composing a simple convex function \\omega with a linear transformation. This setting includes Group Lasso methods, the Fused Lasso and other total variation methods, multi-task learning methods and many more. In this paper, we present a general approach for computing the proximity operator of this class of regularizers, under the assumption that the proximity operator of the function \\omega is known in advance. Our approach builds on a recent line of research on optimal first order optimization methods and uses fixed point iterations for numerically computing the proximity operator. It is more general than current approaches and, as we show with numerical simulations, computationally more efficient than available first order methods which do not achieve the optimal rate. In particular, our method outperforms state of the art O(1/T) methods for overlapping Group Lasso and matches optimal O(1/T^2) methods for the Fused Lasso and tree structured Group Lasso.", "source": "arxiv/ml"}
{"id": "arxiv:856", "title": "Plug-in Approach to Active Learning", "text": "We present a new active learning algorithm based on nonparametric estimators of the regression function. Our investigation provides probabilistic bounds for the rates of convergence of the generalization error achievable by proposed method over a broad class of underlying distributions. We also prove minimax lower bounds which show that the obtained rates are almost tight.", "source": "arxiv/ml"}
{"id": "arxiv:857", "title": "Dimension-free tail inequalities for sums of random matrices", "text": "We derive exponential tail inequalities for sums of random matrices with no dependence on the explicit matrix dimensions. These are similar to the matrix versions of the Chernoff bound and Bernstein inequality except with the explicit matrix dimensions replaced by a trace quantity that can be small even when the dimension is large or infinite. Some applications to principal component analysis and approximate matrix multiplication are given to illustrate the utility of the new bounds.", "source": "arxiv/ml"}
{"id": "arxiv:858", "title": "Convex and Network Flow Optimization for Structured Sparsity", "text": "We consider a class of learning problems regularized by a structured sparsity-inducing norm defined as the sum of l_2- or l_infinity-norms over groups of variables. Whereas much effort has been put in developing fast optimization techniques when the groups are disjoint or embedded in a hierarchy, we address here the case of general overlapping groups. To this end, we present two different strategies: On the one hand, we show that the proximal operator associated with a sum of l_infinity-norms can be computed exactly in polynomial time by solving a quadratic min-cost flow problem, allowing the use of accelerated proximal gradient methods. On the other hand, we use proximal splitting techniques, and address an equivalent formulation with non-overlapping groups, but in higher dimension and with additional constraints. We propose efficient and scalable algorithms exploiting these two strategies, which are significantly faster than alternative approaches. We illustrate these methods with several problems such as CUR matrix factorization, multi-task learning of tree-structured dictionaries, background subtraction in video sequences, image denoising with wavelets, and topographic dictionary learning of natural image patches.", "source": "arxiv/ml"}
{"id": "arxiv:859", "title": "Adaptive Evolutionary Clustering", "text": "In many practical applications of clustering, the objects to be clustered evolve over time, and a clustering result is desired at each time step. In such applications, evolutionary clustering typically outperforms traditional static clustering by producing clustering results that reflect long-term trends while being robust to short-term variations. Several evolutionary clustering algorithms have recently been proposed, often by adding a temporal smoothness penalty to the cost function of a static clustering method. In this paper, we introduce a different approach to evolutionary clustering by accurately tracking the time-varying proximities between objects followed by static clustering. We present an evolutionary clustering framework that adaptively estimates the optimal smoothing parameter using shrinkage estimation, a statistical approach that improves a naive estimate using additional information. The proposed framework can be used to extend a variety of static clustering algorithms, including hierarchical, k-means, and spectral clustering, into evolutionary clustering algorithms. Experiments on synthetic and real data sets indicate that the proposed framework outperforms static clustering and existing evolutionary clustering algorithms in many scenarios.", "source": "arxiv/ml"}
{"id": "arxiv:860", "title": "Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression", "text": "Generalized Linear Models (GLMs) and Single Index Models (SIMs) provide powerful generalizations of linear regression, where the target variable is assumed to be a (possibly unknown) 1-dimensional function of a linear predictor. In general, these problems entail non-convex estimation procedures, and, in practice, iterative local search heuristics are often used. Kalai and Sastry (2009) recently provided the first provably efficient method for learning SIMs and GLMs, under the assumptions that the data are in fact generated under a GLM and under certain monotonicity and Lipschitz constraints. However, to obtain provable performance, the method requires a fresh sample every iteration. In this paper, we provide algorithms for learning GLMs and SIMs, which are both computationally and statistically efficient. We also provide an empirical study, demonstrating their feasibility in practice.", "source": "arxiv/ml"}
{"id": "arxiv:861", "title": "PAC learnability versus VC dimension: a footnote to a basic result of statistical learning", "text": "A fundamental result of statistical learnig theory states that a concept class is PAC learnable if and only if it is a uniform Glivenko-Cantelli class if and only if the VC dimension of the class is finite. However, the theorem is only valid under special assumptions of measurability of the class, in which case the PAC learnability even becomes consistent. Otherwise, there is a classical example, constructed under the Continuum Hypothesis by Dudley and Durst and further adapted by Blumer, Ehrenfeucht, Haussler, and Warmuth, of a concept class of VC dimension one which is neither uniform Glivenko-Cantelli nor consistently PAC learnable. We show that, rather surprisingly, under an additional set-theoretic hypothesis which is much milder than the Continuum Hypothesis (Martin's Axiom), PAC learnability is equivalent to finite VC dimension for every concept class.", "source": "arxiv/ml"}
{"id": "arxiv:862", "title": "Hypothesize and Bound: A Computational Focus of Attention Mechanism for Simultaneous N-D Segmentation, Pose Estimation and Classification Using Shape Priors", "text": "Given the ever increasing bandwidth of the visual information available to many intelligent systems, it is becoming essential to endow them with a sense of what is worthwhile their attention and what can be safely disregarded. This article presents a general mathematical framework to efficiently allocate the available computational resources to process the parts of the input that are relevant to solve a given perceptual problem. By this we mean to find the hypothesis H (i.e., the state of the world) that maximizes a function L(H), representing how well each hypothesis \"explains\" the input. Given the large bandwidth of the sensory input, fully evaluating L(H) for each hypothesis H is computationally infeasible (e.g., because it would imply checking a large number of pixels). To address this problem we propose a mathematical framework with two key ingredients. The first one is a Bounding Mechanism (BM) to compute lower and upper bounds of L(H), for a given computational budget. These bounds are much cheaper to compute than L(H) itself, can be refined at any time by increasing the budget allocated to a hypothesis, and are frequently enough to discard a hypothesis. To compute these bounds, we develop a novel theory of shapes and shape priors. The second ingredient is a Focus of Attention Mechanism (FoAM) to select which hypothesis' bounds should be refined next, with the goal of discarding non-optimal hypotheses with the least amount of computation. The proposed framework: 1) is very efficient since most hypotheses are discarded with minimal computation; 2) is parallelizable; 3) is guaranteed to find the globally optimal hypothesis; and 4) its running time depends on the problem at hand, not on the bandwidth of the input. We instantiate the proposed framework for the problem of simultaneously estimating the class, pose, and a noiseless version of a 2D shape in a 2D image.", "source": "arxiv/ml"}
{"id": "arxiv:863", "title": "Cluster Forests", "text": "With inspiration from Random Forests (RF) in the context of classification, a new clustering ensemble method---Cluster Forests (CF) is proposed. Geometrically, CF randomly probes a high-dimensional data cloud to obtain \"good local clusterings\" and then aggregates via spectral clustering to obtain cluster assignments for the whole dataset. The search for good local clusterings is guided by a cluster quality measure kappa. CF progressively improves each local clustering in a fashion that resembles the tree growth in RF. Empirical studies on several real-world datasets under two different performance metrics show that CF compares favorably to its competitors. Theoretical analysis reveals that the kappa measure makes it possible to grow the local clustering in a desirable way---it is \"noise-resistant\". A closed-form expression is obtained for the mis-clustering rate of spectral clustering under a perturbation model, which yields new insights into some aspects of spectral clustering.", "source": "arxiv/ml"}
{"id": "arxiv:864", "title": "Signal Classification for Acoustic Neutrino Detection", "text": "This article focuses on signal classification for deep-sea acoustic neutrino detection. In the deep sea, the background of transient signals is very diverse. Approaches like matched filtering are not sufficient to distinguish between neutrino-like signals and other transient signals with similar signature, which are forming the acoustic background for neutrino detection in the deep-sea environment. A classification system based on machine learning algorithms is analysed with the goal to find a robust and effective way to perform this task. For a well-trained model, a testing error on the level of one percent is achieved for strong classifiers like Random Forest and Boosting Trees using the extracted features of the signal as input and utilising dense clusters of sensors instead of single sensors.", "source": "arxiv/ml"}
{"id": "arxiv:865", "title": "A sufficient condition on monotonic increase of the number of nonzero entry in the optimizer of L1 norm penalized least-square problem", "text": "The $\\ell$-1 norm based optimization is widely used in signal processing, especially in recent compressed sensing theory. This paper studies the solution path of the $\\ell$-1 norm penalized least-square problem, whose constrained form is known as Least Absolute Shrinkage and Selection Operator (LASSO). A solution path is the set of all the optimizers with respect to the evolution of the hyperparameter (Lagrange multiplier). The study of the solution path is of great significance in viewing and understanding the profile of the tradeoff between the approximation and regularization terms. If the solution path of a given problem is known, it can help us to find the optimal hyperparameter under a given criterion such as the Akaike Information Criterion. In this paper we present a sufficient condition on $\\ell$-1 norm penalized least-square problem. Under this sufficient condition, the number of nonzero entries in the optimizer or solution vector increases monotonically when the hyperparameter decreases. We also generalize the result to the often used total variation case, where the $\\ell$-1 norm is taken over the first order derivative of the solution vector. We prove that the proposed condition has intrinsic connections with the condition given by Donoho, et al \\cite{Donoho08} and the positive cone condition by Efron {\\it el al} \\cite{Efron04}. However, the proposed condition does not need to assume the sparsity level of the signal as required by Donoho et al's condition, and is easier to verify than Efron, et al's positive cone condition when being used for practical applications.", "source": "arxiv/ml"}
{"id": "arxiv:866", "title": "Understanding Exhaustive Pattern Learning", "text": "Pattern learning in an important problem in Natural Language Processing (NLP). Some exhaustive pattern learning (EPL) methods (Bod, 1992) were proved to be flawed (Johnson, 2002), while similar algorithms (Och and Ney, 2004) showed great advantages on other tasks, such as machine translation. In this article, we first formalize EPL, and then show that the probability given by an EPL model is constant-factor approximation of the probability given by an ensemble method that integrates exponential number of models obtained with various segmentations of the training data. This work for the first time provides theoretical justification for the widely used EPL algorithm in NLP, which was previously viewed as a flawed heuristic method. Better understanding of EPL may lead to improved pattern learning algorithms in future.", "source": "arxiv/ml"}
{"id": "arxiv:867", "title": "Intent Inference and Syntactic Tracking with GMTI Measurements", "text": "In conventional target tracking systems, human operators use the estimated target tracks to make higher level inference of the target behaviour/intent. This paper develops syntactic filtering algorithms that assist human operators by extracting spatial patterns from target tracks to identify suspicious/anomalous spatial trajectories. The targets' spatial trajectories are modeled by a stochastic context free grammar (SCFG) and a switched mode state space model. Bayesian filtering algorithms for stochastic context free grammars are presented for extracting the syntactic structure and illustrated for a ground moving target indicator (GMTI) radar example. The performance of the algorithms is tested with the experimental data collected using DRDC Ottawa's X-band Wideband Experimental Airborne Radar (XWEAR).", "source": "arxiv/ml"}
{"id": "arxiv:868", "title": "Robust Clustering Using Outlier-Sparsity Regularization", "text": "Notwithstanding the popularity of conventional clustering algorithms such as K-means and probabilistic clustering, their clustering results are sensitive to the presence of outliers in the data. Even a few outliers can compromise the ability of these algorithms to identify meaningful hidden structures rendering their outcome unreliable. This paper develops robust clustering algorithms that not only aim to cluster the data, but also to identify the outliers. The novel approaches rely on the infrequent presence of outliers in the data which translates to sparsity in a judiciously chosen domain. Capitalizing on the sparsity in the outlier domain, outlier-aware robust K-means and probabilistic clustering approaches are proposed. Their novelty lies on identifying outliers while effecting sparsity in the outlier domain through carefully chosen regularization. A block coordinate descent approach is developed to obtain iterative algorithms with convergence guarantees and small excess computational complexity with respect to their non-robust counterparts. Kernelized versions of the robust clustering algorithms are also developed to efficiently handle high-dimensional data, identify nonlinearly separable clusters, or even cluster objects that are not represented by vectors. Numerical tests on both synthetic and real datasets validate the performance and applicability of the novel algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:869", "title": "Compressive Network Analysis", "text": "Modern data acquisition routinely produces massive amounts of network data. Though many methods and models have been proposed to analyze such data, the research of network data is largely disconnected with the classical theory of statistical learning and signal processing. In this paper, we present a new framework for modeling network data, which connects two seemingly different areas: network data analysis and compressed sensing. From a nonparametric perspective, we model an observed network using a large dictionary. In particular, we consider the network clique detection problem and show connections between our formulation with a new algebraic tool, namely Randon basis pursuit in homogeneous spaces. Such a connection allows us to identify rigorous recovery conditions for clique detection problems. Though this paper is mainly conceptual, we also develop practical approximation algorithms for solving empirical problems and demonstrate their usefulness on real-world datasets.", "source": "arxiv/ml"}
{"id": "arxiv:870", "title": "Temporal Second Difference Traces", "text": "Q-learning is a reliable but inefficient off-policy temporal-difference method, backing up reward only one step at a time. Replacing traces, using a recency heuristic, are more efficient but less reliable. In this work, we introduce model-free, off-policy temporal difference methods that make better use of experience than Watkins' Q(\\lambda). We introduce both Optimistic Q(\\lambda) and the temporal second difference trace (TSDT). TSDT is particularly powerful in deterministic domains. TSDT uses neither recency nor frequency heuristics, storing (s,a,r,s',\\delta) so that off-policy updates can be performed after apparently suboptimal actions have been taken. There are additional advantages when using state abstraction, as in MAXQ. We demonstrate that TSDT does significantly better than both Q-learning and Watkins' Q(\\lambda) in a deterministic cliff-walking domain. Results in a noisy cliff-walking domain are less advantageous for TSDT, but demonstrate the efficacy of Optimistic Q(\\lambda), a replacing trace with some of the advantages of TSDT.", "source": "arxiv/ml"}
{"id": "arxiv:871", "title": "Clustering Partially Observed Graphs via Convex Optimization", "text": "This paper considers the problem of clustering a partially observed unweighted graph---i.e., one where for some node pairs we know there is an edge between them, for some others we know there is no edge, and for the remaining we do not know whether or not there is an edge. We want to organize the nodes into disjoint clusters so that there is relatively dense (observed) connectivity within clusters, and sparse across clusters. We take a novel yet natural approach to this problem, by focusing on finding the clustering that minimizes the number of \"disagreements\"---i.e., the sum of the number of (observed) missing edges within clusters, and (observed) present edges across clusters. Our algorithm uses convex optimization; its basis is a reduction of disagreement minimization to the problem of recovering an (unknown) low-rank matrix and an (unknown) sparse matrix from their partially observed sum. We evaluate the performance of our algorithm on the classical Planted Partition/Stochastic Block Model. Our main theorem provides sufficient conditions for the success of our algorithm as a function of the minimum cluster size, edge density and observation probability; in particular, the results characterize the tradeoff between the observation probability and the edge density gap. When there are a constant number of clusters of equal size, our results are optimal up to logarithmic factors.", "source": "arxiv/ml"}
{"id": "arxiv:872", "title": "Reducing Commitment to Tasks with Off-Policy Hierarchical Reinforcement Learning", "text": "In experimenting with off-policy temporal difference (TD) methods in hierarchical reinforcement learning (HRL) systems, we have observed unwanted on-policy learning under reproducible conditions. Here we present modifications to several TD methods that prevent unintentional on-policy learning from occurring. These modifications create a tension between exploration and learning. Traditional TD methods require commitment to finishing subtasks without exploration in order to update Q-values for early actions with high probability. One-step intra-option learning and temporal second difference traces (TSDT) do not suffer from this limitation. We demonstrate that our HRL system is efficient without commitment to completion of subtasks in a cliff-walking domain, contrary to a widespread claim in the literature that it is critical for efficiency of learning. Furthermore, decreasing commitment as exploration progresses is shown to improve both online performance and the resultant policy in the taxicab domain, opening a new avenue for research into when it is more beneficial to continue with the current subtask or to replan.", "source": "arxiv/ml"}
{"id": "arxiv:873", "title": "On Combining Machine Learning with Decision Making", "text": "We present a new application and covering number bound for the framework of \"Machine Learning with Operational Costs (MLOC),\" which is an exploratory form of decision theory. The MLOC framework incorporates knowledge about how a predictive model will be used for a subsequent task, thus combining machine learning with the decision that is made afterwards. In this work, we use the MLOC framework to study a problem that has implications for power grid reliability and maintenance, called the Machine Learning and Traveling Repairman Problem ML&TRP. The goal of the ML&TRP is to determine a route for a \"repair crew,\" which repairs nodes on a graph. The repair crew aims to minimize the cost of failures at the nodes, but as in many real situations, the failure probabilities are not known and must be estimated. The MLOC framework allows us to understand how this uncertainty influences the repair route. We also present new covering number generalization bounds for the MLOC framework.", "source": "arxiv/ml"}
{"id": "arxiv:874", "title": "Online Learning: Stochastic and Constrained Adversaries", "text": "Learning theory has largely focused on two main learning scenarios. The first is the classical statistical setting where instances are drawn i.i.d. from a fixed distribution and the second scenario is the online learning, completely adversarial scenario where adversary at every time step picks the worst instance to provide the learner with. It can be argued that in the real world neither of these assumptions are reasonable. It is therefore important to study problems with a range of assumptions on data. Unfortunately, theoretical results in this area are scarce, possibly due to absence of general tools for analysis. Focusing on the regret formulation, we define the minimax value of a game where the adversary is restricted in his moves. The framework captures stochastic and non-stochastic assumptions on data. Building on the sequential symmetrization approach, we define a notion of distribution-dependent Rademacher complexity for the spectrum of problems ranging from i.i.d. to worst-case. The bounds let us immediately deduce variation-type bounds. We then consider the i.i.d. adversary and show equivalence of online and batch learnability. In the supervised setting, we consider various hybrid assumptions on the way that x and y variables are chosen. Finally, we consider smoothed learning problems and show that half-spaces are online learnable in the smoothed model. In fact, exponentially small noise added to adversary's decisions turns this problem with infinite Littlestone's dimension into a learnable problem.", "source": "arxiv/ml"}
{"id": "arxiv:875", "title": "Attacking and Defending Covert Channels and Behavioral Models", "text": "In this paper we present methods for attacking and defending $k$-gram statistical analysis techniques that are used, for example, in network traffic analysis and covert channel detection. The main new result is our demonstration of how to use a behavior's or process' $k$-order statistics to build a stochastic process that has those same $k$-order stationary statistics but possesses different, deliberately designed, $(k+1)$-order statistics if desired. Such a model realizes a \"complexification\" of the process or behavior which a defender can use to monitor whether an attacker is shaping the behavior. By deliberately introducing designed $(k+1)$-order behaviors, the defender can check to see if those behaviors are present in the data. We also develop constructs for source codes that respect the $k$-order statistics of a process while encoding covert information. One fundamental consequence of these results is that certain types of behavior analyses techniques come down to an {\\em arms race} in the sense that the advantage goes to the party that has more computing resources applied to the problem.", "source": "arxiv/ml"}
{"id": "arxiv:876", "title": "File Transfer Application For Sharing Femto Access", "text": "In wireless access network optimization, today's main challenges reside in traffic offload and in the improvement of both capacity and coverage networks. The operators are interested in solving their localized coverage and capacity problems in areas where the macro network signal is not able to serve the demand for mobile data. Thus, the major issue for operators is to find the best solution at reasonable expanses. The femto cell seems to be the answer to this problematic. In this work (This work is supported by the COMET project AWARE. http://www.ftw.at/news/project-start-for-aware-ftw), we focus on the problem of sharing femto access between a same mobile operator's customers. This problem can be modeled as a game where service requesters customers (SRCs) and service providers customers (SPCs) are the players. This work addresses the sharing femto access problem considering only one SPC using game theory tools. We consider that SRCs are static and have some similar and regular connection behavior. We also note that the SPC and each SRC have a software embedded respectively on its femto access, user equipment (UE). After each connection requested by a SRC, its software will learn the strategy increasing its gain knowing that no information about the other SRCs strategies is given. The following article presents a distributed learning algorithm with incomplete information running in SRCs software. We will then answer the following questions for a game with $N$ SRCs and one SPC: how many connections are necessary for each SRC in order to learn the strategy maximizing its gain? Does this algorithm converge to a stable state? If yes, does this state a Nash Equilibrium and is there any way to optimize the learning process duration time triggered by SRCs software?", "source": "arxiv/ml"}
{"id": "arxiv:877", "title": "Learning Undirected Graphical Models with Structure Penalty", "text": "In undirected graphical models, learning the graph structure and learning the functions that relate the predictive variables (features) to the responses given the structure are two topics that have been widely investigated in machine learning and statistics. Learning graphical models in two stages will have problems because graph structure may change after considering the features. The main contribution of this paper is the proposed method that learns the graph structure and functions on the graph at the same time. General graphical models with binary outcomes conditioned on predictive variables are proved to be equivalent to multivariate Bernoulli model. The reparameterization of the potential functions in graphical model by conditional log odds ratios in multivariate Bernoulli model offers advantage in the representation of the conditional independence structure in the model. Additionally, we impose a structure penalty on groups of conditional log odds ratios to learn the graph structure. These groups of functions are designed with overlaps to enforce hierarchical function selection. In this way, we are able to shrink higher order interactions to obtain a sparse graph structure. Simulation studies show that the method is able to recover the graph structure. The analysis of county data from Census Bureau gives interesting relations between unemployment rate, crime and others discovered by the model.", "source": "arxiv/ml"}
{"id": "arxiv:878", "title": "On Optimality of Greedy Policy for a Class of Standard Reward Function of Restless Multi-armed Bandit Problem", "text": "In this paper,we consider the restless bandit problem, which is one of the most well-studied generalizations of the celebrated stochastic multi-armed bandit problem in decision theory. However, it is known be PSPACE-Hard to approximate to any non-trivial factor. Thus the optimality is very difficult to obtain due to its high complexity. A natural method is to obtain the greedy policy considering its stability and simplicity. However, the greedy policy will result in the optimality loss for its intrinsic myopic behavior generally. In this paper, by analyzing one class of so-called standard reward function, we establish the closed-form condition about the discounted factor \\beta such that the optimality of the greedy policy is guaranteed under the discounted expected reward criterion, especially, the condition \\beta = 1 indicating the optimality of the greedy policy under the average accumulative reward criterion. Thus, the standard form of reward function can easily be used to judge the optimality of the greedy policy without any complicated calculation. Some examples in cognitive radio networks are presented to verify the effectiveness of the mathematical result in judging the optimality of the greedy policy.", "source": "arxiv/ml"}
{"id": "arxiv:879", "title": "Notes on a New Philosophy of Empirical Science", "text": "This book presents a methodology and philosophy of empirical science based on large scale lossless data compression. In this view a theory is scientific if it can be used to build a data compression program, and it is valuable if it can compress a standard benchmark database to a small size, taking into account the length of the compressor itself. This methodology therefore includes an Occam principle as well as a solution to the problem of demarcation. Because of the fundamental difficulty of lossless compression, this type of research must be empirical in nature: compression can only be achieved by discovering and characterizing empirical regularities in the data. Because of this, the philosophy provides a way to reformulate fields such as computer vision and computational linguistics as empirical sciences: the former by attempting to compress databases of natural images, the latter by attempting to compress large text databases. The book argues that the rigor and objectivity of the compression principle should set the stage for systematic progress in these fields. The argument is especially strong in the context of computer vision, which is plagued by chronic problems of evaluation. The book also considers the field of machine learning. Here the traditional approach requires that the models proposed to solve learning problems be extremely simple, in order to avoid overfitting. However, the world may contain intrinsically complex phenomena, which would require complex models to understand. The compression philosophy can justify complex models because of the large quantity of data being modeled (if the target database is 100 Gb, it is easy to justify a 10 Mb model). The complex models and abstractions learned on the basis of the raw data (images, language, etc) can then be reused to solve any specific learning problem, such as face recognition or machine translation.", "source": "arxiv/ml"}
{"id": "arxiv:880", "title": "Mean-Variance Optimization in Markov Decision Processes", "text": "We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:881", "title": "Learning high-dimensional directed acyclic graphs with latent and selection variables", "text": "We consider the problem of learning causal information between random variables in directed acyclic graphs (DAGs) when allowing arbitrarily many latent and selection variables. The FCI (Fast Causal Inference) algorithm has been explicitly designed to infer conditional independence and causal information in such settings. However, FCI is computationally infeasible for large graphs. We therefore propose the new RFCI algorithm, which is much faster than FCI. In some situations the output of RFCI is slightly less informative, in particular with respect to conditional independence information. However, we prove that any causal information in the output of RFCI is correct in the asymptotic limit. We also define a class of graphs on which the outputs of FCI and RFCI are identical. We prove consistency of FCI and RFCI in sparse high-dimensional settings, and demonstrate in simulations that the estimation performances of the algorithms are very similar. All software is implemented in the R-package pcalg.", "source": "arxiv/ml"}
{"id": "arxiv:882", "title": "Preference elicitation and inverse reinforcement learning", "text": "We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optionally, the obtained reward sequence, from observations. We examine the relation of the resulting approach to other statistical methods for inverse reinforcement learning via analysis and experimental results. We show that preferences can be determined accurately, even if the observed agent's policy is sub-optimal with respect to its own preferences. In that case, significantly improved policies with respect to the agent's preferences are obtained, compared to both other methods and to the performance of the demonstrated policy.", "source": "arxiv/ml"}
{"id": "arxiv:883", "title": "Rapid Learning with Stochastic Focus of Attention", "text": "We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online margin-based machine learning algorithms where a classifier traditionally evaluates all the features for every example. We observe that some examples are easier to classify than others, a phenomenon which is characterized by the event when most of the features agree on the class of an example. By stopping the feature evaluation when encountering an easy to classify example, the learning algorithm can achieve substantial gains in computation. Our method provides a natural attention mechanism for learning algorithms. By modifying Pegasos, a margin-based online learning algorithm, to include our attentive method we lower the number of attributes computed from $n$ to an average of $O(\\sqrt{n})$ features without loss in prediction accuracy. We demonstrate the effectiveness of Attentive Pegasos on MNIST data.", "source": "arxiv/ml"}
{"id": "arxiv:884", "title": "Suboptimal Solution Path Algorithm for Support Vector Machine", "text": "We consider a suboptimal solution path algorithm for the Support Vector Machine. The solution path algorithm is an effective tool for solving a sequence of a parametrized optimization problems in machine learning. The path of the solutions provided by this algorithm are very accurate and they satisfy the optimality conditions more strictly than other SVM optimization algorithms. In many machine learning application, however, this strict optimality is often unnecessary, and it adversely affects the computational efficiency. Our algorithm can generate the path of suboptimal solutions within an arbitrary user-specified tolerance level. It allows us to control the trade-off between the accuracy of the solution and the computational cost. Moreover, We also show that our suboptimal solutions can be interpreted as the solution of a \\emph{perturbed optimization problem} from the original one. We provide some theoretical analyses of our algorithm based on this novel interpretation. The experimental results also demonstrate the effectiveness of our algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:885", "title": "Pruning nearest neighbor cluster trees", "text": "Nearest neighbor (k-NN) graphs are widely used in machine learning and data mining applications, and our aim is to better understand what they reveal about the cluster structure of the unknown underlying distribution of points. Moreover, is it possible to identify spurious structures that might arise due to sampling variability? Our first contribution is a statistical analysis that reveals how certain subgraphs of a k-NN graph form a consistent estimator of the cluster tree of the underlying distribution of points. Our second and perhaps most important contribution is the following finite sample guarantee. We carefully work out the tradeoff between aggressive and conservative pruning and are able to guarantee the removal of all spurious cluster structures at all levels of the tree while at the same time guaranteeing the recovery of salient clusters. This is the first such finite sample result in the context of clustering.", "source": "arxiv/ml"}
{"id": "arxiv:886", "title": "Domain Adaptation: Overfitting and Small Sample Statistics", "text": "We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our goal is to generalize to a new domain. For example, we may want to learn a similarity function using only certain classes of objects, but we desire that this similarity function be applicable to object classes not present in our training sample (e.g. we might seek to learn that \"dogs are similar to dogs\" even though images of dogs were absent from our training set). Our theoretical analysis shows that we can select many more features than domains while avoiding overfitting by utilizing data-dependent variance properties. We present a greedy feature selection algorithm based on using T-statistics. Our experiments validate this theory showing that our T-statistic based greedy feature selection is more robust at avoiding overfitting than the classical greedy procedure.", "source": "arxiv/ml"}
{"id": "arxiv:887", "title": "Rapid Feature Learning with Stacked Linear Denoisers", "text": "We investigate unsupervised pre-training of deep architectures as feature generators for \"shallow\" classifiers. Stacked Denoising Autoencoders (SdA), when used as feature pre-processing tools for SVM classification, can lead to significant improvements in accuracy - however, at the price of a substantial increase in computational cost. In this paper we create a simple algorithm which mimics the layer by layer training of SdAs. However, in contrast to SdAs, our algorithm requires no training through gradient descent as the parameters can be computed in closed-form. It can be implemented in less than 20 lines of MATLABTMand reduces the computation time from several hours to mere seconds. We show that our feature transformation reliably improves the results of SVM classification significantly on all our data sets - often outperforming SdAs and even deep neural networks in three out of four deep learning benchmarks.", "source": "arxiv/ml"}
{"id": "arxiv:888", "title": "Adaptively Learning the Crowd Kernel", "text": "We introduce an algorithm that, given n objects, learns a similarity matrix over all n^2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen triplet-based relative-similarity queries. Each query has the form \"is object 'a' more similar to 'b' or to 'c'?\" and is chosen to be maximally informative given the preceding responses. The output is an embedding of the objects into Euclidean space (like MDS); we refer to this as the \"crowd kernel.\" SVMs reveal that the crowd kernel captures prominent and subtle features across a number of domains, such as \"is striped\" among neckties and \"vowel vs. consonant\" among letters.", "source": "arxiv/ml"}
{"id": "arxiv:889", "title": "Interpreting Graph Cuts as a Max-Product Algorithm", "text": "The maximum a posteriori (MAP) configuration of binary variable models with submodular graph-structured energy functions can be found efficiently and exactly by graph cuts. Max-product belief propagation (MP) has been shown to be suboptimal on this class of energy functions by a canonical counterexample where MP converges to a suboptimal fixed point (Kulesza & Pereira, 2008). In this work, we show that under a particular scheduling and damping scheme, MP is equivalent to graph cuts, and thus optimal. We explain the apparent contradiction by showing that with proper scheduling and damping, MP always converges to an optimal fixed point. Thus, the canonical counterexample only shows the suboptimality of MP with a particular suboptimal choice of schedule and damping. With proper choices, MP is optimal.", "source": "arxiv/ml"}
{"id": "arxiv:890", "title": "Self-configuration from a Machine-Learning Perspective", "text": "The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for machine learning (e.g. data mining or board games), most applications beyond the level of toy problems need careful hand-tuning or human ingenuity (i.e. detection of interesting patterns) or both. We discuss several aspects how self-configuration can help to alleviate these problems. One aspect is the self-configuration by tuning of algorithms, where recent advances have been made in the area of SPO (Sequen- tial Parameter Optimization). Another aspect is the self-configuration by pattern detection or feature construction. Forming multiple features (e.g. random boolean functions) and using algorithms (e.g. random forests) which easily digest many fea- tures can largely increase learning speed. However, a full-fledged theory of feature construction is not yet available and forms a current barrier in machine learning. We discuss several ideas for systematic inclusion of feature construction. This may lead to partly self-configuring machine learning solutions which show robustness, flexibility, and fast learning in potentially changing environments.", "source": "arxiv/ml"}
{"id": "arxiv:891", "title": "Generalized Boosting Algorithms for Convex Optimization", "text": "Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks, we analyze gradient-based descent algorithms for boosting with respect to any convex objective and introduce a new measure of weak learner performance into this setting which generalizes existing work. We present the weak to strong learning guarantees for the existing gradient boosting work for strongly-smooth, strongly-convex objectives under this new measure of performance, and also demonstrate that this work fails for non-smooth objectives. To address this issue, we present new algorithms which extend this boosting approach to arbitrary convex loss functions and give corresponding weak to strong convergence results. In addition, we demonstrate experimental results that support our analysis and demonstrate the need for the new algorithms we present.", "source": "arxiv/ml"}
{"id": "arxiv:892", "title": "A Framework for Optimization under Limited Information", "text": "In many real world problems, optimization decisions have to be made with limited information. The decision maker may have no a priori or posteriori data about the often nonconvex objective function except from on a limited number of points that are obtained over time through costly observations. This paper presents an optimization framework that takes into account the information collection (observation), estimation (regression), and optimization (maximization) aspects in a holistic and structured manner. Explicitly quantifying the information acquired at each optimization step using the entropy measure from information theory, the (nonconvex) objective function to be optimized (maximized) is modeled and estimated by adopting a Bayesian approach and using Gaussian processes as a state-of-the-art regression method. The resulting iterative scheme allows the decision maker to solve the problem by expressing preferences for each aspect quantitatively and concurrently.", "source": "arxiv/ml"}
{"id": "arxiv:893", "title": "Dual Control with Active Learning using Gaussian Process Regression", "text": "In many real world problems, control decisions have to be made with limited information. The controller may have no a priori (or even posteriori) data on the nonlinear system, except from a limited number of points that are obtained over time. This is either due to high cost of observation or the highly non-stationary nature of the system. The resulting conflict between information collection (identification, exploration) and control (optimization, exploitation) necessitates an active learning approach for iteratively selecting the control actions which concurrently provide the data points for system identification. This paper presents a dual control approach where the information acquired at each control step is quantified using the entropy measure from information theory and serves as the training input to a state-of-the-art Gaussian process regression (Bayesian learning) method. The explicit quantification of the information obtained from each data point allows for iterative optimization of both identification and control objectives. The approach developed is illustrated with two examples: control of logistic map as a chaotic system and position control of a cart with inverted pendulum.", "source": "arxiv/ml"}
{"id": "arxiv:894", "title": "Data-Distributed Weighted Majority and Online Mirror Descent", "text": "In this paper, we focus on the question of the extent to which online learning can benefit from distributed computing. We focus on the setting in which $N$ agents online-learn cooperatively, where each agent only has access to its own data. We propose a generic data-distributed online learning meta-algorithm. We then introduce the Distributed Weighted Majority and Distributed Online Mirror Descent algorithms, as special cases. We show, using both theoretical analysis and experiments, that compared to a single agent: given the same computation time, these distributed algorithms achieve smaller generalization errors; and given the same generalization errors, they can be $N$ times faster.", "source": "arxiv/ml"}
{"id": "arxiv:895", "title": "PAC-Bayesian Analysis of Martingales and Multiarmed Bandits", "text": "We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by expectations of the same functions of independent Bernoulli random variables. This lemma provides an alternative tool to Hoeffding-Azuma inequality to bound concentration of martingale values. Our second approach is based on integration of Hoeffding-Azuma inequality with PAC-Bayesian analysis. We also introduce a way to apply PAC-Bayesian analysis in situation of limited feedback. We combine the new tools to derive PAC-Bayesian generalization and regret bounds for the multiarmed bandit problem. Although our regret bound is not yet as tight as state-of-the-art regret bounds based on other well-established techniques, our results significantly expand the range of potential applications of PAC-Bayesian analysis and introduce a new analysis tool to reinforcement learning and many other fields, where martingales and limited feedback are encountered.", "source": "arxiv/ml"}
{"id": "arxiv:896", "title": "A Maximal Large Deviation Inequality for Sub-Gaussian Variables", "text": "In this short note we prove a maximal concentration lemma for sub-Gaussian random variables stating that for independent sub-Gaussian random variables we have \\[P<(\\max_{1\\le i\\le N}S_{i}>\\epsilon>) \\le\\exp<(-\\frac{1}{N^2}\\sum_{i=1}^{N}\\frac{\\epsilon^{2}}{2\\sigma_{i}^{2}}>), \\] where $S_i$ is the sum of $i$ zero mean independent sub-Gaussian random variables and $\\sigma_i$ is the variance of the $i$th random variable.", "source": "arxiv/ml"}
{"id": "arxiv:897", "title": "A Note on the Entropy/Influence Conjecture", "text": "The entropy/influence conjecture, raised by Friedgut and Kalai in 1996, seeks to relate two different measures of concentration of the Fourier coefficients of a Boolean function. Roughly saying, it claims that if the Fourier spectrum is \"smeared out\", then the Fourier coefficients are concentrated on \"high\" levels. In this note we generalize the conjecture to biased product measures on the discrete cube, and prove a variant of the conjecture for functions with an extremely low Fourier weight on the \"high\" levels.", "source": "arxiv/ml"}
{"id": "arxiv:898", "title": "Semantic Vector Machines", "text": "We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an $d$-dimensional space, such that n-grams that are the translation of each other are close with respect to some metric. Good n-grams to n-grams translation results were achieved, but full sentences translation is still problematic. We realized that learning semantics of sentences and documents was the key for solving a lot of natural language processing problems, and thus moved to the second part of our work: sentence compression. We introduce a flexible neural network architecture for learning embeddings of words and sentences that extract their semantics, propose an efficient implementation in the Torch framework and present embedding results comparable to the ones obtained with classical neural language models, while being more powerful.", "source": "arxiv/ml"}
{"id": "arxiv:899", "title": "Feature Selection for MAUC-Oriented Classification Systems", "text": "Feature selection is an important pre-processing step for many pattern classification tasks. Traditionally, feature selection methods are designed to obtain a feature subset that can lead to high classification accuracy. However, classification accuracy has recently been shown to be an inappropriate performance metric of classification systems in many cases. Instead, the Area Under the receiver operating characteristic Curve (AUC) and its multi-class extension, MAUC, have been proved to be better alternatives. Hence, the target of classification system design is gradually shifting from seeking a system with the maximum classification accuracy to obtaining a system with the maximum AUC/MAUC. Previous investigations have shown that traditional feature selection methods need to be modified to cope with this new objective. These methods most often are restricted to binary classification problems only. In this study, a filter feature selection method, namely MAUC Decomposition based Feature Selection (MDFS), is proposed for multi-class classification problems. To the best of our knowledge, MDFS is the first method specifically designed to select features for building classification systems with maximum MAUC. Extensive empirical results demonstrate the advantage of MDFS over several compared feature selection methods.", "source": "arxiv/ml"}
{"id": "arxiv:900", "title": "On R\\'enyi and Tsallis entropies and divergences for exponential families", "text": "Many common probability distributions in statistics like the Gaussian, multinomial, Beta or Gamma distributions can be studied under the unified framework of exponential families. In this paper, we prove that both R\\'enyi and Tsallis divergences of distributions belonging to the same exponential family admit a generic closed form expression. Furthermore, we show that R\\'enyi and Tsallis entropies can also be calculated in closed-form for sub-families including the Gaussian or exponential distributions, among others.", "source": "arxiv/ml"}
{"id": "arxiv:901", "title": "Behavior of Graph Laplacians on Manifolds with Boundary", "text": "In manifold learning, algorithms based on graph Laplacians constructed from data have received considerable attention both in practical applications and theoretical analysis. In particular, the convergence of graph Laplacians obtained from sampled data to certain continuous operators has become an active research topic recently. Most of the existing work has been done under the assumption that the data is sampled from a manifold without boundary or that the functions of interests are evaluated at a point away from the boundary. However, the question of boundary behavior is of considerable practical and theoretical interest. In this paper we provide an analysis of the behavior of graph Laplacians at a point near or on the boundary, discuss their convergence rates and their implications and provide some numerical results. It turns out that while points near the boundary occupy only a small part of the total volume of a manifold, the behavior of graph Laplacian there has different scaling properties from its behavior elsewhere on the manifold, with global effects on the whole manifold, an observation with potentially important implications for the general problem of learning on manifolds.", "source": "arxiv/ml"}
{"id": "arxiv:902", "title": "Adaptive and optimal online linear regression on $\\ell^1$-balls", "text": "We consider the problem of online linear regression on individual sequences. The goal in this paper is for the forecaster to output sequential predictions which are, after $T$ time rounds, almost as good as the ones output by the best linear predictor in a given $\\ell^1$-ball in $\\\\R^d$. We consider both the cases where the dimension~$d$ is small and large relative to the time horizon $T$. We first present regret bounds with optimal dependencies on $d$, $T$, and on the sizes $U$, $X$ and $Y$ of the $\\ell^1$-ball, the input data and the observations. The minimax regret is shown to exhibit a regime transition around the point $d = \\sqrt{T} U X / (2 Y)$. Furthermore, we present efficient algorithms that are adaptive, \\ie, that do not require the knowledge of $U$, $X$, $Y$, and $T$, but still achieve nearly optimal regret bounds.", "source": "arxiv/ml"}
{"id": "arxiv:903", "title": "Calibration with Changing Checking Rules and Its Application to Short-Term Trading", "text": "We provide a natural learning process in which a financial trader without a risk receives a gain in case when Stock Market is inefficient. In this process, the trader rationally choose his gambles using a prediction made by a randomized calibrated algorithm. Our strategy is based on Dawid's notion of calibration with more general changing checking rules and on some modification of Kakade and Foster's randomized algorithm for computing calibrated forecasts.", "source": "arxiv/ml"}
{"id": "arxiv:904", "title": "b-Bit Minwise Hashing for Large-Scale Linear SVM", "text": "In this paper, we propose to (seamlessly) integrate b-bit minwise hashing with linear SVM to substantially improve the training (and testing) efficiency using much smaller memory, with essentially no loss of accuracy. Theoretically, we prove that the resemblance matrix, the minwise hashing matrix, and the b-bit minwise hashing matrix are all positive definite matrices (kernels). Interestingly, our proof for the positive definiteness of the b-bit minwise hashing kernel naturally suggests a simple strategy to integrate b-bit hashing with linear SVM. Our technique is particularly useful when the data can not fit in memory, which is an increasingly critical issue in large-scale machine learning. Our preliminary experimental results on a publicly available webspam dataset (350K samples and 16 million dimensions) verified the effectiveness of our algorithm. For example, the training time was reduced to merely a few seconds. In addition, our technique can be easily extended to many other linear and nonlinear machine learning applications such as logistic regression.", "source": "arxiv/ml"}
{"id": "arxiv:905", "title": "PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off", "text": "We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combination is also of independent interest for studies of multiple simultaneously evolving martingales.", "source": "arxiv/ml"}
{"id": "arxiv:906", "title": "Bounding the Fat Shattering Dimension of a Composition Function Class Built Using a Continuous Logic Connective", "text": "We begin this report by describing the Probably Approximately Correct (PAC) model for learning a concept class, consisting of subsets of a domain, and a function class, consisting of functions from the domain to the unit interval. Two combinatorial parameters, the Vapnik-Chervonenkis (VC) dimension and its generalization, the Fat Shattering dimension of scale e, are explained and a few examples of their calculations are given with proofs. We then explain Sauer's Lemma, which involves the VC dimension and is used to prove the equivalence of a concept class being distribution-free PAC learnable and it having finite VC dimension. As the main new result of our research, we explore the construction of a new function class, obtained by forming compositions with a continuous logic connective, a uniformly continuous function from the unit hypercube to the unit interval, from a collection of function classes. Vidyasagar had proved that such a composition function class has finite Fat Shattering dimension of all scales if the classes in the original collection do; however, no estimates of the dimension were known. Using results by Mendelson-Vershynin and Talagrand, we bound the Fat Shattering dimension of scale e of this new function class in terms of the Fat Shattering dimensions of the collection's classes. We conclude this report by providing a few open questions and future research topics involving the PAC learning model.", "source": "arxiv/ml"}
{"id": "arxiv:907", "title": "Online Learning, Stability, and Stochastic Gradient Descent", "text": "In batch learning, stability together with existence and uniqueness of the solution corresponds to well-posedness of Empirical Risk Minimization (ERM) methods; recently, it was proved that CV_loo stability is necessary and sufficient for generalization and consistency of ERM. In this note, we introduce CV_on stability, which plays a similar note in online learning. We show that stochastic gradient descent (SDG) with the usual hypotheses is CVon stable and we then discuss the implications of CV_on stability for convergence of SGD.", "source": "arxiv/ml"}
{"id": "arxiv:908", "title": "Robust approachability and regret minimization in games with partial monitoring", "text": "Approachability has become a standard tool in analyzing earning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms (i.e., with constant per-step complexity) for this setup. We finally consider external regret and internal regret in repeated games with partial monitoring and derive regret-minimizing strategies based on approachability theory.", "source": "arxiv/ml"}
{"id": "arxiv:909", "title": "Large-Scale Music Annotation and Retrieval: Learning to Rank in Joint Semantic Spaces", "text": "Music prediction tasks range from predicting tags given a song or clip of audio, predicting the name of the artist, or predicting related songs given a song, clip, artist name or tag. That is, we are interested in every semantic relationship between the different musical concepts in our database. In realistically sized databases, the number of songs is measured in the hundreds of thousands or more, and the number of artists in the tens of thousands or more, providing a considerable challenge to standard machine learning techniques. In this work, we propose a method that scales to such datasets which attempts to capture the semantic similarities between the database items by modeling audio, artist names, and tags in a single low-dimensional semantic space. This choice of space is learnt by optimizing the set of prediction tasks of interest jointly using multi-task learning. Our method both outperforms baseline methods and, in comparison to them, is faster and consumes less memory. We then demonstrate how our method learns an interpretable model, where the semantic space captures well the similarities of interest.", "source": "arxiv/ml"}
{"id": "arxiv:910", "title": "Parallel Coordinate Descent for L1-Regularized Loss Minimization", "text": "We propose Shotgun, a parallel coordinate descent algorithm for minimizing L1-regularized losses. Though coordinate descent seems inherently sequential, we prove convergence bounds for Shotgun which predict linear speedups, up to a problem-dependent limit. We present a comprehensive empirical study of Shotgun for Lasso and sparse logistic regression. Our theoretical predictions on the potential for parallelism closely match behavior on real data. Shotgun outperforms other published solvers on a range of large problems, proving to be one of the most scalable algorithms for L1.", "source": "arxiv/ml"}
{"id": "arxiv:911", "title": "Learning to Order Things", "text": "There are many applications in which it is desirable to order rather than classify instances. Here we consider the problem of learning how to order instances given feedback in the form of preference judgments, i.e., statements to the effect that one instance should be ranked ahead of another. We outline a two-stage approach in which one first learns by conventional means a binary preference function indicating whether it is advisable to rank one instance before another. Here we consider an on-line algorithm for learning preference functions that is based on Freund and Schapire's 'Hedge' algorithm. In the second stage, new instances are ordered so as to maximize agreement with the learned preference function. We show that the problem of finding the ordering that agrees best with a learned preference function is NP-complete. Nevertheless, we describe simple greedy algorithms that are guaranteed to find a good approximation. Finally, we show how metasearch can be formulated as an ordering problem, and present experimental results on learning a combination of 'search experts', each of which is a domain-specific query expansion strategy for a web search engine.", "source": "arxiv/ml"}
{"id": "arxiv:912", "title": "Kernel Belief Propagation", "text": "We propose a nonparametric generalization of belief propagation, Kernel Belief Propagation (KBP), for pairwise Markov random fields. Messages are represented as functions in a reproducing kernel Hilbert space (RKHS), and message updates are simple linear operations in the RKHS. KBP makes none of the assumptions commonly required in classical BP algorithms: the variables need not arise from a finite domain or a Gaussian distribution, nor must their relations take any particular parametric form. Rather, the relations between variables are represented implicitly, and are learned nonparametrically from training data. KBP has the advantage that it may be used on any domain where kernels are defined (Rd, strings, groups), even where explicit parametric models are not known, or closed form expressions for the BP updates do not exist. The computational cost of message updates in KBP is polynomial in the training data size. We also propose a constant time approximate message update procedure by representing messages using a small number of basis functions. In experiments, we apply KBP to image denoising, depth prediction from still images, and protein configuration prediction: KBP is faster than competing classical and nonparametric approaches (by orders of magnitude, in some cases), while providing significantly more accurate results.", "source": "arxiv/ml"}
{"id": "arxiv:913", "title": "A Philosophical Treatise of Universal Induction", "text": "Understanding inductive reasoning is a problem that has engaged mankind for thousands of years. This problem is relevant to a wide range of fields and is integral to the philosophy of science. It has been tackled by many great minds ranging from philosophers to scientists to mathematicians, and more recently computer scientists. In this article we argue the case for Solomonoff Induction, a formal inductive framework which combines algorithmic information theory with the Bayesian framework. Although it achieves excellent theoretical results and is based on solid philosophical foundations, the requisite technical knowledge necessary for understanding this framework has caused it to remain largely unknown and unappreciated in the wider scientific community. The main contribution of this article is to convey Solomonoff induction and its related concepts in a generally accessible form with the aim of bridging this current technical gap. In the process we examine the major historical contributions that have led to the formulation of Solomonoff Induction as well as criticisms of Solomonoff and induction in general. In particular we examine how Solomonoff induction addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem, and compare this approach with other recent approaches.", "source": "arxiv/ml"}
{"id": "arxiv:914", "title": "Efficient sampling of high-dimensional Gaussian fields: the non-stationary / non-sparse case", "text": "This paper is devoted to the problem of sampling Gaussian fields in high dimension. Solutions exist for two specific structures of inverse covariance : sparse and circulant. The proposed approach is valid in a more general case and especially as it emerges in inverse problems. It relies on a perturbation-optimization principle: adequate stochastic perturbation of a criterion and optimization of the perturbed criterion. It is shown that the criterion minimizer is a sample of the target density. The motivation in inverse problems is related to general (non-convolutive) linear observation models and their resolution in a Bayesian framework implemented through sampling algorithms when existing samplers are not feasible. It finds a direct application in myopic and/or unsupervised inversion as well as in some non-Gaussian inversion. An illustration focused on hyperparameter estimation for super-resolution problems assesses the effectiveness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:915", "title": "The Perceptron with Dynamic Margin", "text": "The classical perceptron rule provides a varying upper bound on the maximum margin, namely the length of the current weight vector divided by the total number of updates up to that time. Requiring that the perceptron updates its internal state whenever the normalized margin of a pattern is found not to exceed a certain fraction of this dynamic upper bound we construct a new approximate maximum margin classifier called the perceptron with dynamic margin (PDM). We demonstrate that PDM converges in a finite number of steps and derive an upper bound on them. We also compare experimentally PDM with other perceptron-like algorithms and support vector machines on hard margin tasks involving linear kernels which are equivalent to 2-norm soft margin.", "source": "arxiv/ml"}
{"id": "arxiv:916", "title": "Evolutionary Algorithms for Reinforcement Learning", "text": "There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are well-known examples of these approaches. Kaelbling, Littman and Moore recently provided an informative survey of temporal difference methods. This article focuses on the application of evolutionary algorithms to the reinforcement learning problem, emphasizing alternative policy representations, credit assignment methods, and problem-specific genetic operators. Strengths and weaknesses of the evolutionary approach to reinforcement learning are presented, along with a survey of representative applications.", "source": "arxiv/ml"}
{"id": "arxiv:917", "title": "Learning Hierarchical Sparse Representations using Iterative Dictionary Learning and Dimension Reduction", "text": "This paper introduces an elemental building block which combines Dictionary Learning and Dimension Reduction (DRDL). We show how this foundational element can be used to iteratively construct a Hierarchical Sparse Representation (HSR) of a sensory stream. We compare our approach to existing models showing the generality of our simple prescription. We then perform preliminary experiments using this framework, illustrating with the example of an object recognition task using standard datasets. This work introduces the very first steps towards an integrated framework for designing and analyzing various computational tasks from learning to attention to action. The ultimate goal is building a mathematically rigorous, integrated theory of intelligence.", "source": "arxiv/ml"}
{"id": "arxiv:918", "title": "Learning unbelievable marginal probabilities", "text": "Loopy belief propagation performs approximate inference on graphical models with loops. One might hope to compensate for the approximation by adjusting model parameters. Learning algorithms for this purpose have been explored previously, and the claim has been made that every set of locally consistent marginals can arise from belief propagation run on a graphical model. On the contrary, here we show that many probability distributions have marginals that cannot be reached by belief propagation using any set of model parameters or any learning algorithm. We call such marginals `unbelievable.' This problem occurs whenever the Hessian of the Bethe free energy is not positive-definite at the target marginals. All learning algorithms for belief propagation necessarily fail in these cases, producing beliefs or sets of beliefs that may even be worse than the pre-learning approximation. We then show that averaging inaccurate beliefs, each obtained from belief propagation using model parameters perturbed about some learned mean values, can achieve the unbelievable marginals.", "source": "arxiv/ml"}
{"id": "arxiv:919", "title": "Submodular Functions Are Noise Stable", "text": "We show that all non-negative submodular functions have high {\\em noise-stability}. As a consequence, we obtain a polynomial-time learning algorithm for this class with respect to any product distribution on $\\{-1,1\\}^n$ (for any constant accuracy parameter $\\epsilon$). Our algorithm also succeeds in the agnostic setting. Previous work on learning submodular functions required either query access or strong assumptions about the types of submodular functions to be learned (and did not hold in the agnostic setting).", "source": "arxiv/ml"}
{"id": "arxiv:920", "title": "Experiments with Infinite-Horizon, Policy-Gradient Estimation", "text": "In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter and Bartlett, this volume), which computes biased estimates of the performance gradient in POMDPs. The algorithm's chief advantages are that it uses only one free parameter beta, which has a natural interpretation in terms of bias-variance trade-off, it requires no knowledge of the underlying state, and it can be applied to infinite state, control and observation spaces. We show how the gradient estimates produced by GPOMDP can be used to perform gradient ascent, both with a traditional stochastic-gradient algorithm, and with an algorithm based on conjugate-gradients that utilizes gradient information to bracket maxima in line searches. Experimental results are presented illustrating both the theoretical results of (Baxter and Bartlett, this volume) on a toy problem, and practical aspects of the algorithms on a number of more realistic problems.", "source": "arxiv/ml"}
{"id": "arxiv:921", "title": "Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System", "text": "Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue policy, which addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We report on the design, construction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey. Our results show that by optimizing its performance via reinforcement learning, NJFun measurably improves system performance.", "source": "arxiv/ml"}
{"id": "arxiv:922", "title": "Accelerating Reinforcement Learning through Implicit Imitation", "text": "Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents. We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases. Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space. We study two specific instantiations of this model, one in which the learning agent and the mentor have identical abilities, and one designed to deal with agents and mentors with different action sets. We illustrate the benefits of implicit imitation by integrating it with prioritized sweeping, and demonstrating improved performance and convergence through observation of single and multiple mentors. Though we make some stringent assumptions regarding observability and possible interactions, we briefly comment on extensions of the model that relax these restricitions.", "source": "arxiv/ml"}
{"id": "arxiv:923", "title": "Efficient Reinforcement Learning Using Recursive Least-Squares Methods", "text": "The recursive least-squares (RLS) algorithm is one of the most well-known algorithms used in adaptive filtering, system identification and adaptive control. Its popularity is mainly due to its fast convergence speed, which is considered to be optimal in practice. In this paper, RLS methods are used to solve reinforcement learning problems, where two new reinforcement learning algorithms using linear value function approximators are proposed and analyzed. The two algorithms are called RLS-TD(lambda) and Fast-AHC (Fast Adaptive Heuristic Critic), respectively. RLS-TD(lambda) can be viewed as the extension of RLS-TD(0) from lambda=0 to general lambda within interval [0,1], so it is a multi-step temporal-difference (TD) learning algorithm using RLS methods. The convergence with probability one and the limit of convergence of RLS-TD(lambda) are proved for ergodic Markov chains. Compared to the existing LS-TD(lambda) algorithm, RLS-TD(lambda) has advantages in computation and is more suitable for online learning. The effectiveness of RLS-TD(lambda) is analyzed and verified by learning prediction experiments of Markov chains with a wide range of parameter settings. The Fast-AHC algorithm is derived by applying the proposed RLS-TD(lambda) algorithm in the critic network of the adaptive heuristic critic method. Unlike conventional AHC algorithm, Fast-AHC makes use of RLS methods to improve the learning-prediction efficiency in the critic. Learning control experiments of the cart-pole balancing and the acrobot swing-up problems are conducted to compare the data efficiency of Fast-AHC with conventional AHC. From the experimental results, it is shown that the data efficiency of learning control can also be improved by using RLS methods in the learning-prediction process of the critic. The performance of Fast-AHC is also compared with that of the AHC method using LS-TD(lambda). Furthermore, it is demonstrated in the experiments that different initial values of the variance matrix in RLS-TD(lambda) are required to get better performance not only in learning prediction but also in learning control. The experimental results are analyzed based on the existing theoretical work on the transient phase of forgetting factor RLS methods.", "source": "arxiv/ml"}
{"id": "arxiv:924", "title": "Rademacher complexity of stationary sequences", "text": "We show how to control the generalization error of time series models wherein past values of the outcome are used to predict future values. The results are based on a generalization of standard i.i.d. concentration inequalities to dependent data without the mixing assumptions common in the time series setting. Our proof and the result are simpler than previous analyses with dependent data or stochastic adversaries which use sequential Rademacher complexities rather than the expected Rademacher complexity for i.i.d. processes. We also derive empirical Rademacher results without mixing assumptions resulting in fully calculable upper bounds.", "source": "arxiv/ml"}
{"id": "arxiv:925", "title": "Optimal Reinforcement Learning for Gaussian Systems", "text": "The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are possible if all beliefs are Gaussian processes. A first order approximation of learning of both loss and dynamics, for nonlinear, time-varying systems in continuous time and space, subject to a relatively weak restriction on the dynamics, is described by an infinite-dimensional partial differential equation. An approximate finite-dimensional projection gives an impression for how this result may be helpful.", "source": "arxiv/ml"}
{"id": "arxiv:926", "title": "Hashing Algorithms for Large-Scale Learning", "text": "In this paper, we first demonstrate that b-bit minwise hashing, whose estimators are positive definite kernels, can be naturally integrated with learning algorithms such as SVM and logistic regression. We adopt a simple scheme to transform the nonlinear (resemblance) kernel into linear (inner product) kernel; and hence large-scale problems can be solved extremely efficiently. Our method provides a simple effective solution to large-scale learning in massive and extremely high-dimensional datasets, especially when data do not fit in memory. We then compare b-bit minwise hashing with the Vowpal Wabbit (VW) algorithm (which is related the Count-Min (CM) sketch). Interestingly, VW has the same variances as random projections. Our theoretical and empirical comparisons illustrate that usually $b$-bit minwise hashing is significantly more accurate (at the same storage) than VW (and random projections) in binary data. Furthermore, $b$-bit minwise hashing can be combined with VW to achieve further improvements in terms of training speed, especially when $b$ is large.", "source": "arxiv/ml"}
{"id": "arxiv:927", "title": "Nearest Prime Simplicial Complex for Object Recognition", "text": "The structure representation of data distribution plays an important role in understanding the underlying mechanism of generating data. In this paper, we propose nearest prime simplicial complex approaches (NSC) by utilizing persistent homology to capture such structures. Assuming that each class is represented with a prime simplicial complex, we classify unlabeled samples based on the nearest projection distances from the samples to the simplicial complexes. We also extend the extrapolation ability of these complexes with a projection constraint term. Experiments in simulated and practical datasets indicate that compared with several published algorithms, the proposed NSC approaches achieve promising performance without losing the structure representation.", "source": "arxiv/ml"}
{"id": "arxiv:928", "title": "Complexity Analysis of Vario-eta through Structure", "text": "Graph-based representations of images have recently acquired an important role for classification purposes within the context of machine learning approaches. The underlying idea is to consider that relevant information of an image is implicitly encoded into the relationships between more basic entities that compose by themselves the whole image. The classification problem is then reformulated in terms of an optimization problem usually solved by a gradient-based search procedure. Vario-eta through structure is an approximate second order stochastic optimization technique that achieves a good trade-off between speed of convergence and the computational effort required. However, the robustness of this technique for large scale problems has not been yet assessed. In this paper we firstly provide a theoretical justification of the assumptions made by this optimization procedure. Secondly, a complexity analysis of the algorithm is performed to prove its suitability for large scale learning problems.", "source": "arxiv/ml"}
{"id": "arxiv:929", "title": "Bayesian and L1 Approaches to Sparse Unsupervised Learning", "text": "The use of L1 regularisation for sparse learning has generated immense research interest, with successful application in such diverse areas as signal acquisition, image coding, genomics and collaborative filtering. While existing work highlights the many advantages of L1 methods, in this paper we find that L1 regularisation often dramatically underperforms in terms of predictive performance when compared with other methods for inferring sparsity. We focus on unsupervised latent variable models, and develop L1 minimising factor models, Bayesian variants of \"L1\", and Bayesian models with a stronger L0-like sparsity induced through spike-and-slab distributions. These spike-and-slab Bayesian factor models encourage sparsity while accounting for uncertainty in a principled manner and avoiding unnecessary shrinkage of non-zero values. We demonstrate on a number of data sets that in practice spike-and-slab Bayesian methods outperform L1 minimisation, even on a computational budget. We thus highlight the need to re-assess the wide use of L1 methods in sparsity-reliant applications, particularly when we care about generalising to previously unseen data, and provide an alternative that, over many varying conditions, provides improved generalisation performance.", "source": "arxiv/ml"}
{"id": "arxiv:930", "title": "Using More Data to Speed-up Training Time", "text": "In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more data can be leveraged to reduce the required training runtime. In this paper, we study the runtime of learning as a function of the number of available training examples, and underscore the main high-level techniques. We provide some initial positive results showing that the runtime can decrease exponentially while only requiring a polynomial growth of the number of examples, and spell-out several interesting open problems.", "source": "arxiv/ml"}
{"id": "arxiv:931", "title": "A Unified Framework for Approximating and Clustering Data", "text": "Given a set $F$ of $n$ positive functions over a ground set $X$, we consider the problem of computing $x^*$ that minimizes the expression $\\sum_{f\\in F}f(x)$, over $x\\in X$. A typical application is \\emph{shape fitting}, where we wish to approximate a set $P$ of $n$ elements (say, points) by a shape $x$ from a (possibly infinite) family $X$ of shapes. Here, each point $p\\in P$ corresponds to a function $f$ such that $f(x)$ is the distance from $p$ to $x$, and we seek a shape $x$ that minimizes the sum of distances from each point in $P$. In the $k$-clustering variant, each $x\\in X$ is a tuple of $k$ shapes, and $f(x)$ is the distance from $p$ to its closest shape in $x$. Our main result is a unified framework for constructing {\\em coresets} and {\\em approximate clustering} for such general sets of functions. To achieve our results, we forge a link between the classic and well defined notion of $\\varepsilon$-approximations from the theory of PAC Learning and VC dimension, to the relatively new (and not so consistent) paradigm of coresets, which are some kind of \"compressed representation\" of the input set $F$. Using traditional techniques, a coreset usually implies an LTAS (linear time approximation scheme) for the corresponding optimization problem, which can be computed in parallel, via one pass over the data, and using only polylogarithmic space (i.e, in the streaming model). We show how to generalize the results of our framework for squared distances (as in $k$-mean), distances to the $q$th power, and deterministic constructions.", "source": "arxiv/ml"}
{"id": "arxiv:932", "title": "Large-Scale Convex Minimization with a Low-Rank Constraint", "text": "We address the problem of minimizing a convex function over the space of large matrices with low rank. While this optimization problem is hard in general, we propose an efficient greedy algorithm and derive its formal approximation guarantees. Each iteration of the algorithm involves (approximately) finding the left and right singular vectors corresponding to the largest singular value of a certain matrix, which can be calculated in linear time. This leads to an algorithm which can scale to large matrices arising in several applications such as matrix completion for collaborative filtering and robust low rank matrix approximation.", "source": "arxiv/ml"}
{"id": "arxiv:933", "title": "Sparse Principal Component of a Rank-deficient Matrix", "text": "We consider the problem of identifying the sparse principal component of a rank-deficient matrix. We introduce auxiliary spherical variables and prove that there exists a set of candidate index-sets (that is, sets of indices to the nonzero elements of the vector argument) whose size is polynomially bounded, in terms of rank, and contains the optimal index-set, i.e. the index-set of the nonzero elements of the optimal solution. Finally, we develop an algorithm that computes the optimal sparse principal component in polynomial time for any sparsity degree.", "source": "arxiv/ml"}
{"id": "arxiv:934", "title": "Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection", "text": "The main principle of stacked generalization (or Stacking) is using a second-level generalizer to combine the outputs of base classifiers in an ensemble. In this paper, we investigate different combination types under the stacking framework; namely weighted sum (WS), class-dependent weighted sum (CWS) and linear stacked generalization (LSG). For learning the weights, we propose using regularized empirical risk minimization with the hinge loss. In addition, we propose using group sparsity for regularization to facilitate classifier selection. We performed experiments using two different ensemble setups with differing diversities on 8 real-world datasets. Results show the power of regularized learning with the hinge loss function. Using sparse regularization, we are able to reduce the number of selected classifiers of the diverse ensemble without sacrificing accuracy. With the non-diverse ensembles, we even gain accuracy on average by using sparse regularization.", "source": "arxiv/ml"}
{"id": "arxiv:935", "title": "Reinforcement learning based sensing policy optimization for energy efficient cognitive radio networks", "text": "This paper introduces a machine learning based collaborative multi-band spectrum sensing policy for cognitive radios. The proposed sensing policy guides secondary users to focus the search of unused radio spectrum to those frequencies that persistently provide them high data rate. The proposed policy is based on machine learning, which makes it adaptive with the temporally and spatially varying radio spectrum. Furthermore, there is no need for dynamic modeling of the primary activity since it is implicitly learned over time. Energy efficiency is achieved by minimizing the number of assigned sensors per each subband under a constraint on miss detection probability. It is important to control the missed detections because they cause collisions with primary transmissions and lead to retransmissions at both the primary and secondary user. Simulations show that the proposed machine learning based sensing policy improves the overall throughput of the secondary network and improves the energy efficiency while controlling the miss detection probability.", "source": "arxiv/ml"}
{"id": "arxiv:936", "title": "Learning the Dependence Graph of Time Series with Latent Factors", "text": "This paper considers the problem of learning, from samples, the dependency structure of a system of linear stochastic differential equations, when some of the variables are latent. In particular, we observe the time evolution of some variables, and never observe other variables; from this, we would like to find the dependency structure between the observed variables - separating out the spurious interactions caused by the (marginalizing out of the) latent variables' time series. We develop a new method, based on convex optimization, to do so in the case when the number of latent variables is smaller than the number of observed ones. For the case when the dependency structure between the observed variables is sparse, we theoretically establish a high-dimensional scaling result for structure recovery. We verify our theoretical result with both synthetic and real data (from the stock market).", "source": "arxiv/ml"}
{"id": "arxiv:937", "title": "Ranking via Sinkhorn Propagation", "text": "It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular metrics such as precision and discounted cumulative gain. In particular, we observe that expectations of these gains are completely characterized by the marginals of the corresponding distribution over permutation matrices. Thus, the expectations of rank-linear objectives can always be described through locations in the Birkhoff polytope, i.e., doubly-stochastic matrices (DSMs). We propose a technique for learning DSM-based ranking functions using an iterative projection operator known as Sinkhorn normalization. Gradients of this operator can be computed via backpropagation, resulting in an algorithm we call Sinkhorn propagation, or SinkProp. This approach can be combined with a wide range of gradient-based approaches to rank learning. We demonstrate the utility of SinkProp on several information retrieval data sets.", "source": "arxiv/ml"}
{"id": "arxiv:938", "title": "Lyapunov stochastic stability and control of robust dynamic coalitional games with transferable utilities", "text": "This paper considers a dynamic game with transferable utilities (TU), where the characteristic function is a continuous-time bounded mean ergodic process. A central planner interacts continuously over time with the players by choosing the instantaneous allocations subject to budget constraints. Before the game starts, the central planner knows the nature of the process (bounded mean ergodic), the bounded set from which the coalitions' values are sampled, and the long run average coalitions' values. On the other hand, he has no knowledge of the underlying probability function generating the coalitions' values. Our goal is to find allocation rules that use a measure of the extra reward that a coalition has received up to the current time by re-distributing the budget among the players. The objective is two-fold: i) guaranteeing convergence of the average allocations to the core (or a specific point in the core) of the average game, ii) driving the coalitions' excesses to an a priori given cone. The resulting allocation rules are robust as they guarantee the aforementioned convergence properties despite the uncertain and time-varying nature of the coaltions' values. We highlight three main contributions. First, we design an allocation rule based on full observation of the extra reward so that the average allocation approaches a specific point in the core of the average game, while the coalitions' excesses converge to an a priori given direction. Second, we design a new allocation rule based on partial observation on the extra reward so that the average allocation converges to the core of the average game, while the coalitions' excesses converge to an a priori given cone. And third, we establish connections to approachability theory and attainability theory.", "source": "arxiv/ml"}
{"id": "arxiv:939", "title": "Clustering with Multi-Layer Graphs: A Spectral Perspective", "text": "Observational data usually comes with a multimodal nature, which means that it can be naturally represented by a multi-layer graph whose layers share the same set of vertices (users) with different edges (pairwise relationships). In this paper, we address the problem of combining different layers of the multi-layer graph for improved clustering of the vertices compared to using layers independently. We propose two novel methods, which are based on joint matrix factorization and graph regularization framework respectively, to efficiently combine the spectrum of the multiple graph layers, namely the eigenvectors of the graph Laplacian matrices. In each case, the resulting combination, which we call a \"joint spectrum\" of multiple graphs, is used for clustering the vertices. We evaluate our approaches by simulations with several real world social network datasets. Results demonstrate the superior or competitive performance of the proposed methods over state-of-the-art technique and common baseline methods, such as co-regularization and summation of information from individual graphs.", "source": "arxiv/ml"}
{"id": "arxiv:940", "title": "Random design analysis of ridge regression", "text": "This work gives a simultaneous analysis of both the ordinary least squares estimator and the ridge regression estimator in the random design setting under mild assumptions on the covariate/response distributions. In particular, the analysis provides sharp results on the ``out-of-sample'' prediction error, as opposed to the ``in-sample'' (fixed design) error. The analysis also reveals the effect of errors in the estimated covariance structure, as well as the effect of modeling errors, neither of which effects are present in the fixed design setting. The proofs of the main results are based on a simple decomposition lemma combined with concentration inequalities for random vectors and matrices.", "source": "arxiv/ml"}
{"id": "arxiv:941", "title": "Efficient Optimal Learning for Contextual Bandits", "text": "We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and has a running time $\\mathrm{polylog}(N)$, where $N$ is the number of classification rules among which the oracle might choose. This is exponentially faster than all previous algorithms that achieve optimal regret in this setting. Our formulation also enables us to create an algorithm with regret that is additive rather than multiplicative in feedback delay as in all previous work.", "source": "arxiv/ml"}
{"id": "arxiv:942", "title": "Efficient Transductive Online Learning via Randomized Rounding", "text": "Most traditional online learning algorithms are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, tailored for transductive settings, which combines \"random playout\" and randomized rounding of loss subgradients. As an application of our approach, we present the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question linking batch learning and transductive online learning", "source": "arxiv/ml"}
{"id": "arxiv:943", "title": "From Bandits to Experts: On the Value of Side-Observations", "text": "We consider an adversarial online learning setting where a decision maker can choose an action in every stage of the game. In addition to observing the reward of the chosen action, the decision maker gets side observations on the reward he would have obtained had he chosen some of the other actions. The observation structure is encoded as a graph, where node i is linked to node j if sampling i provides information on the reward of j. This setting naturally interpolates between the well-known \"experts\" setting, where the decision maker can view all rewards, and the multi-armed bandits setting, where the decision maker can only view the reward of the chosen action. We develop practical algorithms with provable regret guarantees, which depend on non-trivial graph-theoretic properties of the information feedback structure. We also provide partially-matching lower bounds.", "source": "arxiv/ml"}
{"id": "arxiv:944", "title": "Learning Equilibria with Partial Information in Decentralized Wireless Networks", "text": "In this article, a survey of several important equilibrium concepts for decentralized networks is presented. The term decentralized is used here to refer to scenarios where decisions (e.g., choosing a power allocation policy) are taken autonomously by devices interacting with each other (e.g., through mutual interference). The iterative long-term interaction is characterized by stable points of the wireless network called equilibria. The interest in these equilibria stems from the relevance of network stability and the fact that they can be achieved by letting radio devices to repeatedly interact over time. To achieve these equilibria, several learning techniques, namely, the best response dynamics, fictitious play, smoothed fictitious play, reinforcement learning algorithms, and regret matching, are discussed in terms of information requirements and convergence properties. Most of the notions introduced here, for both equilibria and learning schemes, are illustrated by a simple case study, namely, an interference channel with two transmitter-receiver pairs.", "source": "arxiv/ml"}
{"id": "arxiv:945", "title": "Learning, investments and derivatives", "text": "The recent crisis and the following flight to simplicity put most derivative businesses around the world under considerable pressure. We argue that the traditional modeling techniques must be extended to include product design. We propose a quantitative framework for creating products which meet the challenge of being optimal from the investors point of view while remaining relatively simple and transparent.", "source": "arxiv/ml"}
{"id": "arxiv:946", "title": "On epsilon-optimality of the pursuit learning algorithm", "text": "Estimator algorithms in learning automata are useful tools for adaptive, real-time optimization in computer science and engineering applications. This paper investigates theoretical convergence properties for a special case of estimator algorithms: the pursuit learning algorithm. In this note, we identify and fill a gap in existing proofs of probabilistic convergence for pursuit learning. It is tradition to take the pursuit learning tuning parameter to be fixed in practical applications, but our proof sheds light on the importance of a vanishing sequence of tuning parameters in a theoretical convergence analysis.", "source": "arxiv/ml"}
{"id": "arxiv:947", "title": "Decoding finger movements from ECoG signals using switching linear models", "text": "One of the major challenges of ECoG-based Brain-Machine Interfaces is the movement prediction of a human subject. Several methods exist to predict an arm 2-D trajectory. The fourth BCI Competition gives a dataset in which the aim is to predict individual finger movements (5-D trajectory). The difficulty lies in the fact that there is no simple relation between ECoG signals and finger movement. We propose in this paper to decode finger flexions using switching models. This method permits to simplify the system as it is now described as an ensemble of linear models depending on an internal state. We show that an interesting accuracy prediction can be obtained by such a model.", "source": "arxiv/ml"}
{"id": "arxiv:948", "title": "Large margin filtering for signal sequence labeling", "text": "Signal Sequence Labeling consists in predicting a sequence of labels given an observed sequence of samples. A naive way is to filter the signal in order to reduce the noise and to apply a classification algorithm on the filtered samples. We propose in this paper to jointly learn the filter with the classifier leading to a large margin filtering for classification. This method allows to learn the optimal cutoff frequency and phase of the filter that may be different from zero. Two methods are proposed and tested on a toy dataset and on a real life BCI dataset from BCI Competition III.", "source": "arxiv/ml"}
{"id": "arxiv:949", "title": "Handling uncertainties in SVM classification", "text": "This paper addresses the pattern classification problem arising when available target data include some uncertainty information. Target data considered here is either qualitative (a class label) or quantitative (an estimation of the posterior probability). Our main contribution is a SVM inspired formulation of this problem allowing to take into account class label through a hinge loss as well as probability estimates using epsilon-insensitive cost function together with a minimum norm (maximum margin) objective. This formulation shows a dual form leading to a quadratic problem and allows the use of a representer theorem and associated kernel. The solution provided can be used for both decision and posterior probability estimation. Based on empirical evidence our method outperforms regular SVM in terms of probability predictions and classification performances.", "source": "arxiv/ml"}
{"id": "arxiv:950", "title": "Robust Bayesian reinforcement learning through tight lower bounds", "text": "In the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinforcement learning problems. While utility bounds are known to exist for this problem, so far none of them were particularly tight. In this paper, we show how to efficiently calculate a lower bound, which corresponds to the utility of a near-optimal memoryless policy for the decision problem, which is generally different from both the Bayes-optimal policy and the policy which is optimal for the expected MDP under the current belief. We then show how these can be applied to obtain robust exploration policies in a Bayesian reinforcement learning setting.", "source": "arxiv/ml"}
{"id": "arxiv:951", "title": "Prediction and Modularity in Dynamical Systems", "text": "Identifying and understanding modular organizations is centrally important in the study of complex systems. Several approaches to this problem have been advanced, many framed in information-theoretic terms. Our treatment starts from the complementary point of view of statistical modeling and prediction of dynamical systems. It is known that for finite amounts of training data, simpler models can have greater predictive power than more complex ones. We use the trade-off between model simplicity and predictive accuracy to generate optimal multiscale decompositions of dynamical networks into weakly-coupled, simple modules. State-dependent and causal versions of our method are also proposed.", "source": "arxiv/ml"}
{"id": "arxiv:952", "title": "Learning XML Twig Queries", "text": "We investigate the problem of learning XML queries, path queries and tree pattern queries, from examples given by the user. A learning algorithm takes on the input a set of XML documents with nodes annotated by the user and returns a query that selects the nodes in a manner consistent with the annotation. We study two learning settings that differ with the types of annotations. In the first setting the user may only indicate required nodes that the query must return. In the second, more general, setting, the user may also indicate forbidden nodes that the query must not return. The query may or may not return any node with no annotation. We formalize what it means for a class of queries to be \\emph{learnable}. One requirement is the existence of a learning algorithm that is sound i.e., always returns a query consistent with the examples given by the user. Furthermore, the learning algorithm should be complete i.e., able to produce every query with a sufficiently rich example. Other requirements involve tractability of learning and its robustness to nonessential examples. We show that the classes of simple path queries and path-subsumption-free tree queries are learnable from positive examples. The learnability of the full class of tree pattern queries (and the full class of path queries) remains an open question. We show also that adding negative examples to the picture renders the learning unfeasible. Published in ICDT 2012, Berlin.", "source": "arxiv/ml"}
{"id": "arxiv:953", "title": "Algorithmic Programming Language Identification", "text": "Motivated by the amount of code that goes unidentified on the web, we introduce a practical method for algorithmically identifying the programming language of source code. Our work is based on supervised learning and intelligent statistical features. We also explored, but abandoned, a grammatical approach. In testing, our implementation greatly outperforms that of an existing tool that relies on a Bayesian classifier. Code is written in Python and available under an MIT license.", "source": "arxiv/ml"}
{"id": "arxiv:954", "title": "On the Inclusion Relation of Reproducing Kernel Hilbert Spaces", "text": "To help understand various reproducing kernels used in applied sciences, we investigate the inclusion relation of two reproducing kernel Hilbert spaces. Characterizations in terms of feature maps of the corresponding reproducing kernels are established. A full table of inclusion relations among widely-used translation invariant kernels is given. Concrete examples for Hilbert-Schmidt kernels are presented as well. We also discuss the preservation of such a relation under various operations of reproducing kernels. Finally, we briefly discuss the special inclusion with a norm equivalence.", "source": "arxiv/ml"}
{"id": "arxiv:955", "title": "Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions", "text": "We provide rigorous guarantees on learning with the weighted trace-norm under arbitrary sampling distributions. We show that the standard weighted trace-norm might fail when the sampling distribution is not a product distribution (i.e. when row and column indexes are not selected independently), present a corrected variant for which we establish strong learning guarantees, and demonstrate that it works better in practice. We provide guarantees when weighting by either the true or empirical sampling distribution, and suggest that even if the true distribution is known (or is uniform), weighting by the empirical distribution may be beneficial.", "source": "arxiv/ml"}
{"id": "arxiv:956", "title": "Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals", "text": "Standard compressive sensing results state that to exactly recover an s sparse signal in R^p, one requires O(s. log(p)) measurements. While this bound is extremely useful in practice, often real world signals are not only sparse, but also exhibit structure in the sparsity pattern. We focus on group-structured patterns in this paper. Under this model, groups of signal coefficients are active (or inactive) together. The groups are predefined, but the particular set of groups that are active (i.e., in the signal support) must be learned from measurements. We show that exploiting knowledge of groups can further reduce the number of measurements required for exact signal recovery, and derive universal bounds for the number of measurements needed. The bound is universal in the sense that it only depends on the number of groups under consideration, and not the particulars of the groups (e.g., compositions, sizes, extents, overlaps, etc.). Experiments show that our result holds for a variety of overlapping group configurations.", "source": "arxiv/ml"}
{"id": "arxiv:957", "title": "Specific-to-General Learning for Temporal Events with Application to Learning Event Definitions from Video", "text": "We develop, analyze, and evaluate a novel, supervised, specific-to-general learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions from video sequences. First, we introduce a simple, propositional, temporal, event-description language called AMA that is sufficiently expressive to represent many events yet sufficiently restrictive to support learning. We then give algorithms, along with lower and upper complexity bounds, for the subsumption and generalization problems for AMA formulas. We present a positive-examples--only specific-to-general learning method based on these algorithms. We also present a polynomial-time--computable ``syntactic'' subsumption test that implies semantic subsumption without being equivalent to it. A generalization algorithm based on syntactic subsumption can be used in place of semantic generalization to improve the asymptotic complexity of the resulting learning algorithm. Finally, we apply this algorithm to the task of learning relational event definitions from video and show that it yields definitions that are competitive with hand-coded ones.", "source": "arxiv/ml"}
{"id": "arxiv:958", "title": "Better Mini-Batch Algorithms via Accelerated Gradient Methods", "text": "Mini-batch algorithms have been proposed as a way to speed-up stochastic convex optimization problems. We study how such algorithms can be improved using accelerated gradient methods. We provide a novel analysis, which shows how standard gradient methods may sometimes be insufficient to obtain a significant speed-up and propose a novel accelerated gradient algorithm, which deals with this deficiency, enjoys a uniformly superior guarantee and works well in practice.", "source": "arxiv/ml"}
{"id": "arxiv:959", "title": "A General Framework for Structured Sparsity via Proximal Optimization", "text": "We study a generalized framework for structured sparsity. It extends the well-known methods of Lasso and Group Lasso by incorporating additional constraints on the variables as part of a convex optimization problem. This framework provides a straightforward way of favouring prescribed sparsity patterns, such as orderings, contiguous regions and overlapping groups, among others. Existing optimization methods are limited to specific constraint sets and tend to not scale well with sample size and dimensionality. We propose a novel first order proximal method, which builds upon results on fixed points and successive approximations. The algorithm can be applied to a general class of conic and norm constraints sets and relies on a proximity operator subproblem which can be computed explicitly. Experiments on different regression problems demonstrate the efficiency of the optimization algorithm and its scalability with the size of the problem. They also demonstrate state of the art statistical performance, which improves over Lasso and StructOMP.", "source": "arxiv/ml"}
{"id": "arxiv:960", "title": "Potential-Based Shaping and Q-Value Initialization are Equivalent", "text": "Shaping has proven to be a powerful but precarious means of improving reinforcement learning performance. Ng, Harada, and Russell (1999) proposed the potential-based shaping algorithm for adding shaping rewards in a way that guarantees the learner will learn optimal behavior. In this note, we prove certain similarities between this shaping algorithm and the initialization step required for several reinforcement learning algorithms. More specifically, we prove that a reinforcement learner with initial Q-values based on the shaping algorithm's potential function make the same updates throughout learning as a learner receiving potential-based shaping rewards. We further prove that under a broad category of policies, the behavior of these two learners are indistinguishable. The comparison provides intuition on the theoretical properties of the shaping algorithm as well as a suggestion for a simpler method for capturing the algorithm's benefit. In addition, the equivalence raises previously unaddressed issues concerning the efficiency of learning with potential-based shaping.", "source": "arxiv/ml"}
{"id": "arxiv:961", "title": "Set systems: order types, continuous nondeterministic deformations, and quasi-orders", "text": "By reformulating a learning process of a set system L as a game between Teacher and Learner, we define the order type of L to be the order type of the game tree, if the tree is well-founded. The features of the order type of L (dim L in symbol) are (1) We can represent any well-quasi-order (wqo for short) by the set system L of the upper-closed sets of the wqo such that the maximal order type of the wqo is equal to dim L. (2) dim L is an upper bound of the mind-change complexity of L. dim L is defined iff L has a finite elasticity (fe for short), where, according to computational learning theory, if an indexed family of recursive languages has fe then it is learnable by an algorithm from positive data. Regarding set systems as subspaces of Cantor spaces, we prove that fe of set systems is preserved by any continuous function which is monotone with respect to the set-inclusion. By it, we prove that finite elasticity is preserved by various (nondeterministic) language operators (Kleene-closure, shuffle-closure, union, product, intersection,. . ..) The monotone continuous functions represent nondeterministic computations. If a monotone continuous function has a computation tree with each node followed by at most n immediate successors and the order type of a set system L is {\\alpha}, then the direct image of L is a set system of order type at most n-adic diagonal Ramsey number of {\\alpha}. Furthermore, we provide an order-type-preserving contravariant embedding from the category of quasi-orders and finitely branching simulations between them, into the complete category of subspaces of Cantor spaces and monotone continuous functions having Girard's linearity between them. Keyword: finite elasticity, shuffle-closure", "source": "arxiv/ml"}
{"id": "arxiv:962", "title": "Pose Estimation from a Single Depth Image for Arbitrary Kinematic Skeletons", "text": "We present a method for estimating pose information from a single depth image given an arbitrary kinematic structure without prior training. For an arbitrary skeleton and depth image, an evolutionary algorithm is used to find the optimal kinematic configuration to explain the observed image. Results show that our approach can correctly estimate poses of 39 and 78 degree-of-freedom models from a single depth image, even in cases of significant self-occlusion.", "source": "arxiv/ml"}
{"id": "arxiv:963", "title": "HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent", "text": "Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but all require performance-destroying memory locking and synchronization. This work aims to show using novel theoretical analysis, algorithms, and implementation that SGD can be implemented without any locking. We present an update scheme called HOGWILD! which allows processors access to shared memory with the possibility of overwriting each other's work. We show that when the associated optimization problem is sparse, meaning most gradient updates only modify small parts of the decision variable, then HOGWILD! achieves a nearly optimal rate of convergence. We demonstrate experimentally that HOGWILD! outperforms alternative schemes that use locking by an order of magnitude.", "source": "arxiv/ml"}
{"id": "arxiv:964", "title": "A Dirty Model for Multiple Sparse Regression", "text": "Sparse linear regression -- finding an unknown vector from linear measurements -- is now known to be possible with fewer samples than variables, via methods like the LASSO. We consider the multiple sparse linear regression problem, where several related vectors -- with partially shared support sets -- have to be recovered. A natural question in this setting is whether one can use the sharing to further decrease the overall number of samples required. A line of recent research has studied the use of \\ell_1/\\ell_q norm block-regularizations with q>1 for such problems; however these could actually perform worse in sample complexity -- vis a vis solving each problem separately ignoring sharing -- depending on the level of sharing. We present a new method for multiple sparse linear regression that can leverage support and parameter overlap when it exists, but not pay a penalty when it does not. A very simple idea: we decompose the parameters into two components and regularize these differently. We show both theoretically and empirically, our method strictly and noticeably outperforms both \\ell_1 or \\ell_1/\\ell_q methods, over the entire range of possible overlaps (except at boundary cases, where we match the best method). We also provide theoretical guarantees that the method performs well under high-dimensional scaling.", "source": "arxiv/ml"}
{"id": "arxiv:965", "title": "Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems", "text": "In the Multi-Armed Bandit (MAB) problem, there is a given set of arms with unknown reward models. At each time, a player selects one arm to play, aiming to maximize the total expected reward over a horizon of length T. An approach based on a Deterministic Sequencing of Exploration and Exploitation (DSEE) is developed for constructing sequential arm selection policies. It is shown that for all light-tailed reward distributions, DSEE achieves the optimal logarithmic order of the regret, where regret is defined as the total expected reward loss against the ideal case with known reward models. For heavy-tailed reward distributions, DSEE achieves O(T^1/p) regret when the moments of the reward distributions exist up to the pth order for 1<p<=2 and O(T^1/(1+p/2)) for p>2. With the knowledge of an upperbound on a finite moment of the heavy-tailed reward distributions, DSEE offers the optimal logarithmic regret order. The proposed DSEE approach complements existing work on MAB by providing corresponding results for general reward distributions. Furthermore, with a clearly defined tunable parameter-the cardinality of the exploration sequence, the DSEE approach is easily extendable to variations of MAB, including MAB with various objectives, decentralized MAB with multiple players and incomplete reward observations under collisions, MAB with unknown Markov dynamics, and combinatorial MAB with dependent arms that often arise in network optimization problems such as the shortest path, the minimum spanning, and the dominating set problems under unknown random weights.", "source": "arxiv/ml"}
{"id": "arxiv:966", "title": "IBSEAD: - A Self-Evolving Self-Obsessed Learning Algorithm for Machine Learning", "text": "We present IBSEAD or distributed autonomous entity systems based Interaction - a learning algorithm for the computer to self-evolve in a self-obsessed manner. This learning algorithm will present the computer to look at the internal and external environment in series of independent entities, which will interact with each other, with and/or without knowledge of the computer's brain. When a learning algorithm interacts, it does so by detecting and understanding the entities in the human algorithm. However, the problem with this approach is that the algorithm does not consider the interaction of the third party or unknown entities, which may be interacting with each other. These unknown entities in their interaction with the non-computer entities make an effect in the environment that influences the information and the behaviour of the computer brain. Such details and the ability to process the dynamic and unsettling nature of these interactions are absent in the current learning algorithm such as the decision tree learning algorithm. IBSEAD is able to evaluate and consider such algorithms and thus give us a better accuracy in simulation of the highly evolved nature of the human brain. Processes such as dreams, imagination and novelty, that exist in humans are not fully simulated by the existing learning algorithms. Also, Hidden Markov models (HMM) are useful in finding \"hidden\" entities, which may be known or unknown. However, this model fails to consider the case of unknown entities which maybe unclear or unknown. IBSEAD is better because it considers three types of entities- known, unknown and invisible. We present our case with a comparison of existing algorithms in known environments and cases and present the results of the experiments using dry run of the simulated runs of the existing machine learning algorithms versus IBSEAD.", "source": "arxiv/ml"}
{"id": "arxiv:967", "title": "A Note on Improved Loss Bounds for Multiple Kernel Learning", "text": "In this paper, we correct an upper bound, presented in~\\cite{hs-11}, on the generalisation error of classifiers learned through multiple kernel learning. The bound in~\\cite{hs-11} uses Rademacher complexity and has an\\emph{additive} dependence on the logarithm of the number of kernels and the margin achieved by the classifier. However, there are some errors in parts of the proof which are corrected in this paper. Unfortunately, the final result turns out to be a risk bound which has a \\emph{multiplicative} dependence on the logarithm of the number of kernels and the margin achieved by the classifier.", "source": "arxiv/ml"}
{"id": "arxiv:968", "title": "Abstraction Super-structuring Normal Forms: Towards a Theory of Structural Induction", "text": "Induction is the process by which we obtain predictive laws or theories or models of the world. We consider the structural aspect of induction. We answer the question as to whether we can find a finite and minmalistic set of operations on structural elements in terms of which any theory can be expressed. We identify abstraction (grouping similar entities) and super-structuring (combining topologically e.g., spatio-temporally close entities) as the essential structural operations in the induction process. We show that only two more structural operations, namely, reverse abstraction and reverse super-structuring (the duals of abstraction and super-structuring respectively) suffice in order to exploit the full power of Turing-equivalent generative grammars in induction. We explore the implications of this theorem with respect to the nature of hidden variables, radical positivism and the 2-century old claim of David Hume about the principles of connexion among ideas.", "source": "arxiv/ml"}
{"id": "arxiv:969", "title": "\"Memory foam\" approach to unsupervised learning", "text": "We propose an alternative approach to construct an artificial learning system, which naturally learns in an unsupervised manner. Its mathematical prototype is a dynamical system, which automatically shapes its vector field in response to the input signal. The vector field converges to a gradient of a multi-dimensional probability density distribution of the input process, taken with negative sign. The most probable patterns are represented by the stable fixed points, whose basins of attraction are formed automatically. The performance of this system is illustrated with musical signals.", "source": "arxiv/ml"}
{"id": "arxiv:970", "title": "Distributed Matrix Completion and Robust Factorization", "text": "If learning methods are to scale to the massive sizes of modern datasets, it is essential for the field of machine learning to embrace parallel and distributed computing. Inspired by the recent development of matrix factorization methods with rich theory but poor computational complexity and by the relative ease of mapping matrices onto distributed architectures, we introduce a scalable divide-and-conquer framework for noisy matrix factorization. We present a thorough theoretical analysis of this framework in which we characterize the statistical errors introduced by the \"divide\" step and control their magnitude in the \"conquer\" step, so that the overall algorithm enjoys high-probability estimation guarantees comparable to those of its base algorithm. We also present experiments in collaborative filtering and video background modeling that demonstrate the near-linear to superlinear speed-ups attainable with this approach.", "source": "arxiv/ml"}
{"id": "arxiv:971", "title": "GraphLab: A Distributed Framework for Machine Learning in the Cloud", "text": "Machine Learning (ML) techniques are indispensable in a wide range of fields. Unfortunately, the exponential increase of dataset sizes are rapidly extending the runtime of sequential algorithms and threatening to slow future progress in ML. With the promise of affordable large-scale parallel computing, Cloud systems offer a viable platform to resolve the computational challenges in ML. However, designing and implementing efficient, provably correct distributed ML algorithms is often prohibitively challenging. To enable ML researchers to easily and efficiently use parallel systems, we introduced the GraphLab abstraction which is designed to represent the computational patterns in ML algorithms while permitting efficient parallel and distributed implementations. In this paper we provide a formal description of the GraphLab parallel abstraction and present an efficient distributed implementation. We conduct a comprehensive evaluation of GraphLab on three state-of-the-art ML algorithms using real large-scale data and a 64 node EC2 cluster of 512 processors. We find that GraphLab achieves orders of magnitude performance gains over Hadoop while performing comparably or superior to hand-tuned MPI implementations.", "source": "arxiv/ml"}
{"id": "arxiv:972", "title": "High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion", "text": "We consider the problem of high-dimensional Gaussian graphical model selection. We identify a set of graphs for which an efficient estimation algorithm exists, and this algorithm is based on thresholding of empirical conditional covariances. Under a set of transparent conditions, we establish structural consistency (or sparsistency) for the proposed algorithm, when the number of samples n=omega(J_{min}^{-2} log p), where p is the number of variables and J_{min} is the minimum (absolute) edge potential of the graphical model. The sufficient conditions for sparsistency are based on the notion of walk-summability of the model and the presence of sparse local vertex separators in the underlying graph. We also derive novel non-asymptotic necessary conditions on the number of samples required for sparsistency.", "source": "arxiv/ml"}
{"id": "arxiv:973", "title": "Spectral Methods for Learning Multivariate Latent Tree Structure", "text": "This work considers the problem of learning the structure of multivariate linear tree models, which include a variety of directed tree graphical models with continuous, discrete, and mixed latent variables such as linear-Gaussian models, hidden Markov models, Gaussian mixture models, and Markov evolutionary trees. The setting is one where we only have samples from certain observed variables in the tree, and our goal is to estimate the tree structure (i.e., the graph of how the underlying hidden variables are connected to each other and to the observed variables). We propose the Spectral Recursive Grouping algorithm, an efficient and simple bottom-up procedure for recovering the tree structure from independent samples of the observed variables. Our finite sample size bounds for exact recovery of the tree structure reveal certain natural dependencies on underlying statistical and structural properties of the underlying joint distribution. Furthermore, our sample complexity guarantees have no explicit dependence on the dimensionality of the observed variables, making the algorithm applicable to many high-dimensional settings. At the heart of our algorithm is a spectral quartet test for determining the relative topology of a quartet of variables from second-order statistics.", "source": "arxiv/ml"}
{"id": "arxiv:974", "title": "Text Classification: A Sequential Reading Approach", "text": "We propose to model the text classification process as a sequential decision process. In this process, an agent learns to classify documents into topics while reading the document sentences sequentially and learns to stop as soon as enough information was read for deciding. The proposed algorithm is based on a modelisation of Text Classification as a Markov Decision Process and learns by using Reinforcement Learning. Experiments on four different classical mono-label corpora show that the proposed approach performs comparably to classical SVM approaches for large training sets, and better for small training sets. In addition, the model automatically adapts its reading process to the quantity of training information provided.", "source": "arxiv/ml"}
{"id": "arxiv:975", "title": "On the Furthest Hyperplane Problem and Maximal Margin Clustering", "text": "This paper introduces the Furthest Hyperplane Problem (FHP), which is an unsupervised counterpart of Support Vector Machines. Given a set of n points in Rd, the objective is to produce the hyperplane (passing through the origin) which maximizes the separation margin, that is, the minimal distance between the hyperplane and any input point. To the best of our knowledge, this is the first paper achieving provable results regarding FHP. We provide both lower and upper bounds to this NP-hard problem. First, we give a simple randomized algorithm whose running time is n^O(1/{\\theta}^2) where {\\theta} is the optimal separation margin. We show that its exponential dependency on 1/{\\theta}^2 is tight, up to sub-polynomial factors, assuming SAT cannot be solved in sub-exponential time. Next, we give an efficient approxima- tion algorithm. For any {\\alpha} \\in [0, 1], the algorithm produces a hyperplane whose distance from at least 1 - 5{\\alpha} fraction of the points is at least {\\alpha} times the optimal separation margin. Finally, we show that FHP does not admit a PTAS by presenting a gap preserving reduction from a particular version of the PCP theorem.", "source": "arxiv/ml"}
{"id": "arxiv:976", "title": "Polyceptron: A Polyhedral Learning Algorithm", "text": "In this paper we propose a new algorithm for learning polyhedral classifiers which we call as Polyceptron. It is a Perception like algorithm which updates the parameters only when the current classifier misclassifies any training data. We give both batch and online version of Polyceptron algorithm. Finally we give experimental results to show the effectiveness of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:977", "title": "High-dimensional structure estimation in Ising models: Local separation criterion", "text": "We consider the problem of high-dimensional Ising (graphical) model selection. We propose a simple algorithm for structure estimation based on the thresholding of the empirical conditional variation distances. We introduce a novel criterion for tractable graph families, where this method is efficient, based on the presence of sparse local separators between node pairs in the underlying graph. For such graphs, the proposed algorithm has a sample complexity of $n=\\Omega(J_{\\min}^{-2}\\log p)$, where $p$ is the number of variables, and $J_{\\min}$ is the minimum (absolute) edge potential in the model. We also establish nonasymptotic necessary and sufficient conditions for structure estimation.", "source": "arxiv/ml"}
{"id": "arxiv:978", "title": "Stochastic convex optimization with bandit feedback", "text": "This paper addresses the problem of minimizing a convex, Lipschitz function $f$ over a convex, compact set $\\xset$ under a stochastic bandit feedback model. In this model, the algorithm is allowed to observe noisy realizations of the function value $f(x)$ at any query point $x \\in \\xset$. The quantity of interest is the regret of the algorithm, which is the sum of the function values at algorithm's query points minus the optimal function value. We demonstrate a generalization of the ellipsoid algorithm that incurs $\\otil(\\poly(d)\\sqrt{T})$ regret. Since any algorithm has regret at least $\\Omega(\\sqrt{T})$ on this problem, our algorithm is optimal in terms of the scaling with $T$.", "source": "arxiv/ml"}
{"id": "arxiv:979", "title": "Multi-Instance Learning with Any Hypothesis Class", "text": "In the supervised learning setting termed Multiple-Instance Learning (MIL), the examples are bags of instances, and the bag label is a function of the labels of its instances. Typically, this function is the Boolean OR. The learner observes a sample of bags and the bag labels, but not the instance labels that determine the bag labels. The learner is then required to emit a classification rule for bags based on the sample. MIL has numerous applications, and many heuristic algorithms have been used successfully on this problem, each adapted to specific settings or applications. In this work we provide a unified theoretical analysis for MIL, which holds for any underlying hypothesis class, regardless of a specific application or problem domain. We show that the sample complexity of MIL is only poly-logarithmically dependent on the size of the bag, for any underlying hypothesis class. In addition, we introduce a new PAC-learning algorithm for MIL, which uses a regular supervised learning algorithm as an oracle. We prove that efficient PAC-learning for MIL can be generated from any efficient non-MIL supervised learning algorithm that handles one-sided error. The computational complexity of the resulting algorithm is only polynomially dependent on the bag size.", "source": "arxiv/ml"}
{"id": "arxiv:980", "title": "Data Stability in Clustering: A Closer Look", "text": "We consider the model introduced by Bilu and Linial (2010), who study problems for which the optimal clustering does not change when distances are perturbed. They show that even when a problem is NP-hard, it is sometimes possible to obtain efficient algorithms for instances resilient to certain multiplicative perturbations, e.g. on the order of $O(\\sqrt{n})$ for max-cut clustering. Awasthi et al. (2010) consider center-based objectives, and Balcan and Liang (2011) analyze the $k$-median and min-sum objectives, giving efficient algorithms for instances resilient to certain constant multiplicative perturbations. Here, we are motivated by the question of to what extent these assumptions can be relaxed while allowing for efficient algorithms. We show there is little room to improve these results by giving NP-hardness lower bounds for both the $k$-median and min-sum objectives. On the other hand, we show that constant multiplicative resilience parameters can be so strong as to make the clustering problem trivial, leaving only a narrow range of resilience parameters for which clustering is interesting. We also consider a model of additive perturbations and give a correspondence between additive and multiplicative notions of stability. Our results provide a close examination of the consequences of assuming stability in data.", "source": "arxiv/ml"}
{"id": "arxiv:981", "title": "Private Data Release via Learning Thresholds", "text": "This work considers computationally efficient privacy-preserving data release. We study the task of analyzing a database containing sensitive information about individual participants. Given a set of statistical queries on the data, we want to release approximate answers to the queries while also guaranteeing differential privacy---protecting each participant's sensitive data. Our focus is on computationally efficient data release algorithms; we seek algorithms whose running time is polynomial, or at least sub-exponential, in the data dimensionality. Our primary contribution is a computationally efficient reduction from differentially private data release for a class of counting queries, to learning thresholded sums of predicates from a related class. We instantiate this general reduction with a variety of algorithms for learning thresholds. These instantiations yield several new results for differentially private data release. As two examples, taking {0,1}^d to be the data domain (of dimension d), we obtain differentially private algorithms for: (*) Releasing all k-way conjunctions. For any given k, the resulting data release algorithm has bounded error as long as the database is of size at least d^{O(\\sqrt{k\\log(k\\log d)})}. The running time is polynomial in the database size. (*) Releasing a (1-\\gamma)-fraction of all parity queries. For any \\gamma \\geq \\poly(1/d), the algorithm has bounded error as long as the database is of size at least \\poly(d). The running time is polynomial in the database size. Several other instantiations yield further results for privacy-preserving data release. Of the two results highlighted above, the first learning algorithm uses techniques for representing thresholded sums of predicates as low-degree polynomial threshold functions. The second learning algorithm is based on Jackson's Harmonic Sieve algorithm [Jackson 1997].", "source": "arxiv/ml"}
{"id": "arxiv:982", "title": "Statistical Topic Models for Multi-Label Document Classification", "text": "Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word tokens with different labels. We investigate the advantages of this approach relative to discriminative models, particularly with respect to classification problems involving large numbers of relatively rare labels. We compare the performance of generative and discriminative approaches on document labeling tasks ranging from datasets with several thousand labels to datasets with tens of labels. The experimental results indicate that probabilistic generative models can achieve competitive multi-label classification performance compared to discriminative methods, and have advantages for datasets with many labels and skewed label frequencies.", "source": "arxiv/ml"}
{"id": "arxiv:983", "title": "Provably Safe and Robust Learning-Based Model Predictive Control", "text": "Controller design faces a trade-off between robustness and performance, and the reliability of linear controllers has caused many practitioners to focus on the former. However, there is renewed interest in improving system performance to deal with growing energy constraints. This paper describes a learning-based model predictive control (LBMPC) scheme that provides deterministic guarantees on robustness, while statistical identification tools are used to identify richer models of the system in order to improve performance; the benefits of this framework are that it handles state and input constraints, optimizes system performance with respect to a cost function, and can be designed to use a wide variety of parametric or nonparametric statistical tools. The main insight of LBMPC is that safety and performance can be decoupled under reasonable conditions in an optimization framework by maintaining two models of the system. The first is an approximate model with bounds on its uncertainty, and the second model is updated by statistical methods. LBMPC improves performance by choosing inputs that minimize a cost subject to the learned dynamics, and it ensures safety and robustness by checking whether these same inputs keep the approximate model stable when it is subject to uncertainty. Furthermore, we show that if the system is sufficiently excited, then the LBMPC control action probabilistically converges to that of an MPC computed using the true dynamics.", "source": "arxiv/ml"}
{"id": "arxiv:984", "title": "Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent", "text": "For large scale learning problems, it is desirable if we can obtain the optimal model parameters by going through the data in only one pass. Polyak and Juditsky (1992) showed that asymptotically the test performance of the simple average of the parameters obtained by stochastic gradient descent (SGD) is as good as that of the parameters which minimize the empirical cost. However, to our knowledge, despite its optimal asymptotic convergence rate, averaged SGD (ASGD) received little attention in recent research on large scale learning. One possible reason is that it may take a prohibitively large number of training samples for ASGD to reach its asymptotic region for most real problems. In this paper, we present a finite sample analysis for the method of Polyak and Juditsky (1992). Our analysis shows that it indeed usually takes a huge number of samples for ASGD to reach its asymptotic region for improperly chosen learning rate. More importantly, based on our analysis, we propose a simple way to properly set learning rate so that it takes a reasonable amount of data for ASGD to reach its asymptotic region. We compare ASGD using our proposed learning rate with other well known algorithms for training large scale linear classifiers. The experiments clearly show the superiority of ASGD.", "source": "arxiv/ml"}
{"id": "arxiv:985", "title": "Learning $k$-Modal Distributions via Testing", "text": "A $k$-modal probability distribution over the discrete domain $\\{1,...,n\\}$ is one whose histogram has at most $k$ \"peaks\" and \"valleys.\" Such distributions are natural generalizations of monotone ($k=0$) and unimodal ($k=1$) probability distributions, which have been intensively studied in probability theory and statistics. In this paper we consider the problem of \\emph{learning} (i.e., performing density estimation of) an unknown $k$-modal distribution with respect to the $L_1$ distance. The learning algorithm is given access to independent samples drawn from an unknown $k$-modal distribution $p$, and it must output a hypothesis distribution $\\widehat{p}$ such that with high probability the total variation distance between $p$ and $\\widehat{p}$ is at most $\\epsilon.$ Our main goal is to obtain \\emph{computationally efficient} algorithms for this problem that use (close to) an information-theoretically optimal number of samples. We give an efficient algorithm for this problem that runs in time $\\mathrm{poly}(k,\\log(n),1/\\epsilon)$. For $k \\leq \\tilde{O}(\\log n)$, the number of samples used by our algorithm is very close (within an $\\tilde{O}(\\log(1/\\epsilon))$ factor) to being information-theoretically optimal. Prior to this work computationally efficient algorithms were known only for the cases $k=0,1$ \\cite{Birge:87b,Birge:97}. A novel feature of our approach is that our learning algorithm crucially uses a new algorithm for \\emph{property testing of probability distributions} as a key subroutine. The learning algorithm uses the property tester to efficiently decompose the $k$-modal distribution into $k$ (near-)monotone distributions, which are easier to learn.", "source": "arxiv/ml"}
{"id": "arxiv:986", "title": "Learning Poisson Binomial Distributions", "text": "We consider a basic problem in unsupervised learning: learning an unknown \\emph{Poisson Binomial Distribution}. A Poisson Binomial Distribution (PBD) over $\\{0,1,\\dots,n\\}$ is the distribution of a sum of $n$ independent Bernoulli random variables which may have arbitrary, potentially non-equal, expectations. These distributions were first studied by S. Poisson in 1837 \\cite{Poisson:37} and are a natural $n$-parameter generalization of the familiar Binomial Distribution. Surprisingly, prior to our work this basic learning problem was poorly understood, and known results for it were far from optimal. We essentially settle the complexity of the learning problem for this basic class of distributions. As our first main result we give a highly efficient algorithm which learns to $\\eps$-accuracy (with respect to the total variation distance) using $\\tilde{O}(1/\\eps^3)$ samples \\emph{independent of $n$}. The running time of the algorithm is \\emph{quasilinear} in the size of its input data, i.e., $\\tilde{O}(\\log(n)/\\eps^3)$ bit-operations. (Observe that each draw from the distribution is a $\\log(n)$-bit string.) Our second main result is a {\\em proper} learning algorithm that learns to $\\eps$-accuracy using $\\tilde{O}(1/\\eps^2)$ samples, and runs in time $(1/\\eps)^{\\poly (\\log (1/\\eps))} \\cdot \\log n$. This is nearly optimal, since any algorithm {for this problem} must use $\\Omega(1/\\eps^2)$ samples. We also give positive and negative results for some extensions of this learning problem to weighted sums of independent Bernoulli random variables.", "source": "arxiv/ml"}
{"id": "arxiv:987", "title": "Modelling Distributed Shape Priors by Gibbs Random Fields of Second Order", "text": "We analyse the potential of Gibbs Random Fields for shape prior modelling. We show that the expressive power of second order GRFs is already sufficient to express simple shapes and spatial relations between them simultaneously. This allows to model and recognise complex shapes as spatial compositions of simpler parts.", "source": "arxiv/ml"}
{"id": "arxiv:988", "title": "From Small-World Networks to Comparison-Based Search", "text": "The problem of content search through comparisons has recently received considerable attention. In short, a user searching for a target object navigates through a database in the following manner: the user is asked to select the object most similar to her target from a small list of objects. A new object list is then presented to the user based on her earlier selection. This process is repeated until the target is included in the list presented, at which point the search terminates. This problem is known to be strongly related to the small-world network design problem. However, contrary to prior work, which focuses on cases where objects in the database are equally popular, we consider here the case where the demand for objects may be heterogeneous. We show that, under heterogeneous demand, the small-world network design problem is NP-hard. Given the above negative result, we propose a novel mechanism for small-world design and provide an upper bound on its performance under heterogeneous demand. The above mechanism has a natural equivalent in the context of content search through comparisons, and we establish both an upper bound and a lower bound for the performance of this mechanism. These bounds are intuitively appealing, as they depend on the entropy of the demand as well as its doubling constant, a quantity capturing the topology of the set of target objects. They also illustrate interesting connections between comparison-based search to classic results from information theory. Finally, we propose an adaptive learning algorithm for content search that meets the performance guarantees achieved by the above mechanisms.", "source": "arxiv/ml"}
{"id": "arxiv:989", "title": "On the Computational Complexity of Stochastic Controller Optimization in POMDPs", "text": "We show that the problem of finding an optimal stochastic 'blind' controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard, in PSPACE, and SQRT-SUM-hard, hence placing it in NP would imply breakthroughs in long-standing open problems in computer science. Our result establishes that the more general problem of stochastic controller optimization in POMDPs is also NP-hard. Nonetheless, we outline a special case that is convex and admits efficient global solutions.", "source": "arxiv/ml"}
{"id": "arxiv:990", "title": "Robust Kernel Density Estimation", "text": "We propose a method for nonparametric density estimation that exhibits robustness to contamination of the training sample. This method achieves robustness by combining a traditional kernel density estimator (KDE) with ideas from classical $M$-estimation. We interpret the KDE based on a radial, positive semi-definite kernel as a sample mean in the associated reproducing kernel Hilbert space. Since the sample mean is sensitive to outliers, we estimate it robustly via $M$-estimation, yielding a robust kernel density estimator (RKDE). An RKDE can be computed efficiently via a kernelized iteratively re-weighted least squares (IRWLS) algorithm. Necessary and sufficient conditions are given for kernelized IRWLS to converge to the global minimizer of the $M$-estimator objective function. The robustness of the RKDE is demonstrated with a representer theorem, the influence function, and experimental results for density estimation and anomaly detection.", "source": "arxiv/ml"}
{"id": "arxiv:991", "title": "On Learning Discrete Graphical Models Using Greedy Methods", "text": "In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsistency, or consistency in sparsity pattern recovery, properties of a forward-backward greedy algorithm as applied to general statistical models. As a special case, we then apply this algorithm to learn the structure of a discrete graphical model via neighborhood estimation. As a corollary of our general result, we derive sufficient conditions on the number of samples n, the maximum node-degree d and the problem size p, as well as other conditions on the model parameters, so that the algorithm recovers all the edges with high probability. Our result guarantees graph selection for samples scaling as n = Omega(d^2 log(p)), in contrast to existing convex-optimization based algorithms that require a sample complexity of \\Omega(d^3 log(p)). Further, the greedy algorithm only requires a restricted strong convexity condition which is typically milder than irrepresentability assumptions. We corroborate these results using numerical simulations at the end.", "source": "arxiv/ml"}
{"id": "arxiv:992", "title": "Discovering Knowledge using a Constraint-based Language", "text": "Discovering pattern sets or global patterns is an attractive issue from the pattern mining community in order to provide useful information. By combining local patterns satisfying a joint meaning, this approach produces patterns of higher level and thus more useful for the data analyst than the usual local patterns, while reducing the number of patterns. In parallel, recent works investigating relationships between data mining and constraint programming (CP) show that the CP paradigm is a nice framework to model and mine such patterns in a declarative and generic way. We present a constraint-based language which enables us to define queries addressing patterns sets and global patterns. The usefulness of such a declarative approach is highlighted by several examples coming from the clustering based on associations. This language has been implemented in the CP framework.", "source": "arxiv/ml"}
{"id": "arxiv:993", "title": "Unsupervised K-Nearest Neighbor Regression", "text": "In many scientific disciplines structures in high-dimensional data have to be found, e.g., in stellar spectra, in genome data, or in face recognition tasks. In this work we present a novel approach to non-linear dimensionality reduction. It is based on fitting K-nearest neighbor regression to the unsupervised regression framework for learning of low-dimensional manifolds. Similar to related approaches that are mostly based on kernel methods, unsupervised K-nearest neighbor (UNN) regression optimizes latent variables w.r.t. the data space reconstruction error employing the K-nearest neighbor heuristic. The problem of optimizing latent neighborhoods is difficult to solve, but the UNN formulation allows the design of efficient strategies that iteratively embed latent points to fixed neighborhood topologies. UNN is well appropriate for sorting of high-dimensional data. The iterative variants are analyzed experimentally.", "source": "arxiv/ml"}
{"id": "arxiv:994", "title": "Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs", "text": "We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled independently of the background. We present a learning scheme that learns this representation directly from cluttered images with only very weak supervision. The model generates plausible samples and performs foreground-background segmentation. We demonstrate that representing foreground objects independently of the background can be beneficial in recognition tasks.", "source": "arxiv/ml"}
{"id": "arxiv:995", "title": "Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems", "text": "In this paper we consider the problem of learning the optimal policy for uncontrolled restless bandit problems. In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields a positive reward. There is a player who sequentially selects one of the arms at each time step. The goal of the player is to maximize its undiscounted reward over a time horizon T. The reward process of each arm is a finite state Markov chain, whose transition probabilities are unknown by the player. State transitions of each arm is independent of the selection of the player. We propose a learning algorithm with logarithmic regret uniformly over time with respect to the optimal finite horizon policy. Our results extend the optimal adaptive learning of MDPs to POMDPs.", "source": "arxiv/ml"}
{"id": "arxiv:996", "title": "On the Universality of Online Mirror Descent", "text": "We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.", "source": "arxiv/ml"}
{"id": "arxiv:997", "title": "Performance and Convergence of Multi-user Online Learning", "text": "We study the problem of allocating multiple users to a set of wireless channels in a decentralized manner when the channel quali- ties are time-varying and unknown to the users, and accessing the same channel by multiple users leads to reduced quality due to interference. In such a setting the users not only need to learn the inherent channel quality and at the same time the best allocations of users to channels so as to maximize the social welfare. Assuming that the users adopt a certain online learning algorithm, we investigate under what conditions the socially optimal allocation is achievable. In particular we examine the effect of different levels of knowledge the users may have and the amount of communications and cooperation. The general conclusion is that when the cooperation of users decreases and the uncertainty about channel payoffs increases it becomes harder to achieve the socially opti- mal allocation.", "source": "arxiv/ml"}
{"id": "arxiv:998", "title": "Analogy perception applied to seven tests of word comprehension", "text": "It has been argued that analogy is the core of cognition. In AI research, algorithms for analogy are often limited by the need for hand-coded high-level representations as input. An alternative approach is to use high-level perception, in which high-level representations are automatically generated from raw data. Analogy perception is the process of recognizing analogies using high-level perception. We present PairClass, an algorithm for analogy perception that recognizes lexical proportional analogies using representations that are automatically generated from a large corpus of raw textual data. A proportional analogy is an analogy of the form A:B::C:D, meaning \"A is to B as C is to D\". A lexical proportional analogy is a proportional analogy with words, such as carpenter:wood::mason:stone. PairClass represents the semantic relations between two words using a high-dimensional feature vector, in which the elements are based on frequencies of patterns in the corpus. PairClass recognizes analogies by applying standard supervised machine learning techniques to the feature vectors. We show how seven different tests of word comprehension can be framed as problems of analogy perception and we then apply PairClass to the seven resulting sets of analogy perception problems. We achieve competitive results on all seven tests. This is the first time a uniform approach has handled such a range of tests of word comprehension.", "source": "arxiv/ml"}
{"id": "arxiv:999", "title": "The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation", "text": "This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a \"value iteration\" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programming algorithms HDP, DHP and GDHP.", "source": "arxiv/ml"}
{"id": "arxiv:1000", "title": "Lifted Graphical Models: A Survey", "text": "This article presents a survey of work on lifted graphical models. We review a general form for a lifted graphical model, a par-factor graph, and show how a number of existing statistical relational representations map to this formalism. We discuss inference algorithms, including lifted inference algorithms, that efficiently compute the answers to probabilistic queries. We also review work in learning lifted graphical models from data. It is our belief that the need for statistical relational models (whether it goes by that name or another) will grow in the coming decades, as we are inundated with data which is a mix of structured and unstructured, with entities and relations extracted in a noisy manner from text, and with the need to reason effectively with this data. We hope that this synthesis of ideas from many different research groups will provide an accessible starting point for new researchers in this expanding field.", "source": "arxiv/ml"}
{"id": "arxiv:1001", "title": "Normative design using inductive learning", "text": "In this paper we propose a use-case-driven iterative design methodology for normative frameworks, also called virtual institutions, which are used to govern open systems. Our computational model represents the normative framework as a logic program under answer set semantics (ASP). By means of an inductive logic programming approach, implemented using ASP, it is possible to synthesise new rules and revise the existing ones. The learning mechanism is guided by the designer who describes the desired properties of the framework through use cases, comprising (i) event traces that capture possible scenarios, and (ii) a state that describes the desired outcome. The learning process then proposes additional rules, or changes to current rules, to satisfy the constraints expressed in the use cases. Thus, the contribution of this paper is a process for the elaboration and revision of a normative framework by means of a semi-automatic and iterative process driven from specifications of (un)desirable behaviour. The process integrates a novel and general methodology for theory revision based on ASP.", "source": "arxiv/ml"}
{"id": "arxiv:1002", "title": "Submodular Optimization for Efficient Semi-supervised Support Vector Machines", "text": "In this work we present a quadratic programming approximation of the Semi-Supervised Support Vector Machine (S3VM) problem, namely approximate QP-S3VM, that can be efficiently solved using off the shelf optimization packages. We prove that this approximate formulation establishes a relation between the low density separation and the graph-based models of semi-supervised learning (SSL) which is important to develop a unifying framework for semi-supervised learning methods. Furthermore, we propose the novel idea of representing SSL problems as submodular set functions and use efficient submodular optimization algorithms to solve them. Using this new idea we develop a representation of the approximate QP-S3VM as a maximization of a submodular set function which makes it possible to optimize using efficient greedy algorithms. We demonstrate that the proposed methods are accurate and provide significant improvement in time complexity over the state of the art in the literature.", "source": "arxiv/ml"}
{"id": "arxiv:1003", "title": "Multi Layer Analysis", "text": "This thesis presents a new methodology to analyze one-dimensional signals trough a new approach called Multi Layer Analysis, for short MLA. It also provides some new insights on the relationship between one-dimensional signals processed by MLA and tree kernels, test of randomness and signal processing techniques. The MLA approach has a wide range of application to the fields of pattern discovery and matching, computational biology and many other areas of computer science and signal processing. This thesis includes also some applications of this approach to real problems in biology and seismology.", "source": "arxiv/ml"}
{"id": "arxiv:1004", "title": "Axioms for Rational Reinforcement Learning", "text": "We provide a formal, simple and intuitive theory of rational decision making including sequential decisions that affect the environment. The theory has a geometric flavor, which makes the arguments easy to visualize and understand. Our theory is for complete decision makers, which means that they have a complete set of preferences. Our main result shows that a complete rational decision maker implicitly has a probabilistic model of the environment. We have a countable version of this result that brings light on the issue of countable vs finite additivity by showing how it depends on the geometry of the space which we have preferences over. This is achieved through fruitfully connecting rationality with the Hahn-Banach Theorem. The theory presented here can be viewed as a formalization and extension of the betting odds approach to probability of Ramsey and De Finetti.", "source": "arxiv/ml"}
{"id": "arxiv:1005", "title": "Universal Prediction of Selected Bits", "text": "Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the target data given input data and previous input/target pairs. Solomonoff induction is known to solve the general sequence prediction problem, but only if the entire sequence is sampled from a computable distribution. In the case of classification and discriminative learning though, only the targets need be structured (given the inputs). We show that the normalised version of Solomonoff induction can still be used in this case, and more generally that it can detect any recursive sub-pattern (regularity) within an otherwise completely unstructured sequence. It is also shown that the unnormalised version can fail to predict very simple recursive sub-patterns.", "source": "arxiv/ml"}
{"id": "arxiv:1006", "title": "Asymptotically Optimal Agents", "text": "Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.", "source": "arxiv/ml"}
{"id": "arxiv:1007", "title": "Automatic Network Reconstruction using ASP", "text": "Building biological models by inferring functional dependencies from experimental data is an im- portant issue in Molecular Biology. To relieve the biologist from this traditionally manual process, various approaches have been proposed to increase the degree of automation. However, available ap- proaches often yield a single model only, rely on specific assumptions, and/or use dedicated, heuris- tic algorithms that are intolerant to changing circumstances or requirements in the view of the rapid progress made in Biotechnology. Our aim is to provide a declarative solution to the problem by ap- peal to Answer Set Programming (ASP) overcoming these difficulties. We build upon an existing approach to Automatic Network Reconstruction proposed by part of the authors. This approach has firm mathematical foundations and is well suited for ASP due to its combinatorial flavor providing a characterization of all models explaining a set of experiments. The usage of ASP has several ben- efits over the existing heuristic algorithms. First, it is declarative and thus transparent for biological experts. Second, it is elaboration tolerant and thus allows for an easy exploration and incorporation of biological constraints. Third, it allows for exploring the entire space of possible models. Finally, our approach offers an excellent performance, matching existing, special-purpose systems.", "source": "arxiv/ml"}
{"id": "arxiv:1008", "title": "Generating a Diverse Set of High-Quality Clusterings", "text": "We provide a new framework for generating multiple good quality partitions (clusterings) of a single data set. Our approach decomposes this problem into two components, generating many high-quality partitions, and then grouping these partitions to obtain k representatives. The decomposition makes the approach extremely modular and allows us to optimize various criteria that control the choice of representative partitions.", "source": "arxiv/ml"}
{"id": "arxiv:1009", "title": "CBR with Commonsense Reasoning and Structure Mapping: An Application to Mediation", "text": "Mediation is an important method in dispute resolution. We implement a case based reasoning approach to mediation integrating analogical and commonsense reasoning components that allow an artificial mediation agent to satisfy requirements expected from a human mediator, in particular: utilizing experience with cases in different domains; and structurally transforming the set of issues for a better solution. We utilize a case structure based on ontologies reflecting the perceptions of the parties in dispute. The analogical reasoning component, employing the Structure Mapping Theory from psychology, provides a flexibility to respond innovatively in unusual circumstances, in contrast with conventional approaches confined into specialized problem domains. We aim to build a mediation case base incorporating real world instances ranging from interpersonal or intergroup disputes to international conflicts.", "source": "arxiv/ml"}
{"id": "arxiv:1010", "title": "Optimization with Sparsity-Inducing Penalties", "text": "Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. They were first dedicated to linear variable selection but numerous extensions have now emerged such as structured sparsity or kernel selection. It turns out that many of the related estimation problems can be cast as convex optimization problems by regularizing the empirical risk with appropriate non-smooth norms. The goal of this paper is to present from a general perspective optimization tools and techniques dedicated to such sparsity-inducing penalties. We cover proximal methods, block-coordinate descent, reweighted $\\ell_2$-penalized techniques, working-set and homotopy methods, as well as non-convex formulations and extensions, and provide an extensive set of experiments to compare various algorithms from a computational point of view.", "source": "arxiv/ml"}
{"id": "arxiv:1011", "title": "Accurate Estimators for Improving Minwise Hashing and b-Bit Minwise Hashing", "text": "Minwise hashing is the standard technique in the context of search and databases for efficiently estimating set (e.g., high-dimensional 0/1 vector) similarities. Recently, b-bit minwise hashing was proposed which significantly improves upon the original minwise hashing in practice by storing only the lowest b bits of each hashed value, as opposed to using 64 bits. b-bit hashing is particularly effective in applications which mainly concern sets of high similarities (e.g., the resemblance >0.5). However, there are other important applications in which not just pairs of high similarities matter. For example, many learning algorithms require all pairwise similarities and it is expected that only a small fraction of the pairs are similar. Furthermore, many applications care more about containment (e.g., how much one object is contained by another object) than the resemblance. In this paper, we show that the estimators for minwise hashing and b-bit minwise hashing used in the current practice can be systematically improved and the improvements are most significant for set pairs of low resemblance and high containment.", "source": "arxiv/ml"}
{"id": "arxiv:1012", "title": "A new embedding quality assessment method for manifold learning", "text": "Manifold learning is a hot research topic in the field of computer science. A crucial issue with current manifold learning methods is that they lack a natural quantitative measure to assess the quality of learned embeddings, which greatly limits their applications to real-world problems. In this paper, a new embedding quality assessment method for manifold learning, named as Normalization Independent Embedding Quality Assessment (NIEQA), is proposed. Compared with current assessment methods which are limited to isometric embeddings, the NIEQA method has a much larger application range due to two features. First, it is based on a new measure which can effectively evaluate how well local neighborhood geometry is preserved under normalization, hence it can be applied to both isometric and normalized embeddings. Second, it can provide both local and global evaluations to output an overall assessment. Therefore, NIEQA can serve as a natural tool in model selection and evaluation tasks for manifold learning. Experimental results on benchmark data sets validate the effectiveness of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1013", "title": "Activized Learning: Transforming Passive to Active with Improved Label Complexity", "text": "We study the theoretical advantages of active learning over passive learning. Specifically, we prove that, in noise-free classifier learning for VC classes, any passive learning algorithm can be transformed into an active learning algorithm with asymptotically strictly superior label complexity for all nontrivial target functions and distributions. We further provide a general characterization of the magnitudes of these improvements in terms of a novel generalization of the disagreement coefficient. We also extend these results to active learning in the presence of label noise, and find that even under broad classes of noise distributions, we can typically guarantee strict improvements over the known results for passive learning.", "source": "arxiv/ml"}
{"id": "arxiv:1014", "title": "Uncertain Nearest Neighbor Classification", "text": "This work deals with the problem of classifying uncertain data. With this aim the Uncertain Nearest Neighbor (UNN) rule is here introduced, which represents the generalization of the deterministic nearest neighbor rule to the case in which uncertain objects are available. The UNN rule relies on the concept of nearest neighbor class, rather than on that of nearest neighbor object. The nearest neighbor class of a test object is the class that maximizes the probability of providing its nearest neighbor. It is provided evidence that the former concept is much more powerful than the latter one in the presence of uncertainty, in that it correctly models the right semantics of the nearest neighbor decision rule when applied to the uncertain scenario. An effective and efficient algorithm to perform uncertain nearest neighbor classification of a generic (un)certain test object is designed, based on properties that greatly reduce the temporal cost associated with nearest neighbor class probability computation. Experimental results are presented, showing that the UNN rule is effective and efficient in classifying uncertain data.", "source": "arxiv/ml"}
{"id": "arxiv:1015", "title": "A survey on independence-based Markov networks learning", "text": "This work reports the most relevant technical aspects in the problem of learning the \\emph{Markov network structure} from data. Such problem has become increasingly important in machine learning, and many other application fields of machine learning. Markov networks, together with Bayesian networks, are probabilistic graphical models, a widely used formalism for handling probability distributions in intelligent systems. Learning graphical models from data have been extensively applied for the case of Bayesian networks, but for Markov networks learning it is not tractable in practice. However, this situation is changing with time, given the exponential growth of computers capacity, the plethora of available digital data, and the researching on new learning technologies. This work stresses on a technology called independence-based learning, which allows the learning of the independence structure of those networks from data in an efficient and sound manner, whenever the dataset is sufficiently large, and data is a representative sampling of the target distribution. In the analysis of such technology, this work surveys the current state-of-the-art algorithms for learning Markov networks structure, discussing its current limitations, and proposing a series of open problems where future works may produce some advances in the area in terms of quality and efficiency. The paper concludes by opening a discussion about how to develop a general formalism for improving the quality of the structures learned, when data is scarce.", "source": "arxiv/ml"}
{"id": "arxiv:1016", "title": "Feature Extraction for Change-Point Detection using Stationary Subspace Analysis", "text": "Detecting changes in high-dimensional time series is difficult because it involves the comparison of probability densities that need to be estimated from finite samples. In this paper, we present the first feature extraction method tailored to change point detection, which is based on an extended version of Stationary Subspace Analysis. We reduce the dimensionality of the data to the most non-stationary directions, which are most informative for detecting state changes in the time series. In extensive simulations on synthetic data we show that the accuracy of three change point detection algorithms is significantly increased by a prior feature extraction step. These findings are confirmed in an application to industrial fault monitoring.", "source": "arxiv/ml"}
{"id": "arxiv:1017", "title": "Efficient Multicore Collaborative Filtering", "text": "This paper describes the solution method taken by LeBuSiShu team for track1 in ACM KDD CUP 2011 contest (resulting in the 5th place). We identified two main challenges: the unique item taxonomy characteristics as well as the large data set size.To handle the item taxonomy, we present a novel method called Matrix Factorization Item Taxonomy Regularization (MFITR). MFITR obtained the 2nd best prediction result out of more then ten implemented algorithms. For rapidly computing multiple solutions of various algorithms, we have implemented an open source parallel collaborative filtering library on top of the GraphLab machine learning framework. We report some preliminary performance results obtained using the BlackLight supercomputer.", "source": "arxiv/ml"}
{"id": "arxiv:1018", "title": "Ensemble Risk Modeling Method for Robust Learning on Scarce Data", "text": "In medical risk modeling, typical data are \"scarce\": they have relatively small number of training instances (N), censoring, and high dimensionality (M). We show that the problem may be effectively simplified by reducing it to bipartite ranking, and introduce new bipartite ranking algorithm, Smooth Rank, for robust learning on scarce data. The algorithm is based on ensemble learning with unsupervised aggregation of predictors. The advantage of our approach is confirmed in comparison with two \"gold standard\" risk modeling methods on 10 real life survival analysis datasets, where the new approach has the best results on all but two datasets with the largest ratio N/M. For systematic study of the effects of data scarcity on modeling by all three methods, we conducted two types of computational experiments: on real life data with randomly drawn training sets of different sizes, and on artificial data with increasing number of features. Both experiments demonstrated that Smooth Rank has critical advantage over the popular methods on the scarce data; it does not suffer from overfitting where other methods do.", "source": "arxiv/ml"}
{"id": "arxiv:1019", "title": "Generalised elastic nets", "text": "The elastic net was introduced as a heuristic algorithm for combinatorial optimisation and has been applied, among other problems, to biological modelling. It has an energy function which trades off a fitness term against a tension term. In the original formulation of the algorithm the tension term was implicitly based on a first-order derivative. In this paper we generalise the elastic net model to an arbitrary quadratic tension term, e.g. derived from a discretised differential operator, and give an efficient learning algorithm. We refer to these as generalised elastic nets (GENs). We give a theoretical analysis of the tension term for 1D nets with periodic boundary conditions, and show that the model is sensitive to the choice of finite difference scheme that represents the discretised derivative. We illustrate some of these issues in the context of cortical map models, by relating the choice of tension term to a cortical interaction function. In particular, we prove that this interaction takes the form of a Mexican hat for the original elastic net, and of progressively more oscillatory Mexican hats for higher-order derivatives. The results apply not only to generalised elastic nets but also to other methods using discrete differential penalties, and are expected to be useful in other areas, such as data analysis, computer graphics and optimisation problems.", "source": "arxiv/ml"}
{"id": "arxiv:1020", "title": "Training Logistic Regression and SVM on 200GB Data Using b-Bit Minwise Hashing and Comparisons with Vowpal Wabbit (VW)", "text": "We generated a dataset of 200 GB with 10^9 features, to test our recent b-bit minwise hashing algorithms for training very large-scale logistic regression and SVM. The results confirm our prior work that, compared with the VW hashing algorithm (which has the same variance as random projections), b-bit minwise hashing is substantially more accurate at the same storage. For example, with merely 30 hashed values per data point, b-bit minwise hashing can achieve similar accuracies as VW with 2^14 hashed values per data point. We demonstrate that the preprocessing cost of b-bit minwise hashing is roughly on the same order of magnitude as the data loading time. Furthermore, by using a GPU, the preprocessing cost can be reduced to a small fraction of the data loading time. Minwise hashing has been widely used in industry, at least in the context of search. One reason for its popularity is that one can efficiently simulate permutations by (e.g.,) universal hashing. In other words, there is no need to store the permutation matrix. In this paper, we empirically verify this practice, by demonstrating that even using the simplest 2-universal hashing does not degrade the learning performance.", "source": "arxiv/ml"}
{"id": "arxiv:1021", "title": "Stability Conditions for Online Learnability", "text": "Stability is a general notion that quantifies the sensitivity of a learning algorithm's output to small change in the training dataset (e.g. deletion or replacement of a single training sample). Such conditions have recently been shown to be more powerful to characterize learnability in the general learning setting under i.i.d. samples where uniform convergence is not necessary for learnability, but where stability is both sufficient and necessary for learnability. We here show that similar stability conditions are also sufficient for online learnability, i.e. whether there exists a learning algorithm such that under any sequence of examples (potentially chosen adversarially) produces a sequence of hypotheses that has no regret in the limit with respect to the best hypothesis in hindsight. We introduce online stability, a stability condition related to uniform-leave-one-out stability in the batch setting, that is sufficient for online learnability. In particular we show that popular classes of online learners, namely algorithms that fall in the category of Follow-the-(Regularized)-Leader, Mirror Descent, gradient-based methods and randomized algorithms like Weighted Majority and Hedge, are guaranteed to have no regret if they have such online stability property. We provide examples that suggest the existence of an algorithm with such stability condition might in fact be necessary for online learnability. For the more restricted binary classification setting, we establish that such stability condition is in fact both sufficient and necessary. We also show that for a large class of online learnable problems in the general learning setting, namely those with a notion of sub-exponential covering, no-regret online algorithms that have such stability condition exists.", "source": "arxiv/ml"}
{"id": "arxiv:1022", "title": "A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition", "text": "Multi-step ahead forecasting is still an open challenge in time series forecasting. Several approaches that deal with this complex problem have been proposed in the literature but an extensive comparison on a large number of tasks is still missing. This paper aims to fill this gap by reviewing existing strategies for multi-step ahead forecasting and comparing them in theoretical and practical terms. To attain such an objective, we performed a large scale comparison of these different strategies using a large experimental benchmark (namely the 111 series from the NN5 forecasting competition). In addition, we considered the effects of deseasonalization, input variable selection, and forecast combination on these strategies and on multi-step ahead forecasting at large. The following three findings appear to be consistently supported by the experimental results: Multiple-Output strategies are the best performing approaches, deseasonalization leads to uniformly improved forecast accuracy, and input selection is more effective when performed in conjunction with deseasonalization.", "source": "arxiv/ml"}
{"id": "arxiv:1023", "title": "A Machine Learning Perspective on Predictive Coding with PAQ", "text": "PAQ8 is an open source lossless data compression algorithm that currently achieves the best compression rates on many benchmarks. This report presents a detailed description of PAQ8 from a statistical machine learning perspective. It shows that it is possible to understand some of the modules of PAQ8 and use this understanding to improve the method. However, intuitive statistical explanations of the behavior of other modules remain elusive. We hope the description in this report will be a starting point for discussions that will increase our understanding, lead to improvements to PAQ8, and facilitate a transfer of knowledge from PAQ8 to other machine learning methods, such a recurrent neural networks and stochastic memoizers. Finally, the report presents a broad range of new applications of PAQ to machine learning tasks including language modeling and adaptive text prediction, adaptive game playing, classification, and compression using features from the field of deep learning.", "source": "arxiv/ml"}
{"id": "arxiv:1024", "title": "Overlapping Mixtures of Gaussian Processes for the Data Association Problem", "text": "In this work we introduce a mixture of GPs to address the data association problem, i.e. to label a group of observations according to the sources that generated them. Unlike several previously proposed GP mixtures, the novel mixture has the distinct characteristic of using no gating function to determine the association of samples and mixture components. Instead, all the GPs in the mixture are global and samples are clustered following \"trajectories\" across input space. We use a non-standard variational Bayesian algorithm to efficiently recover sample labels and learn the hyperparameters. We show how multi-object tracking problems can be disambiguated and also explore the characteristics of the model in traditional regression settings.", "source": "arxiv/ml"}
{"id": "arxiv:1025", "title": "Premise Selection for Mathematics by Corpus Analysis and Kernel Methods", "text": "Smart premise selection is essential when using automated reasoning as a tool for large-theory formal proof development. A good method for premise selection in complex mathematical libraries is the application of machine learning to large corpora of proofs. This work develops learning-based premise selection in two ways. First, a newly available minimal dependency analysis of existing high-level formal mathematical proofs is used to build a large knowledge base of proof dependencies, providing precise data for ATP-based re-verification and for training premise selection algorithms. Second, a new machine learning algorithm for premise selection based on kernel methods is proposed and implemented. To evaluate the impact of both techniques, a benchmark consisting of 2078 large-theory mathematical problems is constructed,extending the older MPTP Challenge benchmark. The combined effect of the techniques results in a 50% improvement on the benchmark over the Vampire/SInE state-of-the-art system for automated reasoning in large theories.", "source": "arxiv/ml"}
{"id": "arxiv:1026", "title": "Structured Sparsity and Generalization", "text": "We present a data dependent generalization bound for a large class of regularized algorithms which implement structured sparsity constraints. The bound can be applied to standard squared-norm regularization, the Lasso, the group Lasso, some versions of the group Lasso with overlapping groups, multiple kernel learning and other regularization schemes. In all these cases competitive results are obtained. A novel feature of our bound is that it can be applied in an infinite dimensional setting such as the Lasso in a separable Hilbert space or multiple kernel learning with a countable number of kernels.", "source": "arxiv/ml"}
{"id": "arxiv:1027", "title": "Dynamic Pricing with Limited Supply", "text": "We consider the problem of dynamic pricing with limited supply. A seller has $k$ identical items for sale and is facing $n$ potential buyers (\"agents\") that are arriving sequentially. Each agent is interested in buying one item. Each agent's value for an item is an IID sample from some fixed distribution with support $[0,1]$. The seller offers a take-it-or-leave-it price to each arriving agent (possibly different for different agents), and aims to maximize his expected revenue. We focus on \"prior-independent\" mechanisms -- ones that do not use any information about the distribution. They are desirable because knowing the distribution is unrealistic in many practical scenarios. We study how the revenue of such mechanisms compares to the revenue of the optimal offline mechanism that knows the distribution (\"offline benchmark\"). We present a prior-independent dynamic pricing mechanism whose revenue is at most $O((k \\log n)^{2/3})$ less than the offline benchmark, for every distribution that is regular. In fact, this guarantee holds without *any* assumptions if the benchmark is relaxed to fixed-price mechanisms. Further, we prove a matching lower bound. The performance guarantee for the same mechanism can be improved to $O(\\sqrt{k} \\log n)$, with a distribution-dependent constant, if $k/n$ is sufficiently small. We show that, in the worst case over all demand distributions, this is essentially the best rate that can be obtained with a distribution-specific constant. On a technical level, we exploit the connection to multi-armed bandits (MAB). While dynamic pricing with unlimited supply can easily be seen as an MAB problem, the intuition behind MAB approaches breaks when applied to the setting with limited supply. Our high-level conceptual contribution is that even the limited supply setting can be fruitfully treated as a bandit problem.", "source": "arxiv/ml"}
{"id": "arxiv:1028", "title": "The fuzzy gene filter: A classifier performance assesment", "text": "The Fuzzy Gene Filter (FGF) is an optimised Fuzzy Inference System designed to rank genes in order of differential expression, based on expression data generated in a microarray experiment. This paper examines the effectiveness of the FGF for feature selection using various classification architectures. The FGF is compared to three of the most common gene ranking algorithms: t-test, Wilcoxon test and ROC curve analysis. Four classification schemes are used to compare the performance of the FGF vis-a-vis the standard approaches: K Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and Artificial Neural Network (ANN). A nested stratified Leave-One-Out Cross Validation scheme is used to identify the optimal number top ranking genes, as well as the optimal classifier parameters. Two microarray data sets are used for the comparison: a prostate cancer data set and a lymphoma data set.", "source": "arxiv/ml"}
{"id": "arxiv:1029", "title": "Improving the performance of the ripper in insurance risk classification : A comparitive study using feature selection", "text": "The Ripper algorithm is designed to generate rule sets for large datasets with many features. However, it was shown that the algorithm struggles with classification performance in the presence of missing data. The algorithm struggles to classify instances when the quality of the data deteriorates as a result of increasing missing data. In this paper, a feature selection technique is used to help improve the classification performance of the Ripper model. Principal component analysis and evidence automatic relevance determination techniques are used to improve the performance. A comparison is done to see which technique helps the algorithm improve the most. Training datasets with completely observable data were used to construct the model and testing datasets with missing values were used for measuring accuracy. The results showed that principal component analysis is a better feature selection for the Ripper in improving the classification performance.", "source": "arxiv/ml"}
{"id": "arxiv:1030", "title": "Optimal Algorithms for Ridge and Lasso Regression with Partially Observed Attributes", "text": "We consider the most common variants of linear regression, including Ridge, Lasso and Support-vector regression, in a setting where the learner is allowed to observe only a fixed number of attributes of each example at training time. We present simple and efficient algorithms for these problems: for Lasso and Ridge regression they need the same total number of attributes (up to constants) as do full-information algorithms, for reaching a certain accuracy. For Support-vector regression, we require exponentially less attributes compared to the state of the art. By that, we resolve an open problem recently posed by Cesa-Bianchi et al. (2010). Experiments show the theoretical bounds to be justified by superior performance compared to the state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:1031", "title": "Non-trivial two-armed partial-monitoring games are bandits", "text": "We consider online learning in partial-monitoring games against an oblivious adversary. We show that when the number of actions available to the learner is two and the game is nontrivial then it is reducible to a bandit-like game and thus the minimax regret is $\\Theta(\\sqrt{T})$.", "source": "arxiv/ml"}
{"id": "arxiv:1032", "title": "Prediction of peptide bonding affinity: kernel methods for nonlinear modeling", "text": "This paper presents regression models obtained from a process of blind prediction of peptide binding affinity from provided descriptors for several distinct datasets as part of the 2006 Comparative Evaluation of Prediction Algorithms (COEPRA) contest. This paper finds that kernel partial least squares, a nonlinear partial least squares (PLS) algorithm, outperforms PLS, and that the incorporation of transferable atom equivalent features improves predictive capability.", "source": "arxiv/ml"}
{"id": "arxiv:1033", "title": "Improving Ranking Using Quantum Probability", "text": "The paper shows that ranking information units by quantum probability differs from ranking them by classical probability provided the same data used for parameter estimation. As probability of detection (also known as recall or power) and probability of false alarm (also known as fallout or size) measure the quality of ranking, we point out and show that ranking by quantum probability yields higher probability of detection than ranking by classical probability provided a given probability of false alarm and the same parameter estimation data. As quantum probability provided more effective detectors than classical probability within other domains that data management, we conjecture that, the system that can implement subspace-based detectors shall be more effective than a system which implements a set-based detectors, the effectiveness being calculated as expected recall estimated over the probability of detection and expected fallout estimated over the probability of false alarm.", "source": "arxiv/ml"}
{"id": "arxiv:1034", "title": "Strategic Learning and Robust Protocol Design for Online Communities with Selfish Users", "text": "This paper focuses on analyzing the free-riding behavior of self-interested users in online communities. Hence, traditional optimization methods for communities composed of compliant users such as network utility maximization cannot be applied here. In our prior work, we show how social reciprocation protocols can be designed in online communities which have populations consisting of a continuum of users and are stationary under stochastic permutations. Under these assumptions, we are able to prove that users voluntarily comply with the pre-determined social norms and cooperate with other users in the community by providing their services. In this paper, we generalize the study by analyzing the interactions of self-interested users in online communities with finite populations and are not stationary. To optimize their long-term performance based on their knowledge, users adapt their strategies to play their best response by solving individual stochastic control problems. The best-response dynamic introduces a stochastic dynamic process in the community, in which the strategies of users evolve over time. We then investigate the long-term evolution of a community, and prove that the community will converge to stochastically stable equilibria which are stable against stochastic permutations. Understanding the evolution of a community provides protocol designers with guidelines for designing social norms in which no user has incentives to adapt its strategy and deviate from the prescribed protocol, thereby ensuring that the adopted protocol will enable the community to achieve the optimal social welfare.", "source": "arxiv/ml"}
{"id": "arxiv:1035", "title": "Getting Beyond the State of the Art of Information Retrieval with Quantum Theory", "text": "According to the probability ranking principle, the document set with the highest values of probability of relevance optimizes information retrieval effectiveness given the probabilities are estimated as accurately as possible. The key point of this principle is the separation of the document set into two subsets with a given level of fallout and with the highest recall. If subsets of set measures are replaced by subspaces and space measures, we obtain an alternative theory stemming from Quantum Theory. That theory is named after vector probability because vectors represent event like sets do in classical probability. The paper shows that the separation into vector subspaces is more effective than the separation into subsets with the same available evidence. The result is proved mathematically and verified experimentally. In general, the paper suggests that quantum theory is not only a source of rhetoric inspiration, but is a sufficient condition to improve retrieval effectiveness in a principled way.", "source": "arxiv/ml"}
{"id": "arxiv:1036", "title": "Datum-Wise Classification: A Sequential Approach to Sparsity", "text": "We propose a novel classification technique whose aim is to select an appropriate representation for each datapoint, in contrast to the usual approach of selecting a representation encompassing the whole dataset. This datum-wise representation is found by using a sparsity inducing empirical risk, which is a relaxation of the standard L 0 regularized risk. The classification problem is modeled as a sequential decision process that sequentially chooses, for each datapoint, which features to use before classifying. Datum-Wise Classification extends naturally to multi-class tasks, and we describe a specific case where our inference has equivalent complexity to a traditional linear classifier, while still using a variable number of features. We compare our classifier to classical L 1 regularized linear models (L 1-SVM and LARS) on a set of common binary and multi-class datasets and show that for an equal average number of features used we can get improved performance using our method.", "source": "arxiv/ml"}
{"id": "arxiv:1037", "title": "Probability Ranking in Vector Spaces", "text": "The Probability Ranking Principle states that the document set with the highest values of probability of relevance optimizes information retrieval effectiveness given the probabilities are estimated as accurately as possible. The key point of the principle is the separation of the document set into two subsets with a given level of fallout and with the highest recall. The paper introduces the separation between two vector subspaces and shows that the separation yields a more effective performance than the optimal separation into subsets with the same available evidence, the performance being measured with recall and fallout. The result is proved mathematically and exemplified experimentally.", "source": "arxiv/ml"}
{"id": "arxiv:1038", "title": "No Internal Regret via Neighborhood Watch", "text": "We present an algorithm which attains O(\\sqrt{T}) internal (and thus external) regret for finite games with partial monitoring under the local observability condition. Recently, this condition has been shown by (Bartok, Pal, and Szepesvari, 2011) to imply the O(\\sqrt{T}) rate for partial monitoring games against an i.i.d. opponent, and the authors conjectured that the same holds for non-stochastic adversaries. Our result is in the affirmative, and it completes the characterization of possible rates for finite partial-monitoring games, an open question stated by (Cesa-Bianchi, Lugosi, and Stoltz, 2006). Our regret guarantees also hold for the more general model of partial monitoring with random signals.", "source": "arxiv/ml"}
{"id": "arxiv:1039", "title": "Transfer from Multiple MDPs", "text": "Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include them into the training set used to solve a given target task. In this paper, we investigate the theoretical properties of this transfer method and we introduce novel algorithms adapting the transfer process on the basis of the similarity between source and target tasks. Finally, we report illustrative experimental results in a continuous chain problem.", "source": "arxiv/ml"}
{"id": "arxiv:1040", "title": "Infinite Tucker Decomposition: Nonparametric Bayesian Models for Multiway Data Analysis", "text": "Tensor decomposition is a powerful computational tool for multiway data analysis. Many popular tensor decomposition approaches---such as the Tucker decomposition and CANDECOMP/PARAFAC (CP)---amount to multi-linear factorization. They are insufficient to model (i) complex interactions between data entities, (ii) various data types (e.g. missing data and binary data), and (iii) noisy observations and outliers. To address these issues, we propose tensor-variate latent nonparametric Bayesian models, coupled with efficient inference methods, for multiway data analysis. We name these models InfTucker. Using these InfTucker, we conduct Tucker decomposition in an infinite feature space. Unlike classical tensor decomposition models, our new approaches handle both continuous and binary data in a probabilistic framework. Unlike previous Bayesian models on matrices and tensors, our models are based on latent Gaussian or $t$ processes with nonlinear covariance functions. To efficiently learn the InfTucker from data, we develop a variational inference technique on tensors. Compared with classical implementation, the new technique reduces both time and space complexities by several orders of magnitude. Our experimental results on chemometrics and social network datasets demonstrate that our new models achieved significantly higher prediction accuracy than the most state-of-art tensor decomposition", "source": "arxiv/ml"}
{"id": "arxiv:1041", "title": "Local Component Analysis", "text": "Kernel density estimation, a.k.a. Parzen windows, is a popular density estimation method, which can be used for outlier detection or clustering. With multivariate data, its performance is heavily reliant on the metric used within the kernel. Most earlier work has focused on learning only the bandwidth of the kernel (i.e., a scalar multiplicative factor). In this paper, we propose to learn a full Euclidean metric through an expectation-minimization (EM) procedure, which can be seen as an unsupervised counterpart to neighbourhood component analysis (NCA). In order to avoid overfitting with a fully nonparametric density estimator in high dimensions, we also consider a semi-parametric Gaussian-Parzen density model, where some of the variables are modelled through a jointly Gaussian density, while others are modelled through Parzen windows. For these two models, EM leads to simple closed-form updates based on matrix inversions and eigenvalue decompositions. We show empirically that our method leads to density estimators with higher test-likelihoods than natural competing methods, and that the metrics may be used within most unsupervised learning techniques that rely on such metrics, such as spectral clustering or manifold learning methods. Finally, we present a stochastic approximation scheme which allows for the use of this method in a large-scale setting.", "source": "arxiv/ml"}
{"id": "arxiv:1042", "title": "Differentially Private Online Learning", "text": "In this paper, we consider the problem of preserving privacy in the online learning setting. We study the problem in the online convex programming (OCP) framework---a popular online learning setting with several interesting theoretical and practical implications---while using differential privacy as the formal privacy measure. For this problem, we distill two critical attributes that a private OCP algorithm should have in order to provide reasonable privacy as well as utility guarantees: 1) linearly decreasing sensitivity, i.e., as new data points arrive their effect on the learning model decreases, 2) sub-linear regret bound---regret bound is a popular goodness/utility measure of an online learning algorithm. Given an OCP algorithm that satisfies these two conditions, we provide a general framework to convert the given algorithm into a privacy preserving OCP algorithm with good (sub-linear) regret. We then illustrate our approach by converting two popular online learning algorithms into their differentially private variants while guaranteeing sub-linear regret ($O(\\sqrt{T})$). Next, we consider the special case of online linear regression problems, a practically important class of online learning problems, for which we generalize an approach by Dwork et al. to provide a differentially private algorithm with just $O(\\log^{1.5} T)$ regret. Finally, we show that our online learning framework can be used to provide differentially private algorithms for offline learning as well. For the offline learning problem, our approach obtains better error bounds as well as can handle larger class of problems than the existing state-of-the-art methods Chaudhuri et al.", "source": "arxiv/ml"}
{"id": "arxiv:1043", "title": "Quantum adiabatic machine learning", "text": "We develop an approach to machine learning and anomaly detection via quantum adiabatic evolution. In the training phase we identify an optimal set of weak classifiers, to form a single strong classifier. In the testing phase we adiabatically evolve one or more strong classifiers on a superposition of inputs in order to find certain anomalous elements in the classification space. Both the training and testing phases are executed via quantum adiabatic evolution. We apply and illustrate this approach in detail to the problem of software verification and validation.", "source": "arxiv/ml"}
{"id": "arxiv:1044", "title": "Gradient-based kernel dimension reduction for supervised learning", "text": "This paper proposes a novel kernel approach to linear dimension reduction for supervised learning. The purpose of the dimension reduction is to find directions in the input space to explain the output as effectively as possible. The proposed method uses an estimator for the gradient of regression function, based on the covariance operators on reproducing kernel Hilbert spaces. In comparison with other existing methods, the proposed one has wide applicability without strong assumptions on the distributions or the type of variables, and uses computationally simple eigendecomposition. Experimental results show that the proposed method successfully finds the effective directions with efficient computation.", "source": "arxiv/ml"}
{"id": "arxiv:1045", "title": "The Variational Garrote", "text": "In this paper, we present a new variational method for sparse regression using $L_0$ regularization. The variational parameters appear in the approximate model in a way that is similar to Breiman's Garrote model. We refer to this method as the variational Garrote (VG). We show that the combination of the variational approximation and $L_0$ regularization has the effect of making the problem effectively of maximal rank even when the number of samples is small compared to the number of variables. The VG is compared numerically with the Lasso method, ridge regression and the recently introduced paired mean field method (PMF) (M. Titsias & M. L\\'azaro-Gredilla., NIPS 2012). Numerical results show that the VG and PMF yield more accurate predictions and more accurately reconstruct the true model than the other methods. It is shown that the VG finds correct solutions when the Lasso solution is inconsistent due to large input correlations. Globally, VG is significantly faster than PMF and tends to perform better as the problems become denser and in problems with strongly correlated inputs. The naive implementation of the VG scales cubic with the number of features. By introducing Lagrange multipliers we obtain a dual formulation of the problem that scales cubic in the number of samples, but close to linear in the number of features.", "source": "arxiv/ml"}
{"id": "arxiv:1046", "title": "How Open Should Open Source Be?", "text": "Many open-source projects land security fixes in public repositories before shipping these patches to users. This paper presents attacks on such projects - taking Firefox as a case-study - that exploit patch metadata to efficiently search for security patches prior to shipping. Using access-restricted bug reports linked from patch descriptions, security patches can be immediately identified for 260 out of 300 days of Firefox 3 development. In response to Mozilla obfuscating descriptions, we show that machine learning can exploit metadata such as patch author to search for security patches, extending the total window of vulnerability by 5 months in an 8 month period when examining up to two patches daily. Finally we present strong evidence that further metadata obfuscation is unlikely to prevent information leaks, and we argue that open-source projects instead ought to keep security patches secret until they are ready to be released.", "source": "arxiv/ml"}
{"id": "arxiv:1047", "title": "ShareBoost: Efficient Multiclass Learning with Feature Sharing", "text": "Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features should be shared by several classes. We describe and analyze the ShareBoost algorithm for learning a multiclass predictor that uses few shared features. We prove that ShareBoost efficiently finds a predictor that uses few shared features (if such a predictor exists) and that it has a small generalization error. We also describe how to use ShareBoost for learning a non-linear predictor that has a fast evaluation time. In a series of experiments with natural data sets we demonstrate the benefits of ShareBoost and evaluate its success relatively to other state-of-the-art approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1048", "title": "Nonlinear Channel Estimation for OFDM System by Complex LS-SVM under High Mobility Conditions", "text": "A nonlinear channel estimator using complex Least Square Support Vector Machines (LS-SVM) is proposed for pilot-aided OFDM system and applied to Long Term Evolution (LTE) downlink under high mobility conditions. The estimation algorithm makes use of the reference signals to estimate the total frequency response of the highly selective multipath channel in the presence of non-Gaussian impulse noise interfering with pilot signals. Thus, the algorithm maps trained data into a high dimensional feature space and uses the structural risk minimization (SRM) principle to carry out the regression estimation for the frequency response function of the highly selective channel. The simulations show the effectiveness of the proposed method which has good performance and high precision to track the variations of the fading channels compared to the conventional LS method and it is robust at high speed mobility.", "source": "arxiv/ml"}
{"id": "arxiv:1049", "title": "Review on Feature Selection Techniques and the Impact of SVM for Cancer Classification using Gene Expression Profile", "text": "The DNA microarray technology has modernized the approach of biology research in such a way that scientists can now measure the expression levels of thousands of genes simultaneously in a single experiment. Gene expression profiles, which represent the state of a cell at a molecular level, have great potential as a medical diagnosis tool. But compared to the number of genes involved, available training data sets generally have a fairly small sample size for classification. These training data limitations constitute a challenge to certain classification methodologies. Feature selection techniques can be used to extract the marker genes which influence the classification accuracy effectively by eliminating the un wanted noisy and redundant genes This paper presents a review of feature selection techniques that have been employed in micro array data based cancer classification and also the predominant role of SVM for cancer classification.", "source": "arxiv/ml"}
{"id": "arxiv:1050", "title": "Localization on low-order eigenvectors of data matrices", "text": "Eigenvector localization refers to the situation when most of the components of an eigenvector are zero or near-zero. This phenomenon has been observed on eigenvectors associated with extremal eigenvalues, and in many of those cases it can be meaningfully interpreted in terms of \"structural heterogeneities\" in the data. For example, the largest eigenvectors of adjacency matrices of large complex networks often have most of their mass localized on high-degree nodes; and the smallest eigenvectors of the Laplacians of such networks are often localized on small but meaningful community-like sets of nodes. Here, we describe localization associated with low-order eigenvectors, i.e., eigenvectors corresponding to eigenvalues that are not extremal but that are \"buried\" further down in the spectrum. Although we have observed it in several unrelated applications, this phenomenon of low-order eigenvector localization defies common intuitions and simple explanations, and it creates serious difficulties for the applicability of popular eigenvector-based machine learning and data analysis tools. After describing two examples where low-order eigenvector localization arises, we present a very simple model that qualitatively reproduces several of the empirically-observed results. This model suggests certain coarse structural similarities among the seemingly-unrelated applications where we have observed low-order eigenvector localization, and it may be used as a diagnostic tool to help extract insight from data graphs when such low-order eigenvector localization is present.", "source": "arxiv/ml"}
{"id": "arxiv:1051", "title": "Gossip Learning with Linear Models on Fully Distributed Data", "text": "Machine learning over fully distributed data poses an important problem in peer-to-peer (P2P) applications. In this model we have one data record at each network node, but without the possibility to move raw data due to privacy considerations. For example, user profiles, ratings, history, or sensor readings can represent this case. This problem is difficult, because there is no possibility to learn local models, the system model offers almost no guarantees for reliability, yet the communication cost needs to be kept low. Here we propose gossip learning, a generic approach that is based on multiple models taking random walks over the network in parallel, while applying an online learning algorithm to improve themselves, and getting combined via ensemble learning methods. We present an instantiation of this approach for the case of classification with linear models. Our main contribution is an ensemble learning method which---through the continuous combination of the models in the network---implements a virtual weighted voting mechanism over an exponential number of models at practically no extra cost as compared to independent random walks. We prove the convergence of the method theoretically, and perform extensive experiments on benchmark datasets. Our experimental analysis demonstrates the performance and robustness of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:1052", "title": "Dynamics of Boltzmann Q-Learning in Two-Player Two-Action Games", "text": "We consider the dynamics of Q-learning in two-player two-action games with a Boltzmann exploration mechanism. For any non-zero exploration rate the dynamics is dissipative, which guarantees that agent strategies converge to rest points that are generally different from the game's Nash Equlibria (NE). We provide a comprehensive characterization of the rest point structure for different games, and examine the sensitivity of this structure with respect to the noise due to exploration. Our results indicate that for a class of games with multiple NE the asymptotic behavior of learning dynamics can undergo drastic changes at critical exploration rates. Furthermore, we demonstrate that for certain games with a single NE, it is possible to have additional rest points (not corresponding to any NE) that persist for a finite range of the exploration rates and disappear when the exploration rates of both players tend to zero.", "source": "arxiv/ml"}
{"id": "arxiv:1053", "title": "The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret", "text": "In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \\geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \\emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie), which leads to the same average reward that can be achieved by the optimal policy under a known model. This is the first such result in the literature for a non-Bayesian RMAB. For our proof, we also develop a novel generalization of the Chernoff-Hoeffding bound.", "source": "arxiv/ml"}
{"id": "arxiv:1054", "title": "Efficient Online Learning for Opportunistic Spectrum Access", "text": "The problem of opportunistic spectrum access in cognitive radio networks has been recently formulated as a non-Bayesian restless multi-armed bandit problem. In this problem, there are N arms (corresponding to channels) and one player (corresponding to a secondary user). The state of each arm evolves as a finite-state Markov chain with unknown parameters. At each time slot, the player can select K < N arms to play and receives state-dependent rewards (corresponding to the throughput obtained given the activity of primary users). The objective is to maximize the expected total rewards (i.e., total throughput) obtained over multiple plays. The performance of an algorithm for such a multi-armed bandit problem is measured in terms of regret, defined as the difference in expected reward compared to a model-aware genie who always plays the best K arms. In this paper, we propose a new continuous exploration and exploitation (CEE) algorithm for this problem. When no information is available about the dynamics of the arms, CEE is the first algorithm to guarantee near-logarithmic regret uniformly over time. When some bounds corresponding to the stationary state distributions and the state-dependent rewards are known, we show that CEE can be easily modified to achieve logarithmic regret over time. In contrast, prior algorithms require additional information concerning bounds on the second eigenvalues of the transition matrices in order to guarantee logarithmic regret. Finally, we show through numerical simulations that CEE is more efficient than prior algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1055", "title": "On Clustering on Graphs with Multiple Edge Types", "text": "We study clustering on graphs with multiple edge types. Our main motivation is that similarities between objects can be measured in many different metrics. For instance similarity between two papers can be based on common authors, where they are published, keyword similarity, citations, etc. As such, graphs with multiple edges is a more accurate model to describe similarities between objects. Each edge/metric provides only partial information about the data; recovering full information requires aggregation of all the similarity metrics. Clustering becomes much more challenging in this context, since in addition to the difficulties of the traditional clustering problem, we have to deal with a space of clusterings. We generalize the concept of clustering in single-edge graphs to multi-edged graphs and investigate problems such as: Can we find a clustering that remains good, even if we change the relative weights of metrics? How can we describe the space of clusterings efficiently? Can we find unexpected clusterings (a good clustering that is distant from all given clusterings)? If given the ground-truth clustering, can we recover how the weights for edge types were aggregated? %In this paper, we discuss these problems and the underlying algorithmic challenges and propose some solutions. We also present two case studies: one based on papers on Arxiv and one based on CIA World Factbook.", "source": "arxiv/ml"}
{"id": "arxiv:1056", "title": "Online Learning for Combinatorial Network Optimization with Restless Markovian Rewards", "text": "Combinatorial network optimization algorithms that compute optimal structures taking into account edge weights form the foundation for many network protocols. Examples include shortest path routing, minimal spanning tree computation, maximum weighted matching on bipartite graphs, etc. We present CLRMR, the first online learning algorithm that efficiently solves the stochastic version of these problems where the underlying edge weights vary as independent Markov chains with unknown dynamics. The performance of an online learning algorithm is characterized in terms of regret, defined as the cumulative difference in rewards between a suitably-defined genie, and that obtained by the given algorithm. We prove that, compared to a genie that knows the Markov transition matrices and uses the single-best structure at all times, CLRMR yields regret that is polynomial in the number of edges and nearly-logarithmic in time.", "source": "arxiv/ml"}
{"id": "arxiv:1057", "title": "Anomaly Sequences Detection from Logs Based on Compression", "text": "Mining information from logs is an old and still active research topic. In recent years, with the rapid emerging of cloud computing, log mining becomes increasingly important to industry. This paper focus on one major mission of log mining: anomaly detection, and proposes a novel method for mining abnormal sequences from large logs. Different from previous anomaly detection systems which based on statistics, probabilities and Markov assumption, our approach measures the strangeness of a sequence using compression. It first trains a grammar about normal behaviors using grammar-based compression, then measures the information quantities and densities of questionable sequences according to incrementation of grammar length. We have applied our approach on mining some real bugs from fine grained execution logs. We have also tested its ability on intrusion detection using some publicity available system call traces. The experiments show that our method successfully selects the strange sequences which related to bugs or attacking.", "source": "arxiv/ml"}
{"id": "arxiv:1058", "title": "Weighted Clustering", "text": "One of the most prominent challenges in clustering is \"the user's dilemma,\" which is the problem of selecting an appropriate clustering algorithm for a specific task. A formal approach for addressing this problem relies on the identification of succinct, user-friendly properties that formally capture when certain clustering methods are preferred over others. Until now these properties focused on advantages of classical Linkage-Based algorithms, failing to identify when other clustering paradigms, such as popular center-based methods, are preferable. We present surprisingly simple new properties that delineate the differences between common clustering paradigms, which clearly and formally demonstrates advantages of center-based approaches for some applications. These properties address how sensitive algorithms are to changes in element frequencies, which we capture in a generalized setting where every element is associated with a real-valued weight.", "source": "arxiv/ml"}
{"id": "arxiv:1059", "title": "Trace Lasso: a trace norm regularization for correlated designs", "text": "Using the $\\ell_1$-norm to regularize the estimation of the parameter vector of a linear model leads to an unstable estimator when covariates are highly correlated. In this paper, we introduce a new penalty function which takes into account the correlation of the design matrix to stabilize the estimation. This norm, called the trace Lasso, uses the trace norm, which is a convex surrogate of the rank, of the selected covariates as the criterion of model complexity. We analyze the properties of our norm, describe an optimization algorithm based on reweighted least-squares, and illustrate the behavior of this norm on synthetic data, showing that it is more adapted to strong correlations than competing methods such as the elastic net.", "source": "arxiv/ml"}
{"id": "arxiv:1060", "title": "Learning Sequence Neighbourhood Metrics", "text": "Recurrent neural networks (RNNs) in combination with a pooling operator and the neighbourhood components analysis (NCA) objective function are able to detect the characterizing dynamics of sequences and embed them into a fixed-length vector space of arbitrary dimensionality. Subsequently, the resulting features are meaningful and can be used for visualization or nearest neighbour classification in linear time. This kind of metric learning for sequential data enables the use of algorithms tailored towards fixed length vector spaces such as R^n.", "source": "arxiv/ml"}
{"id": "arxiv:1061", "title": "Learning From Labeled And Unlabeled Data: An Empirical Study Across Techniques And Domains", "text": "There has been increased interest in devising learning techniques that combine unlabeled data with labeled data ? i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques and different types and amounts of labeled and unlabeled data. Moreover, most of the published work on semi-supervised learning techniques assumes that the labeled and unlabeled data come from the same distribution. It is possible for the labeling process to be associated with a selection bias such that the distributions of data points in the labeled and unlabeled sets are different. Not correcting for such bias can result in biased function approximation with potentially poor performance. In this paper, we present an empirical study of various semi-supervised learning techniques on a variety of datasets. We attempt to answer various questions such as the effect of independence or relevance amongst features, the effect of the size of the labeled and unlabeled sets and the effect of noise. We also investigate the impact of sample-selection bias on the semi-supervised learning techniques under study and implement a bivariate probit technique particularly designed to correct for such bias.", "source": "arxiv/ml"}
{"id": "arxiv:1062", "title": "Online Learning Algorithms for Stochastic Water-Filling", "text": "Water-filling is the term for the classic solution to the problem of allocating constrained power to a set of parallel channels to maximize the total data-rate. It is used widely in practice, for example, for power allocation to sub-carriers in multi-user OFDM systems such as WiMax. The classic water-filling algorithm is deterministic and requires perfect knowledge of the channel gain to noise ratios. In this paper we consider how to do power allocation over stochastically time-varying (i.i.d.) channels with unknown gain to noise ratio distributions. We adopt an online learning framework based on stochastic multi-armed bandits. We consider two variations of the problem, one in which the goal is to find a power allocation to maximize $\\sum\\limits_i \\mathbb{E}[\\log(1 + SNR_i)]$, and another in which the goal is to find a power allocation to maximize $\\sum\\limits_i \\log(1 + \\mathbb{E}[SNR_i])$. For the first problem, we propose a \\emph{cognitive water-filling} algorithm that we call CWF1. We show that CWF1 obtains a regret (defined as the cumulative gap over time between the sum-rate obtained by a distribution-aware genie and this policy) that grows polynomially in the number of channels and logarithmically in time, implying that it asymptotically achieves the optimal time-averaged rate that can be obtained when the gain distributions are known. For the second problem, we present an algorithm called CWF2, which is, to our knowledge, the first algorithm in the literature on stochastic multi-armed bandits to exploit non-linear dependencies between the arms. We prove that the number of times CWF2 picks the incorrect power allocation is bounded by a function that is polynomial in the number of channels and logarithmic in time, implying that its frequency of incorrect allocation tends to zero.", "source": "arxiv/ml"}
{"id": "arxiv:1063", "title": "Efficiency versus Convergence of Boolean Kernels for On-Line Learning Algorithms", "text": "The paper studies machine learning problems where each example is described using a set of Boolean features and where hypotheses are represented by linear threshold elements. One method of increasing the expressiveness of learned hypotheses in this context is to expand the feature set to include conjunctions of basic features. This can be done explicitly or where possible by using a kernel function. Focusing on the well known Perceptron and Winnow algorithms, the paper demonstrates a tradeoff between the computational efficiency with which the algorithm can be run over the expanded feature space and the generalization ability of the corresponding learning algorithm. We first describe several kernel functions which capture either limited forms of conjunctions or all conjunctions. We show that these kernels can be used to efficiently run the Perceptron algorithm over a feature space of exponentially many conjunctions; however we also show that using such kernels, the Perceptron algorithm can provably make an exponential number of mistakes even when learning simple functions. We then consider the question of whether kernel functions can analogously be used to run the multiplicative-update Winnow algorithm over an expanded feature space of exponentially many conjunctions. Known upper bounds imply that the Winnow algorithm can learn Disjunctive Normal Form (DNF) formulae with a polynomial mistake bound in this setting. However, we prove that it is computationally hard to simulate Winnows behavior for learning DNF over such a feature set. This implies that the kernel functions which correspond to running Winnow for this problem are not efficiently computable, and that there is no general construction that can run Winnow with kernels.", "source": "arxiv/ml"}
{"id": "arxiv:1064", "title": "Risk-Sensitive Reinforcement Learning Applied to Control under Constraints", "text": "In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with respect to a policy as the probability of entering such a state when the policy is pursued. We consider the problem of finding good policies whose risk is smaller than some user-specified threshold, and formalize it as a constrained MDP with two criteria. The first criterion corresponds to the value function originally given. We will show that the risk can be formulated as a second criterion function based on a cumulative return, whose definition is independent of the original value function. We present a model free, heuristic reinforcement learning algorithm that aims at finding good deterministic policies. It is based on weighting the original value function and the risk. The weight parameter is adapted in order to find a feasible solution for the constrained problem that has a good performance with respect to the value function. The algorithm was successfully applied to the control of a feed tank with stochastic inflows that lies upstream of a distillation column. This control task was originally formulated as an optimal control problem with chance constraints, and it was solved under certain assumptions on the model to obtain an optimal solution. The power of our learning algorithm is that it can be used even when some of these restrictive assumptions are relaxed.", "source": "arxiv/ml"}
{"id": "arxiv:1065", "title": "A Learning Theory Approach to Non-Interactive Database Privacy", "text": "In this paper we demonstrate that, ignoring computational constraints, it is possible to privately release synthetic databases that are useful for large classes of queries -- much larger in size than the database itself. Specifically, we give a mechanism that privately releases synthetic data for a class of queries over a discrete domain with error that grows as a function of the size of the smallest net approximately representing the answers to that class of queries. We show that this in particular implies a mechanism for counting queries that gives error guarantees that grow only with the VC-dimension of the class of queries, which itself grows only logarithmically with the size of the query class. We also show that it is not possible to privately release even simple classes of queries (such as intervals and their generalizations) over continuous domains. Despite this, we give a privacy-preserving polynomial time algorithm that releases information useful for all halfspace queries, given a slight relaxation of the utility guarantee. This algorithm does not release synthetic data, but instead another data structure capable of representing an answer for each query. We also give an efficient algorithm for releasing synthetic data for the class of interval queries and axis-aligned rectangles of constant dimension. Finally, inspired by learning theory, we introduce a new notion of data privacy, which we call distributional privacy, and show that it is strictly stronger than the prevailing privacy notion, differential privacy.", "source": "arxiv/ml"}
{"id": "arxiv:1066", "title": "Bandits with an Edge", "text": "We consider a bandit problem over a graph where the rewards are not directly observed. Instead, the decision maker can compare two nodes and receive (stochastic) information pertaining to the difference in their value. The graph structure describes the set of possible comparisons. Consequently, comparing between two nodes that are relatively far requires estimating the difference between every pair of nodes on the path between them. We analyze this problem from the perspective of sample complexity: How many queries are needed to find an approximately optimal node with probability more than $1-\\delta$ in the PAC setup? We show that the topology of the graph plays a crucial in defining the sample complexity: graphs with a low diameter have a much better sample complexity.", "source": "arxiv/ml"}
{"id": "arxiv:1067", "title": "MIS-Boost: Multiple Instance Selection Boosting", "text": "In this paper, we present a new multiple instance learning (MIL) method, called MIS-Boost, which learns discriminative instance prototypes by explicit instance selection in a boosting framework. Unlike previous instance selection based MIL methods, we do not restrict the prototypes to a discrete set of training instances but allow them to take arbitrary values in the instance feature space. We also do not restrict the total number of prototypes and the number of selected-instances per bag; these quantities are completely data-driven. We show that MIS-Boost outperforms state-of-the-art MIL methods on a number of benchmark datasets. We also apply MIS-Boost to large-scale image classification, where we show that the automatically selected prototypes map to visually meaningful image regions.", "source": "arxiv/ml"}
{"id": "arxiv:1068", "title": "A Probabilistic Framework for Discriminative Dictionary Learning", "text": "In this paper, we address the problem of discriminative dictionary learning (DDL), where sparse linear representation and classification are combined in a probabilistic framework. As such, a single discriminative dictionary and linear binary classifiers are learned jointly. By encoding sparse representation and discriminative classification models in a MAP setting, we propose a general optimization framework that allows for a data-driven tradeoff between faithful representation and accurate classification. As opposed to previous work, our learning methodology is capable of incorporating a diverse family of classification cost functions (including those used in popular boosting methods), while avoiding the need for involved optimization techniques. We show that DDL can be solved by a sequence of updates that make use of well-known and well-studied sparse coding and dictionary learning algorithms from the literature. To validate our DDL framework, we apply it to digit classification and face recognition and test it on standard benchmarks.", "source": "arxiv/ml"}
{"id": "arxiv:1069", "title": "Structured sparsity through convex optimization", "text": "Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. While naturally cast as a combinatorial optimization problem, variable or feature selection admits a convex relaxation through the regularization by the $\\ell_1$-norm. In this paper, we consider situations where we are not only interested in sparsity, but where some structural prior knowledge is available as well. We show that the $\\ell_1$-norm can then be extended to structured norms built on either disjoint or overlapping groups of variables, leading to a flexible framework that can deal with various structures. We present applications to unsupervised learning, for structured sparse principal component analysis and hierarchical dictionary learning, and to supervised learning in the context of non-linear variable selection.", "source": "arxiv/ml"}
{"id": "arxiv:1070", "title": "Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization", "text": "We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the non-smooth term. We show that both the basic proximal-gradient method and the accelerated proximal-gradient method achieve the same convergence rate as in the error-free case, provided that the errors decrease at appropriate rates.Using these rates, we perform as well as or better than a carefully chosen fixed error level on a set of structured sparsity problems.", "source": "arxiv/ml"}
{"id": "arxiv:1071", "title": "Active Learning for Node Classification in Assortative and Disassortative Networks", "text": "In many real-world networks, nodes have class labels, attributes, or variables that affect the network's topology. If the topology of the network is known but the labels of the nodes are hidden, we would like to select a small subset of nodes such that, if we knew their labels, we could accurately predict the labels of all the other nodes. We develop an active learning algorithm for this problem which uses information-theoretic techniques to choose which nodes to explore. We test our algorithm on networks from three different domains: a social network, a network of English words that appear adjacently in a novel, and a marine food web. Our algorithm makes no initial assumptions about how the groups connect, and performs well even when faced with quite general types of network structure. In particular, we do not assume that nodes of the same class are more likely to be connected to each other---only that they connect to the rest of the network in similar ways.", "source": "arxiv/ml"}
{"id": "arxiv:1072", "title": "Reconstruction of sequential data with density models", "text": "We introduce the problem of reconstructing a sequence of multidimensional real vectors where some of the data are missing. This problem contains regression and mapping inversion as particular cases where the pattern of missing data is independent of the sequence index. The problem is hard because it involves possibly multivalued mappings at each vector in the sequence, where the missing variables can take more than one value given the present variables; and the set of missing variables can vary from one vector to the next. To solve this problem, we propose an algorithm based on two redundancy assumptions: vector redundancy (the data live in a low-dimensional manifold), so that the present variables constrain the missing ones; and sequence redundancy (e.g. continuity), so that consecutive vectors constrain each other. We capture the low-dimensional nature of the data in a probabilistic way with a joint density model, here the generative topographic mapping, which results in a Gaussian mixture. Candidate reconstructions at each vector are obtained as all the modes of the conditional distribution of missing variables given present variables. The reconstructed sequence is obtained by minimising a global constraint, here the sequence length, by dynamic programming. We present experimental results for a toy problem and for inverse kinematics of a robot arm.", "source": "arxiv/ml"}
{"id": "arxiv:1073", "title": "Distributed User Profiling via Spectral Methods", "text": "User profiling is a useful primitive for constructing personalised services, such as content recommendation. In the present paper we investigate the feasibility of user profiling in a distributed setting, with no central authority and only local information exchanges between users. We compute a profile vector for each user (i.e., a low-dimensional vector that characterises her taste) via spectral transformation of observed user-produced ratings for items. Our two main contributions follow: i) We consider a low-rank probabilistic model of user taste. More specifically, we consider that users and items are partitioned in a constant number of classes, such that users and items within the same class are statistically identical. We prove that without prior knowledge of the compositions of the classes, based solely on few random observed ratings (namely $O(N\\log N)$ such ratings for $N$ users), we can predict user preference with high probability for unrated items by running a local vote among users with similar profile vectors. In addition, we provide empirical evaluations characterising the way in which spectral profiling performance depends on the dimension of the profile space. Such evaluations are performed on a data set of real user ratings provided by Netflix. ii) We develop distributed algorithms which provably achieve an embedding of users into a low-dimensional space, based on spectral transformation. These involve simple message passing among users, and provably converge to the desired embedding. Our method essentially relies on a novel combination of gossiping and the algorithm proposed by Oja and Karhunen.", "source": "arxiv/ml"}
{"id": "arxiv:1074", "title": "Learning Topic Models by Belief Propagation", "text": "Latent Dirichlet allocation (LDA) is an important hierarchical Bayesian model for probabilistic topic modeling, which attracts worldwide interests and touches on many important applications in text mining, computer vision and computational biology. This paper represents LDA as a factor graph within the Markov random field (MRF) framework, which enables the classic loopy belief propagation (BP) algorithm for approximate inference and parameter estimation. Although two commonly-used approximate inference methods, such as variational Bayes (VB) and collapsed Gibbs sampling (GS), have gained great successes in learning LDA, the proposed BP is competitive in both speed and accuracy as validated by encouraging experimental results on four large-scale document data sets. Furthermore, the BP algorithm has the potential to become a generic learning scheme for variants of LDA-based topic models. To this end, we show how to learn two typical variants of LDA-based topic models, such as author-topic models (ATM) and relational topic models (RTM), using BP based on the factor graph representation.", "source": "arxiv/ml"}
{"id": "arxiv:1075", "title": "Active Ranking using Pairwise Comparisons", "text": "This paper examines the problem of ranking a collection of objects using pairwise comparisons (rankings of two objects). In general, the ranking of $n$ objects can be identified by standard sorting methods using $n log_2 n$ pairwise comparisons. We are interested in natural situations in which relationships among the objects may allow for ranking using far fewer pairwise comparisons. Specifically, we assume that the objects can be embedded into a $d$-dimensional Euclidean space and that the rankings reflect their relative distances from a common reference point in $R^d$. We show that under this assumption the number of possible rankings grows like $n^{2d}$ and demonstrate an algorithm that can identify a randomly selected ranking using just slightly more than $d log n$ adaptively selected pairwise comparisons, on average. If instead the comparisons are chosen at random, then almost all pairwise comparisons must be made in order to identify any ranking. In addition, we propose a robust, error-tolerant algorithm that only requires that the pairwise comparisons are probably correct. Experimental studies with synthetic and real datasets support the conclusions of our theoretical analysis.", "source": "arxiv/ml"}
{"id": "arxiv:1076", "title": "Fast approximation of matrix coherence and statistical leverage", "text": "The statistical leverage scores of a matrix $A$ are the squared row-norms of the matrix containing its (top) left singular vectors and the coherence is the largest leverage score. These quantities are of interest in recently-popular problems such as matrix completion and Nystr\\\"{o}m-based low-rank matrix approximation as well as in large-scale statistical data analysis applications more generally; moreover, they are of interest since they define the key structural nonuniformity that must be dealt with in developing fast randomized matrix algorithms. Our main result is a randomized algorithm that takes as input an arbitrary $n \\times d$ matrix $A$, with $n \\gg d$, and that returns as output relative-error approximations to all $n$ of the statistical leverage scores. The proposed algorithm runs (under assumptions on the precise values of $n$ and $d$) in $O(n d \\log n)$ time, as opposed to the $O(nd^2)$ time required by the na\\\"{i}ve algorithm that involves computing an orthogonal basis for the range of $A$. Our analysis may be viewed in terms of computing a relative-error approximation to an underconstrained least-squares approximation problem, or, relatedly, it may be viewed as an application of Johnson-Lindenstrauss type ideas. Several practically-important extensions of our basic result are also described, including the approximation of so-called cross-leverage scores, the extension of these ideas to matrices with $n \\approx d$, and the extension to streaming environments.", "source": "arxiv/ml"}
{"id": "arxiv:1077", "title": "Learning Discriminative Metrics via Generative Models and Kernel Learning", "text": "Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework. Specifically, we learn local metrics optimized from parametric generative models. These are then used as base kernels to construct a global kernel that minimizes a discriminative training criterion. We consider both linear and nonlinear combinations of local metric kernels. Our empirical results show that these combinations significantly improve performance on classification tasks. The proposed learning algorithm is also very efficient, achieving order of magnitude speedup in training time compared to previous discriminative baseline methods.", "source": "arxiv/ml"}
{"id": "arxiv:1078", "title": "VC dimension of ellipsoids", "text": "We will establish that the VC dimension of the class of d-dimensional ellipsoids is (d^2+3d)/2, and that maximum likelihood estimate with N-component d-dimensional Gaussian mixture models induces a geometric class having VC dimension at least N(d^2+3d)/2. Keywords: VC dimension; finite dimensional ellipsoid; Gaussian mixture model", "source": "arxiv/ml"}
{"id": "arxiv:1079", "title": "Manifold estimation and singular deconvolution under Hausdorff loss", "text": "We find lower and upper bounds for the risk of estimating a manifold in Hausdorff distance under several models. We also show that there are close connections between manifold estimation and the problem of deconvolving a singular measure.", "source": "arxiv/ml"}
{"id": "arxiv:1080", "title": "Memristive fuzzy edge detector", "text": "Fuzzy inference systems always suffer from the lack of efficient structures or platforms for their hardware implementation. In this paper, we tried to overcome this problem by proposing new method for the implementation of those fuzzy inference systems which use fuzzy rule base to make inference. To achieve this goal, we have designed a multi-layer neuro-fuzzy computing system based on the memristor crossbar structure by introducing some new concepts like fuzzy minterms. Although many applications can be realized through the use of our proposed system, in this study we show how the fuzzy XOR function can be constructed and how it can be used to extract edges from grayscale images. Our memristive fuzzy edge detector (implemented in analog form) compared with other common edge detectors has this advantage that it can extract edges of any given image all at once in real-time.", "source": "arxiv/ml"}
{"id": "arxiv:1081", "title": "Robust estimation of latent tree graphical models: Inferring hidden states with inexact parameters", "text": "Latent tree graphical models are widely used in computational biology, signal and image processing, and network tomography. Here we design a new efficient, estimation procedure for latent tree models, including Gaussian and discrete, reversible models, that significantly improves on previous sample requirement bounds. Our techniques are based on a new hidden state estimator which is robust to inaccuracies in estimated parameters. More precisely, we prove that latent tree models can be estimated with high probability in the so-called Kesten-Stigum regime with $O(log^2 n)$ samples where $n$ is the number of nodes.", "source": "arxiv/ml"}
{"id": "arxiv:1082", "title": "Exhaustive and Efficient Constraint Propagation: A Semi-Supervised Learning Perspective and Its Applications", "text": "This paper presents a novel pairwise constraint propagation approach by decomposing the challenging constraint propagation problem into a set of independent semi-supervised learning subproblems which can be solved in quadratic time using label propagation based on k-nearest neighbor graphs. Considering that this time cost is proportional to the number of all possible pairwise constraints, our approach actually provides an efficient solution for exhaustively propagating pairwise constraints throughout the entire dataset. The resulting exhaustive set of propagated pairwise constraints are further used to adjust the similarity matrix for constrained spectral clustering. Other than the traditional constraint propagation on single-source data, our approach is also extended to more challenging constraint propagation on multi-source data where each pairwise constraint is defined over a pair of data points from different sources. This multi-source constraint propagation has an important application to cross-modal multimedia retrieval. Extensive results have shown the superior performance of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:1083", "title": "Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition", "text": "This paper proposes a novel latent semantic learning method for extracting high-level features (i.e. latent semantics) from a large vocabulary of abundant mid-level features (i.e. visual keywords) with structured sparse representation, which can help to bridge the semantic gap in the challenging task of human action recognition. To discover the manifold structure of midlevel features, we develop a spectral embedding approach to latent semantic learning based on L1-graph, without the need to tune any parameter for graph construction as a key step of manifold learning. More importantly, we construct the L1-graph with structured sparse representation, which can be obtained by structured sparse coding with its structured sparsity ensured by novel L1-norm hypergraph regularization over mid-level features. In the new embedding space, we learn latent semantics automatically from abundant mid-level features through spectral clustering. The learnt latent semantics can be readily used for human action recognition with SVM by defining a histogram intersection kernel. Different from the traditional latent semantic analysis based on topic models, our latent semantic learning method can explore the manifold structure of mid-level features in both L1-graph construction and spectral embedding, which results in compact but discriminative high-level features. The experimental results on the commonly used KTH action dataset and unconstrained YouTube action dataset show the superior performance of our method.", "source": "arxiv/ml"}
{"id": "arxiv:1084", "title": "Application of distances between terms for flat and hierarchical data", "text": "In machine learning, distance-based algorithms, and other approaches, use information that is represented by propositional data. However, this kind of representation can be quite restrictive and, in many cases, it requires more complex structures in order to represent data in a more natural way. Terms are the basis for functional and logic programming representation. Distances between terms are a useful tool not only to compare terms, but also to determine the search space in many of these applications. This dissertation applies distances between terms, exploiting the features of each distance and the possibility to compare from propositional data types to hierarchical representations. The distances between terms are applied through the k-NN (k-nearest neighbor) classification algorithm using XML as a common language representation. To be able to represent these data in an XML structure and to take advantage of the benefits of distance between terms, it is necessary to apply some transformations. These transformations allow the conversion of flat data into hierarchical data represented in XML, using some techniques based on intuitive associations between the names and values of variables and associations based on attribute similarity. Several experiments with the distances between terms of Nienhuys-Cheng and Estruch et al. were performed. In the case of originally propositional data, these distances are compared to the Euclidean distance. In all cases, the experiments were performed with the distance-weighted k-nearest neighbor algorithm, using several exponents for the attraction function (weighted distance). It can be seen that in some cases, the term distances can significantly improve the results on approaches applied to flat representations.", "source": "arxiv/ml"}
{"id": "arxiv:1085", "title": "Noise Tolerance under Risk Minimization", "text": "In this paper we explore noise tolerant learning of classifiers. We formulate the problem as follows. We assume that there is an ${\\bf unobservable}$ training set which is noise-free. The actual training set given to the learning algorithm is obtained from this ideal data set by corrupting the class label of each example. The probability that the class label of an example is corrupted is a function of the feature vector of the example. This would account for most kinds of noisy data one encounters in practice. We say that a learning method is noise tolerant if the classifiers learnt with the ideal noise-free data and with noisy data, both have the same classification accuracy on the noise-free data. In this paper we analyze the noise tolerance properties of risk minimization (under different loss functions), which is a generic method for learning classifiers. We show that risk minimization under 0-1 loss function has impressive noise tolerance properties and that under squared error loss is tolerant only to uniform noise; risk minimization under other loss functions is not noise tolerant. We conclude the paper with some discussion on implications of these theoretical results.", "source": "arxiv/ml"}
{"id": "arxiv:1086", "title": "Simultaneous Codeword Optimization (SimCO) for Dictionary Update and Learning", "text": "We consider the data-driven dictionary learning problem. The goal is to seek an over-complete dictionary from which every training signal can be best approximated by a linear combination of only a few codewords. This task is often achieved by iteratively executing two operations: sparse coding and dictionary update. In the literature, there are two benchmark mechanisms to update a dictionary. The first approach, such as the MOD algorithm, is characterized by searching for the optimal codewords while fixing the sparse coefficients. In the second approach, represented by the K-SVD method, one codeword and the related sparse coefficients are simultaneously updated while all other codewords and coefficients remain unchanged. We propose a novel framework that generalizes the aforementioned two methods. The unique feature of our approach is that one can update an arbitrary set of codewords and the corresponding sparse coefficients simultaneously: when sparse coefficients are fixed, the underlying optimization problem is similar to that in the MOD algorithm; when only one codeword is selected for update, it can be proved that the proposed algorithm is equivalent to the K-SVD method; and more importantly, our method allows us to update all codewords and all sparse coefficients simultaneously, hence the term simultaneous codeword optimization (SimCO). Under the proposed framework, we design two algorithms, namely, primitive and regularized SimCO. We implement these two algorithms based on a simple gradient descent mechanism. Simulations are provided to demonstrate the performance of the proposed algorithms, as compared with two baseline algorithms MOD and K-SVD. Results show that regularized SimCO is particularly appealing in terms of both learning performance and running speed.", "source": "arxiv/ml"}
{"id": "arxiv:1087", "title": "Bias Plus Variance Decomposition for Survival Analysis Problems", "text": "Bias - variance decomposition of the expected error defined for regression and classification problems is an important tool to study and compare different algorithms, to find the best areas for their application. Here the decomposition is introduced for the survival analysis problem. In our experiments, we study bias -variance parts of the expected error for two algorithms: original Cox proportional hazard regression and CoxPath, path algorithm for L1-regularized Cox regression, on the series of increased training sets. The experiments demonstrate that, contrary expectations, CoxPath does not necessarily have an advantage over Cox regression.", "source": "arxiv/ml"}
{"id": "arxiv:1088", "title": "Higher-Order Markov Tag-Topic Models for Tagged Documents and Images", "text": "This paper studies the topic modeling problem of tagged documents and images. Higher-order relations among tagged documents and images are major and ubiquitous characteristics, and play positive roles in extracting reliable and interpretable topics. In this paper, we propose the tag-topic models (TTM) to depict such higher-order topic structural dependencies within the Markov random field (MRF) framework. First, we use the novel factor graph representation of latent Dirichlet allocation (LDA)-based topic models from the MRF perspective, and present an efficient loopy belief propagation (BP) algorithm for approximate inference and parameter estimation. Second, we propose the factor hypergraph representation of TTM, and focus on both pairwise and higher-order relation modeling among tagged documents and images. Efficient loopy BP algorithm is developed to learn TTM, which encourages the topic labeling smoothness among tagged documents and images. Extensive experimental results confirm the incorporation of higher-order relations to be effective in enhancing the overall topic modeling performance, when compared with current state-of-the-art topic models, in many text and image mining tasks of broad interests such as word and link prediction, document classification, and tag recommendation.", "source": "arxiv/ml"}
{"id": "arxiv:1089", "title": "Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization", "text": "Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\\log(T)/T), by running SGD for T iterations and returning the average point. However, recent results showed that using a different algorithm, one can get an optimal O(1/T) rate. This might lead one to believe that standard SGD is suboptimal, and maybe should even be replaced as a method of choice. In this paper, we investigate the optimality of SGD in a stochastic setting. We show that for smooth problems, the algorithm attains the optimal O(1/T) rate. However, for non-smooth problems, the convergence rate with averaging might really be \\Omega(\\log(T)/T), and this is not just an artifact of the analysis. On the flip side, we show that a simple modification of the averaging step suffices to recover the O(1/T) rate, and no other change of the algorithm is necessary. We also present experimental results which support our findings, and point out open problems.", "source": "arxiv/ml"}
{"id": "arxiv:1090", "title": "Deterministic Feature Selection for $k$-means Clustering", "text": "We study feature selection for $k$-means clustering. Although the literature contains many methods with good empirical performance, algorithms with provable theoretical behavior have only recently been developed. Unfortunately, these algorithms are randomized and fail with, say, a constant probability. We address this issue by presenting a deterministic feature selection algorithm for k-means with theoretical guarantees. At the heart of our algorithm lies a deterministic method for decompositions of the identity.", "source": "arxiv/ml"}
{"id": "arxiv:1091", "title": "Learning Item Trees for Probabilistic Modelling of Implicit Feedback", "text": "User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, resulting in the development of accurate and scalable models. However, since explicit feedback is often difficult to collect it is important to develop effective models that take advantage of the more widely available implicit feedback. We introduce a probabilistic approach to collaborative filtering with implicit feedback based on modelling the user's item selection process. In the interests of scalability, we restrict our attention to tree-structured distributions over items and develop a principled and efficient algorithm for learning item trees from data. We also identify a problem with a widely used protocol for evaluating implicit feedback models and propose a way of addressing it using a small quantity of explicit feedback data.", "source": "arxiv/ml"}
{"id": "arxiv:1092", "title": "Domain Adaptation for Statistical Classifiers", "text": "The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the \"in-domain\" test data is drawn from a distribution that is related, but not identical, to the \"out-of-domain\" distribution of the training data. We consider the common case in which labeled out-of-domain data is plentiful, but labeled in-domain data is scarce. We introduce a statistical formulation of this problem in terms of a simple mixture model and present an instantiation of this framework to maximum entropy classifiers and their linear chain counterparts. We present efficient inference algorithms for this special case based on the technique of conditional expectation maximization. Our experimental results show that our approach leads to improved performance on three real world tasks on four different data sets from the natural language processing domain.", "source": "arxiv/ml"}
{"id": "arxiv:1093", "title": "Learning image transformations without training examples", "text": "The use of image transformations is essential for efficient modeling and learning of visual data. But the class of relevant transformations is large: affine transformations, projective transformations, elastic deformations, ... the list goes on. Therefore, learning these transformations, rather than hand coding them, is of great conceptual interest. To the best of our knowledge, all the related work so far has been concerned with either supervised or weakly supervised learning (from correlated sequences, video streams, or image-transform pairs). In this paper, on the contrary, we present a simple method for learning affine and elastic transformations when no examples of these transformations are explicitly given, and no prior knowledge of space (such as ordering of pixels) is included either. The system has only access to a moderately large database of natural images arranged in no particular order.", "source": "arxiv/ml"}
{"id": "arxiv:1094", "title": "Eclectic Extraction of Propositional Rules from Neural Networks", "text": "Artificial Neural Network is among the most popular algorithm for supervised learning. However, Neural Networks have a well-known drawback of being a \"Black Box\" learner that is not comprehensible to the Users. This lack of transparency makes it unsuitable for many high risk tasks such as medical diagnosis that requires a rational justification for making a decision. Rule Extraction methods attempt to curb this limitation by extracting comprehensible rules from a trained Network. Many such extraction algorithms have been developed over the years with their respective strengths and weaknesses. They have been broadly categorized into three types based on their approach to use internal model of the Network. Eclectic Methods are hybrid algorithms that combine the other approaches to attain more performance. In this paper, we present an Eclectic method called HERETIC. Our algorithm uses Inductive Decision Tree learning combined with information of the neural network structure for extracting logical rules. Experiments and theoretical analysis show HERETIC to be better in terms of speed and performance.", "source": "arxiv/ml"}
{"id": "arxiv:1095", "title": "Group Lasso with Overlaps: the Latent Group Lasso approach", "text": "We study a norm for structured sparsity which leads to sparse linear predictors whose supports are unions of prede ned overlapping groups of variables. We call the obtained formulation latent group Lasso, since it is based on applying the usual group Lasso penalty on a set of latent variables. A detailed analysis of the norm and its properties is presented and we characterize conditions under which the set of groups associated with latent variables are correctly identi ed. We motivate and discuss the delicate choice of weights associated to each group, and illustrate this approach on simulated data and on the problem of breast cancer prognosis from gene expression data.", "source": "arxiv/ml"}
{"id": "arxiv:1096", "title": "Two Projection Pursuit Algorithms for Machine Learning under Non-Stationarity", "text": "This thesis derives, tests and applies two linear projection algorithms for machine learning under non-stationarity. The first finds a direction in a linear space upon which a data set is maximally non-stationary. The second aims to robustify two-way classification against non-stationarity. The algorithm is tested on a key application scenario, namely Brain Computer Interfacing.", "source": "arxiv/ml"}
{"id": "arxiv:1097", "title": "Directed information and Pearl's causal calculus", "text": "Probabilistic graphical models are a fundamental tool in statistics, machine learning, signal processing, and control. When such a model is defined on a directed acyclic graph (DAG), one can assign a partial ordering to the events occurring in the corresponding stochastic system. Based on the work of Judea Pearl and others, these DAG-based \"causal factorizations\" of joint probability measures have been used for characterization and inference of functional dependencies (causal links). This mostly expository paper focuses on several connections between Pearl's formalism (and in particular his notion of \"intervention\") and information-theoretic notions of causality and feedback (such as causal conditioning, directed stochastic kernels, and directed information). As an application, we show how conditional directed information can be used to develop an information-theoretic version of Pearl's \"back-door\" criterion for identifiability of causal effects from passive observations. This suggests that the back-door criterion can be thought of as a causal analog of statistical sufficiency.", "source": "arxiv/ml"}
{"id": "arxiv:1098", "title": "Linearized Additive Classifiers", "text": "We revisit the additive model learning literature and adapt a penalized spline formulation due to Eilers and Marx, to train additive classifiers efficiently. We also propose two new embeddings based two classes of orthogonal basis with orthogonal derivatives, which can also be used to efficiently learn additive classifiers. This paper follows the popular theme in the current literature where kernel SVMs are learned much more efficiently using a approximate embedding and linear machine. In this paper we show that spline basis are especially well suited for learning additive models because of their sparsity structure and the ease of computing the embedding which enables one to train these models in an online manner, without incurring the memory overhead of precomputing the storing the embeddings. We show interesting connections between B-Spline basis and histogram intersection kernel and show that for a particular choice of regularization and degree of the B-Splines, our proposed learning algorithm closely approximates the histogram intersection kernel SVM. This enables one to learn additive models with almost no memory overhead compared to fast a linear solver, such as LIBLINEAR, while being only 5-6X slower on average. On two large scale image classification datasets, MNIST and Daimler Chrysler pedestrians, the proposed additive classifiers are as accurate as the kernel SVM, while being two orders of magnitude faster to train.", "source": "arxiv/ml"}
{"id": "arxiv:1099", "title": "Dictionary Learning for Deblurring and Digital Zoom", "text": "This paper proposes a novel approach to image deblurring and digital zooming using sparse local models of image appearance. These models, where small image patches are represented as linear combinations of a few elements drawn from some large set (dictionary) of candidates, have proven well adapted to several image restoration tasks. A key to their success has been to learn dictionaries adapted to the reconstruction of small image patches. In contrast, recent works have proposed instead to learn dictionaries which are not only adapted to data reconstruction, but also tuned for a specific task. We introduce here such an approach to deblurring and digital zoom, using pairs of blurry/sharp (or low-/high-resolution) images for training, as well as an effective stochastic gradient algorithm for solving the corresponding optimization task. Although this learning problem is not convex, once the dictionaries have been learned, the sharp/high-resolution image can be recovered via convex optimization at test time. Experiments with synthetic and real data demonstrate the effectiveness of the proposed approach, leading to state-of-the-art performance for non-blind image deblurring and digital zoom.", "source": "arxiv/ml"}
{"id": "arxiv:1100", "title": "Active Learning with Multiple Views", "text": "Active learners alleviate the burden of labeling large amounts of data by detecting and asking the user to label only the most informative examples in the domain. We focus here on active learning for multi-view domains, in which there are several disjoint subsets of features (views), each of which is sufficient to learn the target concept. In this paper we make several contributions. First, we introduce Co-Testing, which is the first approach to multi-view active learning. Second, we extend the multi-view learning framework by also exploiting weak views, which are adequate only for learning a concept that is more general/specific than the target concept. Finally, we empirically show that Co-Testing outperforms existing active learners on a variety of real world domains such as wrapper induction, Web page classification, advertisement removal, and discourse tree parsing.", "source": "arxiv/ml"}
{"id": "arxiv:1101", "title": "The Augmented Complex Kernel LMS", "text": "Recently, a unified framework for adaptive kernel based signal processing of complex data was presented by the authors, which, besides offering techniques to map the input data to complex Reproducing Kernel Hilbert Spaces, developed a suitable Wirtinger-like Calculus for general Hilbert Spaces. In this short paper, the extended Wirtinger's calculus is adopted to derive complex kernel-based widely-linear estimation filters. Furthermore, we illuminate several important characteristics of the widely linear filters. We show that, although in many cases the gains from adopting widely linear estimation filters, as alternatives to ordinary linear ones, are rudimentary, for the case of kernel based widely linear filters significant performance improvements can be obtained.", "source": "arxiv/ml"}
{"id": "arxiv:1102", "title": "Blackwell Approachability and Minimax Theory", "text": "This manuscript investigates the relationship between Blackwell Approachability, a stochastic vector-valued repeated game, and minimax theory, a single-play scalar-valued scenario. First, it is established in a general setting --- one not permitting invocation of minimax theory --- that Blackwell's Approachability Theorem and its generalization due to Hou are still valid. Second, minimax structure grants a result in the spirit of Blackwell's weak-approachability conjecture, later resolved by Vieille, that any set is either approachable by one player, or avoidable by the opponent. This analysis also reveals a strategy for the opponent.", "source": "arxiv/ml"}
{"id": "arxiv:1103", "title": "On the trade-off between complexity and correlation decay in structural learning algorithms", "text": "We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-complexity algorithms often fail when the Markov random field develops long-range correlations. More precisely, this phenomenon appears to be related to the Ising model phase transition (although it does not coincide with it).", "source": "arxiv/ml"}
{"id": "arxiv:1104", "title": "A Study of Unsupervised Adaptive Crowdsourcing", "text": "We consider unsupervised crowdsourcing performance based on the model wherein the responses of end-users are essentially rated according to how their responses correlate with the majority of other responses to the same subtasks/questions. In one setting, we consider an independent sequence of identically distributed crowdsourcing assignments (meta-tasks), while in the other we consider a single assignment with a large number of component subtasks. Both problems yield intuitive results in which the overall reliability of the crowd is a factor.", "source": "arxiv/ml"}
{"id": "arxiv:1105", "title": "A Behavior-based Approach for Multi-agent Q-learning for Autonomous Exploration", "text": "The use of mobile robots is being popular over the world mainly for autonomous explorations in hazardous/ toxic or unknown environments. This exploration will be more effective and efficient if the explorations in unknown environment can be aided with the learning from past experiences. Currently reinforcement learning is getting more acceptances for implementing learning in robots from the system-environment interactions. This learning can be implemented using the concept of both single-agent and multiagent. This paper describes such a multiagent approach for implementing a type of reinforcement learning using a priority based behaviour-based architecture. This proposed methodology has been successfully tested in both indoor and outdoor environments.", "source": "arxiv/ml"}
{"id": "arxiv:1106", "title": "Dynamic Matrix Factorization: A State Space Approach", "text": "Matrix factorization from a small number of observed entries has recently garnered much attention as the key ingredient of successful recommendation systems. One unresolved problem in this area is how to adapt current methods to handle changing user preferences over time. Recent proposals to address this issue are heuristic in nature and do not fully exploit the time-dependent structure of the problem. As a principled and general temporal formulation, we propose a dynamical state space model of matrix factorization. Our proposal builds upon probabilistic matrix factorization, a Bayesian model with Gaussian priors. We utilize results in state tracking, such as the Kalman filter, to provide accurate recommendations in the presence of both process and measurement noise. We show how system parameters can be learned via expectation-maximization and provide comparisons to current published techniques.", "source": "arxiv/ml"}
{"id": "arxiv:1107", "title": "Active Learning Using Smooth Relative Regret Approximations with Applications", "text": "The disagreement coefficient of Hanneke has become a central data independent invariant in proving active learning rates. It has been shown in various ways that a concept class with low complexity together with a bound on the disagreement coefficient at an optimal solution allows active learning rates that are superior to passive learning ones. We present a different tool for pool based active learning which follows from the existence of a certain uniform version of low disagreement coefficient, but is not equivalent to it. In fact, we present two fundamental active learning problems of significant interest for which our approach allows nontrivial active learning bounds. However, any general purpose method relying on the disagreement coefficient bounds only fails to guarantee any useful bounds for these problems. The tool we use is based on the learner's ability to compute an estimator of the difference between the loss of any hypotheses and some fixed \"pivotal\" hypothesis to within an absolute error of at most $\\eps$ times the", "source": "arxiv/ml"}
{"id": "arxiv:1108", "title": "Large-Margin Learning of Submodular Summarization Methods", "text": "In this paper, we present a supervised learning approach to training submodular scoring functions for extractive multi-document summarization. By taking a structured predicition approach, we provide a large-margin method that directly optimizes a convex relaxation of the desired performance measure. The learning method applies to all submodular summarization methods, and we demonstrate its effectiveness for both pairwise as well as coverage-based scoring functions on multiple datasets. Compared to state-of-the-art functions that were tuned manually, our method significantly improves performance and enables high-fidelity models with numbers of parameters well beyond what could reasonbly be tuned by hand.", "source": "arxiv/ml"}
{"id": "arxiv:1109", "title": "Learning Symbolic Models of Stochastic Domains", "text": "In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a probabilistic, relational planning rule representation that compactly models noisy, nondeterministic action effects, and show how such rules can be effectively learned. Through experiments in simple planning domains and a 3D simulated blocks world with realistic physics, we demonstrate that this learning algorithm allows agents to effectively model world dynamics.", "source": "arxiv/ml"}
{"id": "arxiv:1110", "title": "Ground Metric Learning", "text": "Transportation distances have been used for more than a decade now in machine learning to compare histograms of features. They have one parameter: the ground metric, which can be any metric between the features themselves. As is the case for all parameterized distances, transportation distances can only prove useful in practice when this parameter is carefully chosen. To date, the only option available to practitioners to set the ground metric parameter was to rely on a priori knowledge of the features, which limited considerably the scope of application of transportation distances. We propose to lift this limitation and consider instead algorithms that can learn the ground metric using only a training set of labeled histograms. We call this approach ground metric learning. We formulate the problem of learning the ground metric as the minimization of the difference of two polyhedral convex functions over a convex set of distance matrices. We follow the presentation of our algorithms with promising experimental results on binary classification tasks using GIST descriptors of images taken in the Caltech-256 set.", "source": "arxiv/ml"}
{"id": "arxiv:1111", "title": "A Variant of Azuma's Inequality for Martingales with Subgaussian Tails", "text": "We provide a variant of Azuma's concentration inequality for martingales, in which the standard boundedness requirement is replaced by the milder requirement of a subgaussian tail.", "source": "arxiv/ml"}
{"id": "arxiv:1112", "title": "Supervised learning of short and high-dimensional temporal sequences for life science measurements", "text": "The analysis of physiological processes over time are often given by spectrometric or gene expression profiles over time with only few time points but a large number of measured variables. The analysis of such temporal sequences is challenging and only few methods have been proposed. The information can be encoded time independent, by means of classical expression differences for a single time point or in expression profiles over time. Available methods are limited to unsupervised and semi-supervised settings. The predictive variables can be identified only by means of wrapper or post-processing techniques. This is complicated due to the small number of samples for such studies. Here, we present a supervised learning approach, termed Supervised Topographic Mapping Through Time (SGTM-TT). It learns a supervised mapping of the temporal sequences onto a low dimensional grid. We utilize a hidden markov model (HMM) to account for the time domain and relevance learning to identify the relevant feature dimensions most predictive over time. The learned mapping can be used to visualize the temporal sequences and to predict the class of a new sequence. The relevance learning permits the identification of discriminating masses or gen expressions and prunes dimensions which are unnecessary for the classification task or encode mainly noise. In this way we obtain a very efficient learning system for temporal sequences. The results indicate that using simultaneous supervised learning and metric adaptation significantly improves the prediction accuracy for synthetically and real life data in comparison to the standard techniques. The discriminating features, identified by relevance learning, compare favorably with the results of alternative methods. Our method permits the visualization of the data on a low dimensional grid, highlighting the observed temporal structure.", "source": "arxiv/ml"}
{"id": "arxiv:1113", "title": "The Generalization Ability of Online Algorithms for Dependent Data", "text": "We study the generalization performance of online learning algorithms trained on samples coming from a dependent source of data. We show that the generalization error of any stable online algorithm concentrates around its regret--an easily computable statistic of the online performance of the algorithm--when the underlying ergodic process is $\\beta$- or $\\phi$-mixing. We show high probability error bounds assuming the loss function is convex, and we also establish sharp convergence rates and deviation bounds for strongly convex losses and several linear prediction problems such as linear and logistic regression, least-squares SVM, and boosting on dependent data. In addition, our results have straightforward applications to stochastic optimization with dependent data, and our analysis requires only martingale convergence arguments; we need not rely on more powerful statistical tools such as empirical process theory.", "source": "arxiv/ml"}
{"id": "arxiv:1114", "title": "Issues,Challenges and Tools of Clustering Algorithms", "text": "Clustering is an unsupervised technique of Data Mining. It means grouping similar objects together and separating the dissimilar ones. Each object in the data set is assigned a class label in the clustering process using a distance measure. This paper has captured the problems that are faced in real when clustering algorithms are implemented .It also considers the most extensively used tools which are readily available and support functions which ease the programming. Once algorithms have been implemented, they also need to be tested for its validity. There exist several validation indexes for testing the performance and accuracy which have also been discussed here.", "source": "arxiv/ml"}
{"id": "arxiv:1115", "title": "Analysis of Heart Diseases Dataset using Neural Network Approach", "text": "One of the important techniques of Data mining is Classification. Many real world problems in various fields such as business, science, industry and medicine can be solved by using classification approach. Neural Networks have emerged as an important tool for classification. The advantages of Neural Networks helps for efficient classification of given data. In this study a Heart diseases dataset is analyzed using Neural Network approach. To increase the efficiency of the classification process parallel approach is also adopted in the training phase.", "source": "arxiv/ml"}
{"id": "arxiv:1116", "title": "Efficient Tracking of Large Classes of Experts", "text": "In the framework of prediction of individual sequences, sequential prediction methods are to be constructed that perform nearly as well as the best expert from a given class. We consider prediction strategies that compete with the class of switching strategies that can segment a given sequence into several blocks, and follow the advice of a different \"base\" expert in each block. As usual, the performance of the algorithm is measured by the regret defined as the excess loss relative to the best switching strategy selected in hindsight for the particular sequence to be predicted. In this paper we construct prediction strategies of low computational cost for the case where the set of base experts is large. In particular we provide a method that can transform any prediction algorithm $\\A$ that is designed for the base class into a tracking algorithm. The resulting tracking algorithm can take advantage of the prediction performance and potential computational efficiency of $\\A$ in the sense that it can be implemented with time and space complexity only $O(n^{\\gamma} \\ln n)$ times larger than that of $\\A$, where $n$ is the time horizon and $\\gamma \\ge 0$ is a parameter of the algorithm. With $\\A$ properly chosen, our algorithm achieves a regret bound of optimal order for $\\gamma>0$, and only $O(\\ln n)$ times larger than the optimal order for $\\gamma=0$ for all typical regret bound types we examined. For example, for predicting binary sequences with switching parameters under the logarithmic loss, our method achieves the optimal $O(\\ln n)$ regret rate with time complexity $O(n^{1+\\gamma}\\ln n)$ for any $\\gamma\\in (0,1)$.", "source": "arxiv/ml"}
{"id": "arxiv:1117", "title": "A tail inequality for quadratic forms of subgaussian random vectors", "text": "We prove an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vector has independent Gaussian entries.", "source": "arxiv/ml"}
{"id": "arxiv:1118", "title": "Sparse Image Representation with Epitomes", "text": "Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictionary, is learned to adapt to specific data. This approach has proven to be very effective in many image processing tasks. Traditionally, the dictionary is an unstructured \"flat\" set of atoms. In this paper, we study structured dictionaries which are obtained from an epitome, or a set of epitomes. The epitome is itself a small image, and the atoms are all the patches of a chosen size inside this image. This considerably reduces the number of parameters to learn and provides sparse image decompositions with shiftinvariance properties. We propose a new formulation and an algorithm for learning the structured dictionaries associated with epitomes, and illustrate their use in image denoising tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1119", "title": "Randomized Dimensionality Reduction for k-means Clustering", "text": "We study the topic of dimensionality reduction for $k$-means clustering. Dimensionality reduction encompasses the union of two approaches: \\emph{feature selection} and \\emph{feature extraction}. A feature selection based algorithm for $k$-means clustering selects a small subset of the input features and then applies $k$-means clustering on the selected features. A feature extraction based algorithm for $k$-means clustering constructs a small set of new artificial features and then applies $k$-means clustering on the constructed features. Despite the significance of $k$-means clustering as well as the wealth of heuristic methods addressing it, provably accurate feature selection methods for $k$-means clustering are not known. On the other hand, two provably accurate feature extraction methods for $k$-means clustering are known in the literature; one is based on random projections and the other is based on the singular value decomposition (SVD). This paper makes further progress towards a better understanding of dimensionality reduction for $k$-means clustering. Namely, we present the first provably accurate feature selection method for $k$-means clustering and, in addition, we present two feature extraction methods. The first feature extraction method is based on random projections and it improves upon the existing results in terms of time complexity and number of features needed to be extracted. The second feature extraction method is based on fast approximate SVD factorizations and it also improves upon the existing results in terms of time complexity. The proposed algorithms are randomized and provide constant-factor approximation guarantees with respect to the optimal $k$-means objective value.", "source": "arxiv/ml"}
{"id": "arxiv:1120", "title": "Discovering Emerging Topics in Social Streams via Link Anomaly Detection", "text": "Detection of emerging topics are now receiving renewed interest motivated by the rapid growth of social networks. Conventional term-frequency-based approaches may not be appropriate in this context, because the information exchanged are not only texts but also images, URLs, and videos. We focus on the social aspects of theses networks. That is, the links between users that are generated dynamically intentionally or unintentionally through replies, mentions, and retweets. We propose a probability model of the mentioning behaviour of a social network user, and propose to detect the emergence of a new topic from the anomaly measured through the model. We combine the proposed mention anomaly score with a recently proposed change-point detection technique based on the Sequentially Discounting Normalized Maximum Likelihood (SDNML), or with Kleinberg's burst model. Aggregating anomaly scores from hundreds of users, we show that we can detect emerging topics only based on the reply/mention relationships in social network posts. We demonstrate our technique in a number of real data sets we gathered from Twitter. The experiments show that the proposed mention-anomaly-based approaches can detect new topics at least as early as the conventional term-frequency-based approach, and sometimes much earlier when the keyword is ill-defined.", "source": "arxiv/ml"}
{"id": "arxiv:1121", "title": "Step size adaptation in first-order method for stochastic strongly convex programming", "text": "We propose a first-order method for stochastic strongly convex optimization that attains $O(1/n)$ rate of convergence, analysis show that the proposed method is simple, easily to implement, and in worst case, asymptotically four times faster than its peers. We derive this method from several intuitive observations that are generalized from existing first order optimization methods.", "source": "arxiv/ml"}
{"id": "arxiv:1122", "title": "Efficient Latent Variable Graphical Model Selection via Split Bregman Method", "text": "We consider the problem of covariance matrix estimation in the presence of latent variables. Under suitable conditions, it is possible to learn the marginal covariance matrix of the observed variables via a tractable convex program, where the concentration matrix of the observed variables is decomposed into a sparse matrix (representing the graphical structure of the observed variables) and a low rank matrix (representing the marginalization effect of latent variables). We present an efficient first-order method based on split Bregman to solve the convex problem. The algorithm is guaranteed to converge under mild conditions. We show that our algorithm is significantly faster than the state-of-the-art algorithm on both artificial and real-world data. Applying the algorithm to a gene expression data involving thousands of genes, we show that most of the correlation between observed variables can be explained by only a few dozen latent factors.", "source": "arxiv/ml"}
{"id": "arxiv:1123", "title": "Robust Image Analysis by L1-Norm Semi-supervised Learning", "text": "This paper presents a novel L1-norm semi-supervised learning algorithm for robust image analysis by giving new L1-norm formulation of Laplacian regularization which is the key step of graph-based semi-supervised learning. Since our L1-norm Laplacian regularization is defined directly over the eigenvectors of the normalized Laplacian matrix, we successfully formulate semi-supervised learning as an L1-norm linear reconstruction problem which can be effectively solved with sparse coding. By working with only a small subset of eigenvectors, we further develop a fast sparse coding algorithm for our L1-norm semi-supervised learning. Due to the sparsity induced by sparse coding, the proposed algorithm can deal with the noise in the data to some extent and thus has important applications to robust image analysis, such as noise-robust image classification and noise reduction for visual and textual bag-of-words (BOW) models. In particular, this paper is the first attempt to obtain robust image representation by sparse co-refinement of visual and textual BOW models. The experimental results have shown the promising performance of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1124", "title": "Improving parameter learning of Bayesian nets from incomplete data", "text": "This paper addresses the estimation of parameters of a Bayesian network from incomplete data. The task is usually tackled by running the Expectation-Maximization (EM) algorithm several times in order to obtain a high log-likelihood estimate. We argue that choosing the maximum log-likelihood estimate (as well as the maximum penalized log-likelihood and the maximum a posteriori estimate) has severe drawbacks, being affected both by overfitting and model uncertainty. Two ideas are discussed to overcome these issues: a maximum entropy approach and a Bayesian model averaging approach. Both ideas can be easily applied on top of EM, while the entropy idea can be also implemented in a more sophisticated way, through a dedicated non-linear solver. A vast set of experiments shows that these ideas produce significantly better estimates and inferences than the traditional and widely used maximum (penalized) log-likelihood and maximum a posteriori estimates. In particular, if EM is adopted as optimization engine, the model averaging approach is the best performing one; its performance is matched by the entropy approach when implemented using the non-linear solver. The results suggest that the applicability of these ideas is immediate (they are easy to implement and to integrate in currently available inference engines) and that they constitute a better way to learn Bayesian network parameters.", "source": "arxiv/ml"}
{"id": "arxiv:1125", "title": "Dynamic Batch Bayesian Optimization", "text": "Bayesian optimization (BO) algorithms try to optimize an unknown function that is expensive to evaluate using minimum number of evaluations/experiments. Most of the proposed algorithms in BO are sequential, where only one experiment is selected at each iteration. This method can be time inefficient when each experiment takes a long time and more than one experiment can be ran concurrently. On the other hand, requesting a fix-sized batch of experiments at each iteration causes performance inefficiency in BO compared to the sequential policies. In this paper, we present an algorithm that asks a batch of experiments at each time step t where the batch size p_t is dynamically determined in each step. Our algorithm is based on the observation that the sequence of experiments selected by the sequential policy can sometimes be almost independent from each other. Our algorithm identifies such scenarios and request those experiments at the same time without degrading the performance. We evaluate our proposed method using the Expected Improvement policy and the results show substantial speedup with little impact on the performance in eight real and synthetic benchmarks.", "source": "arxiv/ml"}
{"id": "arxiv:1126", "title": "Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems", "text": "Crowdsourcing systems, in which numerous tasks are electronically distributed to numerous \"information piece-workers\", have emerged as an effective paradigm for human-powered solving of large scale problems in domains such as image classification, data entry, optical character recognition, recommendation, and proofreading. Because these low-paid workers can be unreliable, nearly all such systems must devise schemes to increase confidence in their answers, typically by assigning each task multiple times and combining the answers in an appropriate manner, e.g. majority voting. In this paper, we consider a general model of such crowdsourcing tasks and pose the problem of minimizing the total price (i.e., number of task assignments) that must be paid to achieve a target overall reliability. We give a new algorithm for deciding which tasks to assign to which workers and for inferring correct answers from the workers' answers. We show that our algorithm, inspired by belief propagation and low-rank matrix approximation, significantly outperforms majority voting and, in fact, is optimal through comparison to an oracle that knows the reliability of every worker. Further, we compare our approach with a more general class of algorithms which can dynamically assign tasks. By adaptively deciding which questions to ask to the next arriving worker, one might hope to reduce uncertainty more efficiently. We show that, perhaps surprisingly, the minimum price necessary to achieve a target reliability scales in the same manner under both adaptive and non-adaptive scenarios. Hence, our non-adaptive approach is order-optimal under both scenarios. This strongly relies on the fact that workers are fleeting and can not be exploited. Therefore, architecturally, our results suggest that building a reliable worker-reputation system is essential to fully harnessing the potential of adaptive designs.", "source": "arxiv/ml"}
{"id": "arxiv:1127", "title": "Information, learning and falsification", "text": "There are (at least) three approaches to quantifying information. The first, algorithmic information or Kolmogorov complexity, takes events as strings and, given a universal Turing machine, quantifies the information content of a string as the length of the shortest program producing it. The second, Shannon information, takes events as belonging to ensembles and quantifies the information resulting from observing the given event in terms of the number of alternate events that have been ruled out. The third, statistical learning theory, has introduced measures of capacity that control (in part) the expected risk of classifiers. These capacities quantify the expectations regarding future data that learning algorithms embed into classifiers. This note describes a new method of quantifying information, effective information, that links algorithmic information to Shannon information, and also links both to capacities arising in statistical learning theory. After introducing the measure, we show that it provides a non-universal analog of Kolmogorov complexity. We then apply it to derive basic capacities in statistical learning theory: empirical VC-entropy and empirical Rademacher complexity. A nice byproduct of our approach is an interpretation of the explanatory power of a learning algorithm in terms of the number of hypotheses it falsifies, counted in two different ways for the two capacities. We also discuss how effective information relates to information gain, Shannon and mutual information.", "source": "arxiv/ml"}
{"id": "arxiv:1128", "title": "A critical evaluation of network and pathway based classifiers for outcome prediction in breast cancer", "text": "Recently, several classifiers that combine primary tumor data, like gene expression data, and secondary data sources, such as protein-protein interaction networks, have been proposed for predicting outcome in breast cancer. In these approaches, new composite features are typically constructed by aggregating the expression levels of several genes. The secondary data sources are employed to guide this aggregation. Although many studies claim that these approaches improve classification performance over single gene classifiers, the gain in performance is difficult to assess. This stems mainly from the fact that different breast cancer data sets and validation procedures are employed to assess the performance. Here we address these issues by employing a large cohort of six breast cancer data sets as benchmark set and by performing an unbiased evaluation of the classification accuracies of the different approaches. Contrary to previous claims, we find that composite feature classifiers do not outperform simple single gene classifiers. We investigate the effect of (1) the number of selected features; (2) the specific gene set from which features are selected; (3) the size of the training set and (4) the heterogeneity of the data set on the performance of composite feature and single gene classifiers. Strikingly, we find that randomization of secondary data sources, which destroys all biological information in these sources, does not result in a deterioration in performance of composite feature classifiers. Finally, we show that when a proper correction for gene set size is performed, the stability of single gene sets is similar to the stability of composite feature sets. Based on these results there is currently no reason to prefer prognostic classifiers based on composite features over single gene classifiers for predicting outcome in breast cancer.", "source": "arxiv/ml"}
{"id": "arxiv:1129", "title": "Multi-criteria Anomaly Detection using Pareto Depth Analysis", "text": "We consider the problem of identifying patterns in a data set that exhibit anomalous behavior, often referred to as anomaly detection. In most anomaly detection algorithms, the dissimilarity between data samples is calculated by a single criterion, such as Euclidean distance. However, in many cases there may not exist a single dissimilarity measure that captures all possible anomalous patterns. In such a case, multiple criteria can be defined, and one can test for anomalies by scalarizing the multiple criteria using a linear combination of them. If the importance of the different criteria are not known in advance, the algorithm may need to be executed multiple times with different choices of weights in the linear combination. In this paper, we introduce a novel non-parametric multi-criteria anomaly detection method using Pareto depth analysis (PDA). PDA uses the concept of Pareto optimality to detect anomalies under multiple criteria without having to run an algorithm multiple times with different choices of weights. The proposed PDA approach scales linearly in the number of criteria and is provably better than linear combinations of the criteria.", "source": "arxiv/ml"}
{"id": "arxiv:1130", "title": "How to Evaluate Dimensionality Reduction? - Improving the Co-ranking Matrix", "text": "The growing number of dimensionality reduction methods available for data visualization has recently inspired the development of quality assessment measures, in order to evaluate the resulting low-dimensional representation independently from a methods' inherent criteria. Several (existing) quality measures can be (re)formulated based on the so-called co-ranking matrix, which subsumes all rank errors (i.e. differences between the ranking of distances from every point to all others, comparing the low-dimensional representation to the original data). The measures are often based on the partioning of the co-ranking matrix into 4 submatrices, divided at the K-th row and column, calculating a weighted combination of the sums of each submatrix. Hence, the evaluation process typically involves plotting a graph over several (or even all possible) settings of the parameter K. Considering simple artificial examples, we argue that this parameter controls two notions at once, that need not necessarily be combined, and that the rectangular shape of submatrices is disadvantageous for an intuitive interpretation of the parameter. We debate that quality measures, as general and flexible evaluation tools, should have parameters with a direct and intuitive interpretation as to which specific error types are tolerated or penalized. Therefore, we propose to replace K with two parameters to control these notions separately, and introduce a differently shaped weighting on the co-ranking matrix. The two new parameters can then directly be interpreted as a threshold up to which rank errors are tolerated, and a threshold up to which the rank-distances are significant for the evaluation. Moreover, we propose a color representation of local quality to visually support the evaluation process for a given mapping, where every point in the mapping is colored according to its local contribution to the overall quality.", "source": "arxiv/ml"}
{"id": "arxiv:1131", "title": "Injecting External Solutions Into CMA-ES", "text": "This report considers how to inject external candidate solutions into the CMA-ES algorithm. The injected solutions might stem from a gradient or a Newton step, a surrogate model optimizer or any other oracle or search mechanism. They can also be the result of a repair mechanism, for example to render infeasible solutions feasible. Only small modifications to the CMA-ES are necessary to turn injection into a reliable and effective method: too long steps need to be tightly renormalized. The main objective of this report is to reveal this simple mechanism. Depending on the source of the injected solutions, interesting variants of CMA-ES arise. When the best-ever solution is always (re-)injected, an elitist variant of CMA-ES with weighted multi-recombination arises. When \\emph{all} solutions are injected from an \\emph{external} source, the resulting algorithm might be viewed as \\emph{adaptive encoding} with step-size control. In first experiments, injected solutions of very good quality lead to a convergence speed twice as fast as on the (simple) sphere function without injection. This means that we observe an impressive speed-up on otherwise difficult to solve functions. Single bad injected solutions on the other hand do no significant harm.", "source": "arxiv/ml"}
{"id": "arxiv:1132", "title": "A Reliable Effective Terascale Linear Learning System", "text": "We present a system and a set of techniques for learning linear predictors with convex losses on terascale datasets, with trillions of features, {The number of features here refers to the number of non-zero entries in the data matrix.} billions of training examples and millions of parameters in an hour using a cluster of 1000 machines. Individually none of the component techniques are new, but the careful synthesis required to obtain an efficient implementation is. The result is, up to our knowledge, the most scalable and efficient linear learning system reported in the literature (as of 2011 when our experiments were conducted). We describe and thoroughly evaluate the components of the system, showing the importance of the various design choices.", "source": "arxiv/ml"}
{"id": "arxiv:1133", "title": "An Optimal Algorithm for Linear Bandits", "text": "We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from convex geometry to construct what is essentially an optimal exploration basis. We also present an application to a model of linear bandits with expert advice. Interestingly, these results show that bandit linear optimization with expert advice in d dimensions is no more difficult (in terms of the achievable regret) than the online d-armed bandit problem with expert advice (where EXP4 is optimal).", "source": "arxiv/ml"}
{"id": "arxiv:1134", "title": "Aspiration Learning in Coordination Games", "text": "We consider the problem of distributed convergence to efficient outcomes in coordination games through dynamics based on aspiration learning. Under aspiration learning, a player continues to play an action as long as the rewards received exceed a specified aspiration level. Here, the aspiration level is a fading memory average of past rewards, and these levels also are subject to occasional random perturbations. A player becomes dissatisfied whenever a received reward is less than the aspiration level, in which case the player experiments with a probability proportional to the degree of dissatisfaction. Our first contribution is the characterization of the asymptotic behavior of the induced Markov chain of the iterated process in terms of an equivalent finite-state Markov chain. We then characterize explicitly the behavior of the proposed aspiration learning in a generalized version of coordination games, examples of which include network formation and common-pool games. In particular, we show that in generic coordination games the frequency at which an efficient action profile is played can be made arbitrarily large. Although convergence to efficient outcomes is desirable, in several coordination games, such as common-pool games, attainability of fair outcomes, i.e., sequences of plays at which players experience highly rewarding returns with the same frequency, might also be of special interest. To this end, we demonstrate through analysis and simulations that aspiration learning also establishes fair outcomes in all symmetric coordination games, including common-pool games.", "source": "arxiv/ml"}
{"id": "arxiv:1135", "title": "Data-dependent kernels in nearly-linear time", "text": "We propose a method to efficiently construct data-dependent kernels which can make use of large quantities of (unlabeled) data. Our construction makes an approximation in the standard construction of semi-supervised kernels in Sindhwani et al. 2005. In typical cases these kernels can be computed in nearly-linear time (in the amount of data), improving on the cubic time of the standard construction, enabling large scale semi-supervised learning in a variety of contexts. The methods are validated on semi-supervised and unsupervised problems on data sets containing upto 64,000 sample points.", "source": "arxiv/ml"}
{"id": "arxiv:1136", "title": "Learning Hierarchical and Topographic Dictionaries with Structured Sparsity", "text": "Recent work in signal processing and statistics have focused on defining new regularization functions, which not only induce sparsity of the solution, but also take into account the structure of the problem. We present in this paper a class of convex penalties introduced in the machine learning community, which take the form of a sum of l_2 and l_infinity-norms over groups of variables. They extend the classical group-sparsity regularization in the sense that the groups possibly overlap, allowing more flexibility in the group design. We review efficient optimization methods to deal with the corresponding inverse problems, and their application to the problem of learning dictionaries of natural image patches: On the one hand, dictionary learning has indeed proven effective for various signal processing tasks. On the other hand, structured sparsity provides a natural framework for modeling dependencies between dictionary elements. We thus consider a structured sparse regularization to learn dictionaries embedded in a particular structure, for instance a tree or a two-dimensional grid. In the latter case, the results we obtain are similar to the dictionaries produced by topographic independent component analysis.", "source": "arxiv/ml"}
{"id": "arxiv:1137", "title": "Kernel Topic Models", "text": "Latent Dirichlet Allocation models discrete data as a mixture of discrete distributions, using Dirichlet beliefs over the mixture weights. We study a variation of this concept, in which the documents' mixture weight beliefs are replaced with squashed Gaussian distributions. This allows documents to be associated with elements of a Hilbert space, admitting kernel topic models (KTM), modelling temporal, spatial, hierarchical, social and other structure between documents. The main challenge is efficient approximate inference on the latent Gaussian. We present an approximate algorithm cast around a Laplace approximation in a transformed basis. The KTM can also be interpreted as a type of Gaussian process latent variable model, or as a topic model conditional on document features, uncovering links between earlier work in these areas.", "source": "arxiv/ml"}
{"id": "arxiv:1138", "title": "Web search queries can predict stock market volumes", "text": "We live in a computerized and networked society where many of our actions leave a digital trace and affect other people's actions. This has lead to the emergence of a new data-driven research field: mathematical methods of computer science, statistical physics and sociometry provide insights on a wide range of disciplines ranging from social science to human mobility. A recent important discovery is that query volumes (i.e., the number of requests submitted by users to search engines on the www) can be used to track and, in some cases, to anticipate the dynamics of social phenomena. Successful exemples include unemployment levels, car and home sales, and epidemics spreading. Few recent works applied this approach to stock prices and market sentiment. However, it remains unclear if trends in financial markets can be anticipated by the collective wisdom of on-line users on the web. Here we show that trading volumes of stocks traded in NASDAQ-100 are correlated with the volumes of queries related to the same stocks. In particular, query volumes anticipate in many cases peaks of trading by one day or more. Our analysis is carried out on a unique dataset of queries, submitted to an important web search engine, which enable us to investigate also the user behavior. We show that the query volume dynamics emerges from the collective but seemingly uncoordinated activity of many users. These findings contribute to the debate on the identification of early warnings of financial systemic risk, based on the activity of users of the www.", "source": "arxiv/ml"}
{"id": "arxiv:1139", "title": "Wikipedia Edit Number Prediction based on Temporal Dynamics Only", "text": "In this paper, we describe our approach to the Wikipedia Participation Challenge which aims to predict the number of edits a Wikipedia editor will make in the next 5 months. The best submission from our team, \"zeditor\", achieved 41.7% improvement over WMF's baseline predictive model and the final rank of 3rd place among 96 teams. An interesting characteristic of our approach is that only temporal dynamics features (i.e., how the number of edits changes in recent periods, etc.) are used in a self-supervised learning framework, which makes it easy to be generalised to other application domains.", "source": "arxiv/ml"}
{"id": "arxiv:1140", "title": "Quilting Stochastic Kronecker Product Graphs to Generate Multiplicative Attribute Graphs", "text": "We describe the first sub-quadratic sampling algorithm for the Multiplicative Attribute Graph Model (MAGM) of Kim and Leskovec (2010). We exploit the close connection between MAGM and the Kronecker Product Graph Model (KPGM) of Leskovec et al. (2010), and show that to sample a graph from a MAGM it suffices to sample small number of KPGM graphs and \\emph{quilt} them together. Under a restricted set of technical conditions our algorithm runs in $O((\\log_2(n))^3 |E|)$ time, where $n$ is the number of nodes and $|E|$ is the number of edges in the sampled graph. We demonstrate the scalability of our algorithm via extensive empirical evaluation; we can sample a MAGM graph with 8 million nodes and 20 billion edges in under 6 hours.", "source": "arxiv/ml"}
{"id": "arxiv:1141", "title": "Optimal discovery with probabilistic expert advice", "text": "We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and the Good-Turing missing mass estimator. We show that this strategy uniformly attains the optimal discovery rate in a macroscopic limit sense, under some assumptions on the probabilistic experts. We also provide numerical experiments suggesting that this optimal behavior may still hold under weaker assumptions.", "source": "arxiv/ml"}
{"id": "arxiv:1142", "title": "Inducing Probabilistic Programs by Bayesian Program Merging", "text": "This report outlines an approach to learning generative models from data. We express models as probabilistic programs, which allows us to capture abstract patterns within the examples. By choosing our language for programs to be an extension of the algebraic data type of the examples, we can begin with a program that generates all and only the examples. We then introduce greater abstraction, and hence generalization, incrementally to the extent that it improves the posterior probability of the examples given the program. Motivated by previous approaches to model merging and program induction, we search for such explanatory abstractions using program transformations. We consider two types of transformation: Abstraction merges common subexpressions within a program into new functions (a form of anti-unification). Deargumentation simplifies functions by reducing the number of arguments. We demonstrate that this approach finds key patterns in the domain of nested lists, including parameterized sub-functions and stochastic recursion.", "source": "arxiv/ml"}
{"id": "arxiv:1143", "title": "Discussion on \"Techniques for Massive-Data Machine Learning in Astronomy\" by A. Gray", "text": "Astronomy is increasingly encountering two fundamental truths: (1) The field is faced with the task of extracting useful information from extremely large, complex, and high dimensional datasets; (2) The techniques of astroinformatics and astrostatistics are the only way to make this tractable, and bring the required level of sophistication to the analysis. Thus, an approach which provides these tools in a way that scales to these datasets is not just desirable, it is vital. The expertise required spans not just astronomy, but also computer science, statistics, and informatics. As a computer scientist and expert in machine learning, Alex's contribution of expertise and a large number of fast algorithms designed to scale to large datasets, is extremely welcome. We focus in this discussion on the questions raised by the practical application of these algorithms to real astronomical datasets. That is, what is needed to maximally leverage their potential to improve the science return? This is not a trivial task. While computing and statistical expertise are required, so is astronomical expertise. Precedent has shown that, to-date, the collaborations most productive in producing astronomical science results (e.g, the Sloan Digital Sky Survey), have either involved astronomers expert in computer science and/or statistics, or astronomers involved in close, long-term collaborations with experts in those fields. This does not mean that the astronomers are giving the most important input, but simply that their input is crucial in guiding the effort in the most fruitful directions, and coping with the issues raised by real data. Thus, the tools must be useable and understandable by those whose primary expertise is not computing or statistics, even though they may have quite extensive knowledge of those fields.", "source": "arxiv/ml"}
{"id": "arxiv:1144", "title": "The multi-armed bandit problem with covariates", "text": "We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate. As opposed to the traditional static multi-armed bandit problem, this setting allows for dynamically changing rewards that better describe applications where side information is available. We adopt a nonparametric model where the expected rewards are smooth functions of the covariate and where the hardness of the problem is captured by a margin parameter. To maximize the expected cumulative reward, we introduce a policy called Adaptively Binned Successive Elimination (abse) that adaptively decomposes the global problem into suitably \"localized\" static bandit problems. This policy constructs an adaptive partition using a variant of the Successive Elimination (se) policy. Our results include sharper regret bounds for the se policy in a static bandit problem and minimax optimal regret bounds for the abse policy in the dynamic problem.", "source": "arxiv/ml"}
{"id": "arxiv:1145", "title": "Deciding of HMM parameters based on number of critical points for gesture recognition from motion capture data", "text": "This paper presents a method of choosing number of states of a HMM based on number of critical points of the motion capture data. The choice of Hidden Markov Models(HMM) parameters is crucial for recognizer's performance as it is the first step of the training and cannot be corrected automatically within HMM. In this article we define predictor of number of states based on number of critical points of the sequence and test its effectiveness against sample data.", "source": "arxiv/ml"}
{"id": "arxiv:1146", "title": "PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits", "text": "We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The first ingredient is a new concentration inequality that makes it possible to control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. The second ingredient is an application of this inequality to the exploration-exploitation trade-off via importance weighted sampling. We apply the new tool to the stochastic multiarmed bandit problem, however, the main importance of this paper is the development and understanding of the new tool rather than improvement of existing algorithms for stochastic multiarmed bandits. In the follow-up work we demonstrate that the new tool can improve over state-of-the-art in structurally richer problems, such as stochastic multiarmed bandits with side information (Seldin et al., 2011a).", "source": "arxiv/ml"}
{"id": "arxiv:1147", "title": "PAC-Bayesian Inequalities for Martingales", "text": "We present a set of high-probability inequalities that control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. Our results extend the PAC-Bayesian analysis in learning theory from the i.i.d. setting to martingales opening the way for its application to importance weighted sampling, reinforcement learning, and other interactive learning domains, as well as many other domains in probability theory and statistics, where martingales are encountered. We also present a comparison inequality that bounds the expectation of a convex function of a martingale difference sequence shifted to the [0,1] interval by the expectation of the same function of independent Bernoulli variables. This inequality is applied to derive a tighter analog of Hoeffding-Azuma's inequality.", "source": "arxiv/ml"}
{"id": "arxiv:1148", "title": "Text-Independent Speaker Recognition for Low SNR Environments with Encryption", "text": "Recognition systems are commonly designed to authenticate users at the access control levels of a system. A number of voice recognition methods have been developed using a pitch estimation process which are very vulnerable in low Signal to Noise Ratio (SNR) environments thus, these programs fail to provide the desired level of accuracy and robustness. Also, most text independent speaker recognition programs are incapable of coping with unauthorized attempts to gain access by tampering with the samples or reference database. The proposed text-independent voice recognition system makes use of multilevel cryptography to preserve data integrity while in transit or storage. Encryption and decryption follow a transform based approach layered with pseudorandom noise addition whereas for pitch detection, a modified version of the autocorrelation pitch extraction algorithm is used. The experimental results show that the proposed algorithm can decrypt the signal under test with exponentially reducing Mean Square Error over an increasing range of SNR. Further, it outperforms the conventional algorithms in actual identification tasks even in noisy environments. The recognition rate thus obtained using the proposed method is compared with other conventional methods used for speaker identification.", "source": "arxiv/ml"}
{"id": "arxiv:1149", "title": "Diffusion Adaptation Strategies for Distributed Optimization and Learning over Networks", "text": "We propose an adaptive diffusion mechanism to optimize a global cost function in a distributed manner over a network of nodes. The cost function is assumed to consist of a collection of individual components. Diffusion adaptation allows the nodes to cooperate and diffuse information in real-time; it also helps alleviate the effects of stochastic gradient noise and measurement noise through a continuous learning process. We analyze the mean-square-error performance of the algorithm in some detail, including its transient and steady-state behavior. We also apply the diffusion algorithm to two problems: distributed estimation with sparse parameters and distributed localization. Compared to well-studied incremental methods, diffusion methods do not require the use of a cyclic path over the nodes and are robust to node and link failure. Diffusion methods also endow networks with adaptation abilities that enable the individual nodes to continue learning even when the cost function changes with time. Examples involving such dynamic cost functions with moving targets are common in the context of biological networks.", "source": "arxiv/ml"}
{"id": "arxiv:1150", "title": "Revisiting k-means: New Algorithms via Bayesian Nonparametrics", "text": "Bayesian models offer great flexibility for clustering applications---Bayesian nonparametrics can be used for modeling infinite mixtures, and hierarchical Bayesian models can be utilized for sharing clusters across multiple data sets. For the most part, such flexibility is lacking in classical clustering methods such as k-means. In this paper, we revisit the k-means clustering algorithm from a Bayesian nonparametric viewpoint. Inspired by the asymptotic connection between k-means and mixtures of Gaussians, we show that a Gibbs sampling algorithm for the Dirichlet process mixture approaches a hard clustering algorithm in the limit, and further that the resulting algorithm monotonically minimizes an elegant underlying k-means-like clustering objective that includes a penalty for the number of clusters. We generalize this analysis to the case of clustering multiple data sets through a similar asymptotic argument with the hierarchical Dirichlet process. We also discuss further extensions that highlight the benefits of our analysis: i) a spectral relaxation involving thresholded eigenvectors, and ii) a normalized cut graph clustering algorithm that does not fix the number of clusters in the graph.", "source": "arxiv/ml"}
{"id": "arxiv:1151", "title": "Approximate Stochastic Subgradient Estimation Training for Support Vector Machines", "text": "Subgradient algorithms for training support vector machines have been quite successful for solving large-scale and online learning problems. However, they have been restricted to linear kernels and strongly convex formulations. This paper describes efficient subgradient approaches without such limitations. Our approaches make use of randomized low-dimensional approximations to nonlinear kernels, and minimization of a reduced primal formulation using an algorithm based on robust stochastic approximation, which do not require strong convexity. Experiments illustrate that our approaches produce solutions of comparable prediction accuracy with the solutions acquired from existing SVM solvers, but often in much shorter time. We also suggest efficient prediction schemes that depend only on the dimension of kernel approximation, not on the number of support vectors.", "source": "arxiv/ml"}
{"id": "arxiv:1152", "title": "Online Learning with Preference Feedback", "text": "We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback (e.g. clicks). In particular, at each time step a potentially structured object (e.g. a ranking) is presented to the user in response to a context (e.g. query), providing him or her with some unobserved amount of utility. As feedback the algorithm receives an improved object that would have provided higher utility. We propose a learning algorithm with provable regret bounds for this online learning setting and demonstrate its effectiveness on a web-search application. The new learning model also applies to many other interactive learning problems and admits several interesting extensions.", "source": "arxiv/ml"}
{"id": "arxiv:1153", "title": "Computing a Nonnegative Matrix Factorization -- Provably", "text": "In the Nonnegative Matrix Factorization (NMF) problem we are given an $n \\times m$ nonnegative matrix $M$ and an integer $r > 0$. Our goal is to express $M$ as $A W$ where $A$ and $W$ are nonnegative matrices of size $n \\times r$ and $r \\times m$ respectively. In some applications, it makes sense to ask instead for the product $AW$ to approximate $M$ -- i.e. (approximately) minimize $\\norm{M - AW}_F$ where $\\norm{}_F$ denotes the Frobenius norm; we refer to this as Approximate NMF. This problem has a rich history spanning quantum mechanics, probability theory, data analysis, polyhedral combinatorics, communication complexity, demography, chemometrics, etc. In the past decade NMF has become enormously popular in machine learning, where $A$ and $W$ are computed using a variety of local search heuristics. Vavasis proved that this problem is NP-complete. We initiate a study of when this problem is solvable in polynomial time: 1. We give a polynomial-time algorithm for exact and approximate NMF for every constant $r$. Indeed NMF is most interesting in applications precisely when $r$ is small. 2. We complement this with a hardness result, that if exact NMF can be solved in time $(nm)^{o(r)}$, 3-SAT has a sub-exponential time algorithm. This rules out substantial improvements to the above algorithm. 3. We give an algorithm that runs in time polynomial in $n$, $m$ and $r$ under the separablity condition identified by Donoho and Stodden in 2003. The algorithm may be practical since it is simple and noise tolerant (under benign assumptions). Separability is believed to hold in many practical settings. To the best of our knowledge, this last result is the first example of a polynomial-time algorithm that provably works under a non-trivial condition on the input and we believe that this will be an interesting and important direction for future work.", "source": "arxiv/ml"}
{"id": "arxiv:1154", "title": "Tight Bounds on Proper Equivalence Query Learning of DNF", "text": "We prove a new structural lemma for partial Boolean functions $f$, which we call the seed lemma for DNF. Using the lemma, we give the first subexponential algorithm for proper learning of DNF in Angluin's Equivalence Query (EQ) model. The algorithm has time and query complexity $2^{(\\tilde{O}{\\sqrt{n}})}$, which is optimal. We also give a new result on certificates for DNF-size, a simple algorithm for properly PAC-learning DNF, and new results on EQ-learning $\\log n$-term DNF and decision trees.", "source": "arxiv/ml"}
{"id": "arxiv:1155", "title": "Universal MMSE Filtering With Logarithmic Adaptive Regret", "text": "We consider the problem of online estimation of a real-valued signal corrupted by oblivious zero-mean noise using linear estimators. The estimator is required to iteratively predict the underlying signal based on the current and several last noisy observations, and its performance is measured by the mean-square-error. We describe and analyze an algorithm for this task which: 1. Achieves logarithmic adaptive regret against the best linear filter in hindsight. This bound is assyptotically tight, and resolves the question of Moon and Weissman [1]. 2. Runs in linear time in terms of the number of filter coefficients. Previous constructions required at least quadratic time.", "source": "arxiv/ml"}
{"id": "arxiv:1156", "title": "Nonparametric Bayesian Estimation of Periodic Functions", "text": "Many real world problems exhibit patterns that have periodic behavior. For example, in astrophysics, periodic variable stars play a pivotal role in understanding our universe. An important step when analyzing data from such processes is the problem of identifying the period: estimating the period of a periodic function based on noisy observations made at irregularly spaced time points. This problem is still a difficult challenge despite extensive study in different disciplines. The paper makes several contributions toward solving this problem. First, we present a nonparametric Bayesian model for period finding, based on Gaussian Processes (GP), that does not make strong assumptions on the shape of the periodic function. As our experiments demonstrate, the new model leads to significantly better results in period estimation when the target function is non-sinusoidal. Second, we develop a new algorithm for parameter optimization for GP which is useful when the likelihood function is very sensitive to the setting of the hyper-parameters with numerous local minima, as in the case of period estimation. The algorithm combines gradient optimization with grid search and incorporates several mechanisms to overcome the high complexity of inference with GP. Third, we develop a novel approach for using domain knowledge, in the form of a probabilistic generative model, and incorporate it into the period estimation algorithm. Experimental results on astrophysics data validate our approach showing significant improvement over the state of the art in this domain.", "source": "arxiv/ml"}
{"id": "arxiv:1157", "title": "Confidence Estimation in Structured Prediction", "text": "Structured classification tasks such as sequence labeling and dependency parsing have seen much interest by the Natural Language Processing and the machine learning communities. Several online learning algorithms were adapted for structured tasks such as Perceptron, Passive- Aggressive and the recently introduced Confidence-Weighted learning . These online algorithms are easy to implement, fast to train and yield state-of-the-art performance. However, unlike probabilistic models like Hidden Markov Model and Conditional random fields, these methods generate models that output merely a prediction with no additional information regarding confidence in the correctness of the output. In this work we fill the gap proposing few alternatives to compute the confidence in the output of non-probabilistic algorithms.We show how to compute confidence estimates in the prediction such that the confidence reflects the probability that the word is labeled correctly. We then show how to use our methods to detect mislabeled words, trade recall for precision and active learning. We evaluate our methods on four noun-phrase chunking and named entity recognition sequence labeling tasks, and on dependency parsing for 14 languages.", "source": "arxiv/ml"}
{"id": "arxiv:1158", "title": "Efficient Nonparametric Conformal Prediction Regions", "text": "We investigate and extend the conformal prediction method due to Vovk,Gammerman and Shafer (2005) to construct nonparametric prediction regions. These regions have guaranteed distribution free, finite sample coverage, without any assumptions on the distribution or the bandwidth. Explicit convergence rates of the loss function are established for such regions under standard regularity conditions. Approximations for simplifying implementation and data driven bandwidth selection methods are also discussed. The theoretical properties of our method are demonstrated through simulations.", "source": "arxiv/ml"}
{"id": "arxiv:1159", "title": "Robust Interactive Learning", "text": "In this paper we propose and study a generalization of the standard active-learning model where a more general type of query, class conditional query, is allowed. Such queries have been quite useful in applications, but have been lacking theoretical understanding. In this work, we characterize the power of such queries under two well-known noise models. We give nearly tight upper and lower bounds on the number of queries needed to learn both for the general agnostic setting and for the bounded noise model. We further show that our methods can be made adaptive to the (unknown) noise rate, with only negligible loss in query complexity.", "source": "arxiv/ml"}
{"id": "arxiv:1160", "title": "UPAL: Unbiased Pool Based Active Learning", "text": "In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of linear classifiers and the squared loss we show that UPAL is equivalent to an exponentially weighted average forecaster. Exploiting some recent results regarding the spectra of random matrices allows us to establish consistency of UPAL when the true hypothesis is a linear hypothesis. Empirical comparison with an active learner implementation in Vowpal Wabbit, and a previously proposed pool based active learner implementation show good empirical performance and better scalability.", "source": "arxiv/ml"}
{"id": "arxiv:1161", "title": "Analysis of Thompson Sampling for the multi-armed bandit problem", "text": "The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W. R. Thompson, dates back to 1933. This algorithm, referred to as Thompson Sampling, is a natural Bayesian algorithm. The basic idea is to choose an arm to play according to its probability of being the best arm. Thompson Sampling algorithm has experimentally been shown to be close to optimal. In addition, it is efficient to implement and exhibits several desirable properties such as small regret for delayed feedback. However, theoretical understanding of this algorithm was quite limited. In this paper, for the first time, we show that Thompson Sampling algorithm achieves logarithmic expected regret for the multi-armed bandit problem. More precisely, for the two-armed bandit problem, the expected regret in time $T$ is $O(\\frac{\\ln T}{\\Delta} + \\frac{1}{\\Delta^3})$. And, for the $N$-armed bandit problem, the expected regret in time $T$ is $O([(\\sum_{i=2}^N \\frac{1}{\\Delta_i^2})^2] \\ln T)$. Our bounds are optimal but for the dependence on $\\Delta_i$ and the constant factors in big-Oh.", "source": "arxiv/ml"}
{"id": "arxiv:1162", "title": "Pushing Your Point of View: Behavioral Measures of Manipulation in Wikipedia", "text": "As a major source for information on virtually any topic, Wikipedia serves an important role in public dissemination and consumption of knowledge. As a result, it presents tremendous potential for people to promulgate their own points of view; such efforts may be more subtle than typical vandalism. In this paper, we introduce new behavioral metrics to quantify the level of controversy associated with a particular user: a Controversy Score (C-Score) based on the amount of attention the user focuses on controversial pages, and a Clustered Controversy Score (CC-Score) that also takes into account topical clustering. We show that both these measures are useful for identifying people who try to \"push\" their points of view, by showing that they are good predictors of which editors get blocked. The metrics can be used to triage potential POV pushers. We apply this idea to a dataset of users who requested promotion to administrator status and easily identify some editors who significantly changed their behavior upon becoming administrators. At the same time, such behavior is not rampant. Those who are promoted to administrator status tend to have more stable behavior than comparable groups of prolific editors. This suggests that the Adminship process works well, and that the Wikipedia community is not overwhelmed by users who become administrators to promote their own points of view.", "source": "arxiv/ml"}
{"id": "arxiv:1163", "title": "Generic Multiplicative Methods for Implementing Machine Learning Algorithms on MapReduce", "text": "In this paper we introduce a generic model for multiplicative algorithms which is suitable for the MapReduce parallel programming paradigm. We implement three typical machine learning algorithms to demonstrate how similarity comparison, gradient descent, power method and other classic learning techniques fit this model well. Two versions of large-scale matrix multiplication are discussed in this paper, and different methods are developed for both cases with regard to their unique computational characteristics and problem settings. In contrast to earlier research, we focus on fundamental linear algebra techniques that establish a generic approach for a range of algorithms, rather than specific ways of scaling up algorithms one at a time. Experiments show promising results when evaluated on both speedup and accuracy. Compared with a standard implementation with computational complexity $O(m^3)$ in the worst case, the large-scale matrix multiplication experiments prove our design is considerably more efficient and maintains a good speedup as the number of cores increases. Algorithm-specific experiments also produce encouraging results on runtime performance.", "source": "arxiv/ml"}
{"id": "arxiv:1164", "title": "Scaling Up Estimation of Distribution Algorithms For Continuous Optimization", "text": "Since Estimation of Distribution Algorithms (EDA) were proposed, many attempts have been made to improve EDAs' performance in the context of global optimization. So far, the studies or applications of multivariate probabilistic model based continuous EDAs are still restricted to rather low dimensional problems (smaller than 100D). Traditional EDAs have difficulties in solving higher dimensional problems because of the curse of dimensionality and their rapidly increasing computational cost. However, scaling up continuous EDAs for higher dimensional optimization is still necessary, which is supported by the distinctive feature of EDAs: Because a probabilistic model is explicitly estimated, from the learnt model one can discover useful properties or features of the problem. Besides obtaining a good solution, understanding of the problem structure can be of great benefit, especially for black box optimization. We propose a novel EDA framework with Model Complexity Control (EDA-MCC) to scale up EDAs. By using Weakly dependent variable Identification (WI) and Subspace Modeling (SM), EDA-MCC shows significantly better performance than traditional EDAs on high dimensional problems. Moreover, the computational cost and the requirement of large population sizes can be reduced in EDA-MCC. In addition to being able to find a good solution, EDA-MCC can also produce a useful problem structure characterization. EDA-MCC is the first successful instance of multivariate model based EDAs that can be effectively applied a general class of up to 500D problems. It also outperforms some newly developed algorithms designed specifically for large scale optimization. In order to understand the strength and weakness of EDA-MCC, we have carried out extensive computational studies of EDA-MCC. Our results have revealed when EDA-MCC is likely to outperform others on what kind of benchmark functions.", "source": "arxiv/ml"}
{"id": "arxiv:1165", "title": "Improved Bound for the Nystrom's Method and its Application to Kernel Classification", "text": "We develop two approaches for analyzing the approximation error bound for the Nystr\\\"{o}m method, one based on the concentration inequality of integral operator, and one based on the compressive sensing theory. We show that the approximation error, measured in the spectral norm, can be improved from $O(N/\\sqrt{m})$ to $O(N/m^{1 - \\rho})$ in the case of large eigengap, where $N$ is the total number of data points, $m$ is the number of sampled data points, and $\\rho \\in (0, 1/2)$ is a positive constant that characterizes the eigengap. When the eigenvalues of the kernel matrix follow a $p$-power law, our analysis based on compressive sensing theory further improves the bound to $O(N/m^{p - 1})$ under an incoherence assumption, which explains why the Nystr\\\"{o}m method works well for kernel matrix with skewed eigenvalues. We present a kernel classification approach based on the Nystr\\\"{o}m method and derive its generalization performance using the improved bound. We show that when the eigenvalues of kernel matrix follow a $p$-power law, we can reduce the number of support vectors to $N^{2p/(p^2 - 1)}$, a number less than $N$ when $p > 1+\\sqrt{2}$, without seriously sacrificing its generalization performance.", "source": "arxiv/ml"}
{"id": "arxiv:1166", "title": "A Collaborative Mechanism for Crowdsourcing Prediction Problems", "text": "Machine Learning competitions such as the Netflix Prize have proven reasonably successful as a method of \"crowdsourcing\" prediction tasks. But these competitions have a number of weaknesses, particularly in the incentive structure they create for the participants. We propose a new approach, called a Crowdsourced Learning Mechanism, in which participants collaboratively \"learn\" a hypothesis for a given prediction task. The approach draws heavily from the concept of a prediction market, where traders bet on the likelihood of a future event. In our framework, the mechanism continues to publish the current hypothesis, and participants can modify this hypothesis by wagering on an update. The critical incentive property is that a participant will profit an amount that scales according to how much her update improves performance on a released test set.", "source": "arxiv/ml"}
{"id": "arxiv:1167", "title": "Using Contextual Information as Virtual Items on Top-N Recommender Systems", "text": "Traditionally, recommender systems for the Web deal with applications that have two dimensions, users and items. Based on access logs that relate these dimensions, a recommendation model can be built and used to identify a set of N items that will be of interest to a certain user. In this paper we propose a method to complement the information in the access logs with contextual information without changing the recommendation algorithm. The method consists in representing context as virtual items. We empirically test this method with two top-N recommender systems, an item-based collaborative filtering technique and association rules, on three data sets. The results show that our method is able to take advantage of the context (new dimensions) when it is informative.", "source": "arxiv/ml"}
{"id": "arxiv:1168", "title": "A Bayesian Model for Plan Recognition in RTS Games applied to StarCraft", "text": "The task of keyhole (unobtrusive) plan recognition is central to adaptive game AI. \"Tech trees\" or \"build trees\" are the core of real-time strategy (RTS) game strategic (long term) planning. This paper presents a generic and simple Bayesian model for RTS build tree prediction from noisy observations, which parameters are learned from replays (game logs). This unsupervised machine learning approach involves minimal work for the game developers as it leverage players' data (com- mon in RTS). We applied it to StarCraft1 and showed that it yields high quality and robust predictions, that can feed an adaptive AI.", "source": "arxiv/ml"}
{"id": "arxiv:1169", "title": "No Free Lunch versus Occam's Razor in Supervised Learning", "text": "The No Free Lunch theorems are often used to argue that domain specific knowledge is required to design successful algorithms. We use algorithmic information theory to argue the case for a universal bias allowing an algorithm to succeed in all interesting problem domains. Additionally, we give a new algorithm for off-line classification, inspired by Solomonoff induction, with good performance on all structured problems under reasonable assumptions. This includes a proof of the efficacy of the well-known heuristic of randomly selecting training data in the hope of reducing misclassification rates.", "source": "arxiv/ml"}
{"id": "arxiv:1170", "title": "Sequential search based on kriging: convergence analysis of some algorithms", "text": "Let $\\FF$ be a set of real-valued functions on a set $\\XX$ and let $S:\\FF \\to \\GG$ be an arbitrary mapping. We consider the problem of making inference about $S(f)$, with $f\\in\\FF$ unknown, from a finite set of pointwise evaluations of $f$. We are mainly interested in the problems of approximation and optimization. In this article, we make a brief review of results concerning average error bounds of Bayesian search methods that use a random process prior about $f$.", "source": "arxiv/ml"}
{"id": "arxiv:1171", "title": "The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo", "text": "Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) algorithm that avoids the random walk behavior and sensitivity to correlated parameters that plague many MCMC methods by taking a series of steps informed by first-order gradient information. These features allow it to converge to high-dimensional target distributions much more quickly than simpler methods such as random walk Metropolis or Gibbs sampling. However, HMC's performance is highly sensitive to two user-specified parameters: a step size {\\epsilon} and a desired number of steps L. In particular, if L is too small then the algorithm exhibits undesirable random walk behavior, while if L is too large the algorithm wastes computation. We introduce the No-U-Turn Sampler (NUTS), an extension to HMC that eliminates the need to set a number of steps L. NUTS uses a recursive algorithm to build a set of likely candidate points that spans a wide swath of the target distribution, stopping automatically when it starts to double back and retrace its steps. Empirically, NUTS perform at least as efficiently as and sometimes more efficiently than a well tuned standard HMC method, without requiring user intervention or costly tuning runs. We also derive a method for adapting the step size parameter {\\epsilon} on the fly based on primal-dual averaging. NUTS can thus be used with no hand-tuning at all. NUTS is also suitable for applications such as BUGS-style automatic inference engines that require efficient \"turnkey\" sampling algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1172", "title": "Parametrized Stochastic Multi-armed Bandits with Binary Rewards", "text": "In this paper, we consider the problem of multi-armed bandits with a large, possibly infinite number of correlated arms. We assume that the arms have Bernoulli distributed rewards, independent across time, where the probabilities of success are parametrized by known attribute vectors for each arm, as well as an unknown preference vector, each of dimension $n$. For this model, we seek an algorithm with a total regret that is sub-linear in time and independent of the number of arms. We present such an algorithm, which we call the Two-Phase Algorithm, and analyze its performance. We show upper bounds on the total regret which applies uniformly in time, for both the finite and infinite arm cases. The asymptotics of the finite arm bound show that for any $f \\in \\omega(\\log(T))$, the total regret can be made to be $O(n \\cdot f(T))$. In the infinite arm case, the total regret is $O(\\sqrt{n^3 T})$.", "source": "arxiv/ml"}
{"id": "arxiv:1173", "title": "Efficient Regression in Metric Spaces via Approximate Lipschitz Extension", "text": "We present a framework for performing efficient regression in general metric spaces. Roughly speaking, our regressor predicts the value at a new point by computing a Lipschitz extension --- the smoothest function consistent with the observed data --- after performing structural risk minimization to avoid overfitting. We obtain finite-sample risk bounds with minimal structural and noise assumptions, and a natural speed-precision tradeoff. The offline (learning) and online (prediction) stages can be solved by convex programming, but this naive approach has runtime complexity $O(n^3)$, which is prohibitive for large datasets. We design instead a regression algorithm whose speed and generalization performance depend on the intrinsic dimension of the data, to which the algorithm adapts. While our main innovation is algorithmic, the statistical results may also be of independent interest.", "source": "arxiv/ml"}
{"id": "arxiv:1174", "title": "Large Scale Spectral Clustering Using Approximate Commute Time Embedding", "text": "Spectral clustering is a novel clustering method which can detect complex shapes of data clusters. However, it requires the eigen decomposition of the graph Laplacian matrix, which is proportion to $O(n^3)$ and thus is not suitable for large scale systems. Recently, many methods have been proposed to accelerate the computational time of spectral clustering. These approximate methods usually involve sampling techniques by which a lot information of the original data may be lost. In this work, we propose a fast and accurate spectral clustering approach using an approximate commute time embedding, which is similar to the spectral embedding. The method does not require using any sampling technique and computing any eigenvector at all. Instead it uses random projection and a linear time solver to find the approximate embedding. The experiments in several synthetic and real datasets show that the proposed approach has better clustering quality and is faster than the state-of-the-art approximate spectral clustering methods.", "source": "arxiv/ml"}
{"id": "arxiv:1175", "title": "Bayesian optimization using sequential Monte Carlo", "text": "We consider the problem of optimizing a real-valued continuous function $f$ using a Bayesian approach, where the evaluations of $f$ are chosen sequentially by combining prior information about $f$, which is described by a random process model, and past evaluation results. The main difficulty with this approach is to be able to compute the posterior distributions of quantities of interest which are used to choose evaluation points. In this article, we decide to use a Sequential Monte Carlo (SMC) approach.", "source": "arxiv/ml"}
{"id": "arxiv:1176", "title": "Stochastic gradient descent on Riemannian manifolds", "text": "Stochastic gradient descent is a simple approach to find the local minima of a cost function whose evaluations are corrupted by noise. In this paper, we develop a procedure extending stochastic gradient descent algorithms to the case where the function is defined on a Riemannian manifold. We prove that, as in the Euclidian case, the gradient descent algorithm converges to a critical point of the cost function. The algorithm has numerous potential applications, and is illustrated here by four examples. In particular a novel gossip algorithm on the set of covariance matrices is derived and tested numerically.", "source": "arxiv/ml"}
{"id": "arxiv:1177", "title": "The Graphical Lasso: New Insights and Alternatives", "text": "The graphical lasso \\citep{FHT2007a} is an algorithm for learning the structure in an undirected Gaussian graphical model, using $\\ell_1$ regularization to control the number of zeros in the precision matrix ${\\B\\Theta}={\\B\\Sigma}^{-1}$ \\citep{BGA2008,yuan_lin_07}. The {\\texttt R} package \\GL\\ \\citep{FHT2007a} is popular, fast, and allows one to efficiently build a path of models for different values of the tuning parameter. Convergence of \\GL\\ can be tricky; the converged precision matrix might not be the inverse of the estimated covariance, and occasionally it fails to converge with warm starts. In this paper we explain this behavior, and propose new algorithms that appear to outperform \\GL. By studying the \"normal equations\" we see that, \\GL\\ is solving the {\\em dual} of the graphical lasso penalized likelihood, by block coordinate ascent; a result which can also be found in \\cite{BGA2008}. In this dual, the target of estimation is $\\B\\Sigma$, the covariance matrix, rather than the precision matrix $\\B\\Theta$. We propose similar primal algorithms \\PGL\\ and \\DPGL, that also operate by block-coordinate descent, where $\\B\\Theta$ is the optimization target. We study all of these algorithms, and in particular different approaches to solving their coordinate sub-problems. We conclude that \\DPGL\\ is superior from several points of view.", "source": "arxiv/ml"}
{"id": "arxiv:1178", "title": "Falsification and future performance", "text": "We information-theoretically reformulate two measures of capacity from statistical learning theory: empirical VC-entropy and empirical Rademacher complexity. We show these capacity measures count the number of hypotheses about a dataset that a learning algorithm falsifies when it finds the classifier in its repertoire minimizing empirical risk. It then follows from that the future performance of predictors on unseen data is controlled in part by how many hypotheses the learner falsifies. As a corollary we show that empirical VC-entropy quantifies the message length of the true hypothesis in the optimal code of a particular probability distribution, the so-called actual repertoire.", "source": "arxiv/ml"}
{"id": "arxiv:1179", "title": "Trading Regret for Efficiency: Online Convex Optimization with Long Term Constraints", "text": "In this paper we propose a framework for solving constrained online convex optimization problem. Our motivation stems from the observation that most algorithms proposed for online convex optimization require a projection onto the convex set $\\mathcal{K}$ from which the decisions are made. While for simple shapes (e.g. Euclidean ball) the projection is straightforward, for arbitrary complex sets this is the main computational challenge and may be inefficient in practice. In this paper, we consider an alternative online convex optimization problem. Instead of requiring decisions belong to $\\mathcal{K}$ for all rounds, we only require that the constraints which define the set $\\mathcal{K}$ be satisfied in the long run. We show that our framework can be utilized to solve a relaxed version of online learning with side constraints addressed in \\cite{DBLP:conf/colt/MannorT06} and \\cite{DBLP:conf/aaai/KvetonYTM08}. By turning the problem into an online convex-concave optimization problem, we propose an efficient algorithm which achieves $\\tilde{\\mathcal{O}}(\\sqrt{T})$ regret bound and $\\tilde{\\mathcal{O}}(T^{3/4})$ bound for the violation of constraints. Then we modify the algorithm in order to guarantee that the constraints are satisfied in the long run. This gain is achieved at the price of getting $\\tilde{\\mathcal{O}}(T^{3/4})$ regret bound. Our second algorithm is based on the Mirror Prox method \\citep{nemirovski-2005-prox} to solve variational inequalities which achieves $\\tilde{\\mathcal{\\mathcal{O}}}(T^{2/3})$ bound for both regret and the violation of constraints when the domain $\\K$ can be described by a finite number of linear constraints. Finally, we extend the result to the setting where we only have partial access to the convex set $\\mathcal{K}$ and propose a multipoint bandit feedback algorithm with the same bounds in expectation as our first algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1180", "title": "Learning a Factor Model via Regularized PCA", "text": "We consider the problem of learning a linear factor model. We propose a regularized form of principal component analysis (PCA) and demonstrate through experiments with synthetic and real data the superiority of resulting estimates to those produced by pre-existing factor analysis approaches. We also establish theoretical results that explain how our algorithm corrects the biases induced by conventional approaches. An important feature of our algorithm is that its computational requirements are similar to those of PCA, which enjoys wide use in large part due to its efficiency.", "source": "arxiv/ml"}
{"id": "arxiv:1181", "title": "Robust Max-Product Belief Propagation", "text": "We study the problem of optimizing a graph-structured objective function under \\emph{adversarial} uncertainty. This problem can be modeled as a two-persons zero-sum game between an Engineer and Nature. The Engineer controls a subset of the variables (nodes in the graph), and tries to assign their values to maximize an objective function. Nature controls the complementary subset of variables and tries to minimize the same objective. This setting encompasses estimation and optimization problems under model uncertainty, and strategic problems with a graph structure. Von Neumann's minimax theorem guarantees the existence of a (minimax) pair of randomized strategies that provide optimal robustness for each player against its adversary. We prove several structural properties of this strategy pair in the case of graph-structured payoff function. In particular, the randomized minimax strategies (distributions over variable assignments) can be chosen in such a way to satisfy the Markov property with respect to the graph. This significantly reduces the problem dimensionality. Finally we introduce a message passing algorithm to solve this minimax problem. The algorithm generalizes max-product belief propagation to this new domain.", "source": "arxiv/ml"}
{"id": "arxiv:1182", "title": "Regret Bound by Variation for Online Convex Optimization", "text": "In citep{Hazan-2008-extract}, the authors showed that the regret of online linear optimization can be bounded by the total variation of the cost vectors. In this paper, we extend this result to general online convex optimization. We first analyze the limitations of the algorithm in \\citep{Hazan-2008-extract} when applied it to online convex optimization. We then present two algorithms for online convex optimization whose regrets are bounded by the variation of cost functions. We finally consider the bandit setting, and present a randomized algorithm for online bandit convex optimization with a variation-based regret bound. We show that the regret bound for online bandit convex optimization is optimal when the variation of cost functions is independent of the number of trials.", "source": "arxiv/ml"}
{"id": "arxiv:1183", "title": "Learning with Submodular Functions: A Convex Optimization Perspective", "text": "Submodular functions are relevant to machine learning for at least two reasons: (1) some problems may be expressed directly as the optimization of submodular functions and (2) the lovasz extension of submodular functions provides a useful set of regularization functions for supervised and unsupervised learning. In this monograph, we present the theory of submodular functions from a convex analysis perspective, presenting tight links between certain polyhedra, combinatorial optimization and convex optimization problems. In particular, we show how submodular function minimization is equivalent to solving a wide variety of convex optimization problems. This allows the derivation of new efficient algorithms for approximate and exact submodular function minimization with theoretical guarantees and good practical performance. By listing many examples of submodular functions, we review various applications to machine learning, such as clustering, experimental design, sensor placement, graphical model structure learning or subset selection, as well as a family of structured sparsity-inducing norms that can be derived and used from submodular functions.", "source": "arxiv/ml"}
{"id": "arxiv:1184", "title": "A kernel-based framework for learning graded relations from data", "text": "Driven by a large number of potential applications in areas like bioinformatics, information retrieval and social network analysis, the problem setting of inferring relations between pairs of data objects has recently been investigated quite intensively in the machine learning community. To this end, current approaches typically consider datasets containing crisp relations, so that standard classification methods can be adopted. However, relations between objects like similarities and preferences are often expressed in a graded manner in real-world applications. A general kernel-based framework for learning relations from data is introduced here. It extends existing approaches because both crisp and graded relations are considered, and it unifies existing approaches because different types of graded relations can be modeled, including symmetric and reciprocal relations. This framework establishes important links between recent developments in fuzzy set theory and machine learning. Its usefulness is demonstrated through various experiments on synthetic and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:1185", "title": "Fast Private Data Release Algorithms for Sparse Queries", "text": "We revisit the problem of accurately answering large classes of statistical queries while preserving differential privacy. Previous approaches to this problem have either been very general but have not had run-time polynomial in the size of the database, have applied only to very limited classes of queries, or have relaxed the notion of worst-case error guarantees. In this paper we consider the large class of sparse queries, which take non-zero values on only polynomially many universe elements. We give efficient query release algorithms for this class, in both the interactive and the non-interactive setting. Our algorithms also achieve better accuracy bounds than previous general techniques do when applied to sparse queries: our bounds are independent of the universe size. In fact, even the runtime of our interactive mechanism is independent of the universe size, and so can be implemented in the \"infinite universe\" model in which no finite universe need be specified by the data curator.", "source": "arxiv/ml"}
{"id": "arxiv:1186", "title": "Multivariate information measures: an experimentalist's perspective", "text": "Information theory is widely accepted as a powerful tool for analyzing complex systems and it has been applied in many disciplines. Recently, some central components of information theory - multivariate information measures - have found expanded use in the study of several phenomena. These information measures differ in subtle yet significant ways. Here, we will review the information theory behind each measure, as well as examine the differences between these measures by applying them to several simple model systems. In addition to these systems, we will illustrate the usefulness of the information measures by analyzing neural spiking data from a dissociated culture through early stages of its development. We hope that this work will aid other researchers as they seek the best multivariate information measure for their specific research goals and system. Finally, we have made software available online which allows the user to calculate all of the information measures discussed within this paper.", "source": "arxiv/ml"}
{"id": "arxiv:1187", "title": "Structure Learning of Probabilistic Graphical Models: A Comprehensive Survey", "text": "Probabilistic graphical models combine the graph theory and probability theory to give a multivariate statistical modeling. They provide a unified description of uncertainty using probability and complexity using the graphical model. Especially, graphical models provide the following several useful properties: - Graphical models provide a simple and intuitive interpretation of the structures of probabilistic models. On the other hand, they can be used to design and motivate new models. - Graphical models provide additional insights into the properties of the model, including the conditional independence properties. - Complex computations which are required to perform inference and learning in sophisticated models can be expressed in terms of graphical manipulations, in which the underlying mathematical expressions are carried along implicitly. The graphical models have been applied to a large number of fields, including bioinformatics, social science, control theory, image processing, marketing analysis, among others. However, structure learning for graphical models remains an open challenge, since one must cope with a combinatorial search over the space of all possible structures. In this paper, we present a comprehensive survey of the existing structure learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1188", "title": "Efficient Discovery of Association Rules and Frequent Itemsets through Sampling with Tight Performance Guarantees", "text": "The tasks of extracting (top-$K$) Frequent Itemsets (FI's) and Association Rules (AR's) are fundamental primitives in data mining and database applications. Exact algorithms for these problems exist and are widely used, but their running time is hindered by the need of scanning the entire dataset, possibly multiple times. High quality approximations of FI's and AR's are sufficient for most practical uses, and a number of recent works explored the application of sampling for fast discovery of approximate solutions to the problems. However, these works do not provide satisfactory performance guarantees on the quality of the approximation, due to the difficulty of bounding the probability of under- or over-sampling any one of an unknown number of frequent itemsets. In this work we circumvent this issue by applying the statistical concept of \\emph{Vapnik-Chervonenkis (VC) dimension} to develop a novel technique for providing tight bounds on the sample size that guarantees approximation within user-specified parameters. Our technique applies both to absolute and to relative approximations of (top-$K$) FI's and AR's. The resulting sample size is linearly dependent on the VC-dimension of a range space associated with the dataset to be mined. The main theoretical contribution of this work is a proof that the VC-dimension of this range space is upper bounded by an easy-to-compute characteristic quantity of the dataset which we call \\emph{d-index}, and is the maximum integer $d$ such that the dataset contains at least $d$ transactions of length at least $d$ such that no one of them is a superset of or equal to another. We show that this bound is strict for a large class of datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1189", "title": "Optoelectronic Reservoir Computing", "text": "Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an opto-electronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line. Our implementation is sufficiently fast for real time information processing. We illustrate its performance on tasks of practical importance such as nonlinear channel equalization and speech recognition, and obtain results comparable to state of the art digital implementations.", "source": "arxiv/ml"}
{"id": "arxiv:1190", "title": "A Learning Framework for Self-Tuning Histograms", "text": "In this paper, we consider the problem of estimating self-tuning histograms using query workloads. To this end, we propose a general learning theoretic formulation. Specifically, we use query feedback from a workload as training data to estimate a histogram with a small memory footprint that minimizes the expected error on future queries. Our formulation provides a framework in which different approaches can be studied and developed. We first study the simple class of equi-width histograms and present a learning algorithm, EquiHist, that is competitive in many settings. We also provide formal guarantees for equi-width histograms that highlight scenarios in which equi-width histograms can be expected to succeed or fail. We then go beyond equi-width histograms and present a novel learning algorithm, SpHist, for estimating general histograms. Here we use Haar wavelets to reduce the problem of learning histograms to that of learning a sparse vector. Both algorithms have multiple advantages over existing methods: 1) simple and scalable extensions to multi-dimensional data, 2) scalability with number of histogram buckets and size of query feedback, 3) natural extensions to incorporate new feedback and handle database updates. We demonstrate these advantages over the current state-of-the-art, ISOMER, through detailed experiments on real and synthetic data. In particular, we show that SpHist obtains up to 50% less error than ISOMER on real-world multi-dimensional datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1191", "title": "Clustering under Perturbation Resilience", "text": "Motivated by the fact that distances between data points in many real-world clustering instances are often based on heuristic measures, Bilu and Linial~\\cite{BL} proposed analyzing objective based clustering problems under the assumption that the optimum clustering to the objective is preserved under small multiplicative perturbations to distances between points. The hope is that by exploiting the structure in such instances, one can overcome worst case hardness results. In this paper, we provide several results within this framework. For center-based objectives, we present an algorithm that can optimally cluster instances resilient to perturbations of factor $(1 + \\sqrt{2})$, solving an open problem of Awasthi et al.~\\cite{ABS10}. For $k$-median, a center-based objective of special interest, we additionally give algorithms for a more relaxed assumption in which we allow the optimal solution to change in a small $\\epsilon$ fraction of the points after perturbation. We give the first bounds known for $k$-median under this more realistic and more general assumption. We also provide positive results for min-sum clustering which is typically a harder objective than center-based objectives from approximability standpoint. Our algorithms are based on new linkage criteria that may be of independent interest. Additionally, we give sublinear-time algorithms, showing algorithms that can return an implicit clustering from only access to a small random sample.", "source": "arxiv/ml"}
{"id": "arxiv:1192", "title": "Learning in embodied action-perception loops through exploration", "text": "Although exploratory behaviors are ubiquitous in the animal kingdom, their computational underpinnings are still largely unknown. Behavioral Psychology has identified learning as a primary drive underlying many exploratory behaviors. Exploration is seen as a means for an animal to gather sensory data useful for reducing its ignorance about the environment. While related problems have been addressed in Data Mining and Reinforcement Learning, the computational modeling of learning-driven exploration by embodied agents is largely unrepresented. Here, we propose a computational theory for learning-driven exploration based on the concept of missing information that allows an agent to identify informative actions using Bayesian inference. We demonstrate that when embodiment constraints are high, agents must actively coordinate their actions to learn efficiently. Compared to earlier approaches, our exploration policy yields more efficient learning across a range of worlds with diverse structures. The improved learning in turn affords greater success in general tasks including navigation and reward gathering. We conclude by discussing how the proposed theory relates to previous information-theoretic objectives of behavior, such as predictive information and the free energy principle, and how it might contribute to a general theory of exploratory behavior.", "source": "arxiv/ml"}
{"id": "arxiv:1193", "title": "Multi-timescale Nexting in a Reinforcement Learning Robot", "text": "The term \"nexting\" has been used by psychologists to refer to the propensity of people and many other animals to continually predict what will happen next in an immediate, local, and personal sense. The ability to \"next\" constitutes a basic kind of awareness and knowledge of one's environment. In this paper we present results with a robot that learns to next in real time, predicting thousands of features of the world's state, including all sensory inputs, at timescales from 0.1 to 8 seconds. This was achieved by treating each state feature as a reward-like target and applying temporal-difference methods to learn a corresponding value function with a discount rate corresponding to the timescale. We show that two thousand predictions, each dependent on six thousand state features, can be learned and updated online at better than 10Hz on a laptop computer, using the standard TD(lambda) algorithm with linear function approximation. We show that this approach is efficient enough to be practical, with most of the learning complete within 30 minutes. We also show that a single tile-coded feature representation suffices to accurately predict many different signals at a significant range of timescales. Finally, we show that the accuracy of our learned predictions compares favorably with the optimal off-line solution.", "source": "arxiv/ml"}
{"id": "arxiv:1194", "title": "An Identity for Kernel Ridge Regression", "text": "This paper derives an identity connecting the square loss of ridge regression in on-line mode with the loss of the retrospectively best regressor. Some corollaries about the properties of the cumulative loss of on-line ridge regression are also obtained.", "source": "arxiv/ml"}
{"id": "arxiv:1195", "title": "Active Learning of Halfspaces under a Margin Assumption", "text": "We derive and analyze a new, efficient, pool-based active learning algorithm for halfspaces, called ALuMA. Most previous algorithms show exponential improvement in the label complexity assuming that the distribution over the instance space is close to uniform. This assumption rarely holds in practical applications. Instead, we study the label complexity under a large-margin assumption -- a much more realistic condition, as evident by the success of margin-based algorithms such as SVM. Our algorithm is computationally efficient and comes with formal guarantees on its label complexity. It also naturally extends to the non-separable case and to non-linear kernels. Experiments illustrate the clear advantage of ALuMA over other active learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1196", "title": "SLA Establishment with Guaranteed QoS in the Interdomain Network: A Stock Model", "text": "The new model that we present in this paper is introduced in the context of guaranteed QoS and resources management in the inter-domain routing framework. This model, called the stock model, is based on a reverse cascade approach and is applied in a distributed context. So transit providers have to learn the right capacities to buy and to stock and, therefore learning theory is applied through an iterative process. We show that transit providers manage to learn how to strategically choose their capacities on each route in order to maximize their benefits, despite the very incomplete information. Finally, we provide and analyse some simulation results given by the application of the model in a simple case where the model quickly converges to a stable state.", "source": "arxiv/ml"}
{"id": "arxiv:1197", "title": "Using Taxonomies to Facilitate the Analysis of the Association Rules", "text": "The Data Mining process enables the end users to analyze, understand and use the extracted knowledge in an intelligent system or to support in the decision-making processes. However, many algorithms used in the process encounter large quantities of patterns, complicating the analysis of the patterns. This fact occurs with association rules, a Data Mining technique that tries to identify intrinsic patterns in large data sets. A method that can help the analysis of the association rules is the use of taxonomies in the step of post-processing knowledge. In this paper, the GART algorithm is proposed, which uses taxonomies to generalize association rules, and the RulEE-GAR computational module, that enables the analysis of the generalized rules.", "source": "arxiv/ml"}
{"id": "arxiv:1198", "title": "Recovery of a Sparse Integer Solution to an Underdetermined System of Linear Equations", "text": "We consider a system of m linear equations in n variables Ax=b where A is a given m x n matrix and b is a given m-vector known to be equal to Ax' for some unknown solution x' that is integer and k-sparse: x' in {0,1}^n and exactly k entries of x' are 1. We give necessary and sufficient conditions for recovering the solution x exactly using an LP relaxation that minimizes l1 norm of x. When A is drawn from a distribution that has exchangeable columns, we show an interesting connection between the recovery probability and a well known problem in geometry, namely the k-set problem. To the best of our knowledge, this connection appears to be new in the compressive sensing literature. We empirically show that for large n if the elements of A are drawn i.i.d. from the normal distribution then the performance of the recovery LP exhibits a phase transition, i.e., for each k there exists a value m' of m such that the recovery always succeeds if m > m' and always fails if m < m'. Using the empirical data we conjecture that m' = nH(k/n)/2 where H(x) = -(x)log_2(x) - (1-x)log_2(1-x) is the binary entropy function.", "source": "arxiv/ml"}
{"id": "arxiv:1199", "title": "Extended UCB Policy for Multi-Armed Bandit with Light-Tailed Reward Distributions", "text": "We consider the multi-armed bandit problems in which a player aims to accrue reward by sequentially playing a given set of arms with unknown reward statistics. In the classic work, policies were proposed to achieve the optimal logarithmic regret order for some special classes of light-tailed reward distributions, e.g., Auer et al.'s UCB1 index policy for reward distributions with finite support. In this paper, we extend Auer et al.'s UCB1 index policy to achieve the optimal logarithmic regret order for all light-tailed (or equivalently, locally sub-Gaussian) reward distributions defined by the (local) existence of the moment-generating function.", "source": "arxiv/ml"}
{"id": "arxiv:1200", "title": "Bootstrapping Intrinsically Motivated Learning with Human Demonstrations", "text": "This paper studies the coupling of internally guided learning and social interaction, and more specifically the improvement owing to demonstrations of the learning by intrinsic motivation. We present Socially Guided Intrinsic Motivation by Demonstration (SGIM-D), an algorithm for learning in continuous, unbounded and non-preset environments. After introducing social learning and intrinsic motivation, we describe the design of our algorithm, before showing through a fishing experiment that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation to gain a wide repertoire while being specialised in specific subspaces.", "source": "arxiv/ml"}
{"id": "arxiv:1201", "title": "Bipartite ranking algorithm for classification and survival analysis", "text": "Unsupervised aggregation of independently built univariate predictors is explored as an alternative regularization approach for noisy, sparse datasets. Bipartite ranking algorithm Smooth Rank implementing this approach is introduced. The advantages of this algorithm are demonstrated on two types of problems. First, Smooth Rank is applied to two-class problems from bio-medical field, where ranking is often preferable to classification. In comparison against SVMs with radial and linear kernels, Smooth Rank had the best performance on 8 out of 12 benchmark benchmarks. The second area of application is survival analysis, which is reduced here to bipartite ranking in a way which allows one to use commonly accepted measures of methods performance. In comparison of Smooth Rank with Cox PH regression and CoxPath methods, Smooth Rank proved to be the best on 9 out of 10 benchmark datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1202", "title": "Chinese Restaurant Game - Part II: Applications to Wireless Networking, Cloud Computing, and Online Social Networking", "text": "In Part I of this two-part paper [1], we proposed a new game, called Chinese restaurant game, to analyze the social learning problem with negative network externality. The best responses of agents in the Chinese restaurant game with imperfect signals are constructed through a recursive method, and the influence of both learning and network externality on the utilities of agents is studied. In Part II of this two-part paper, we illustrate three applications of Chinese restaurant game in wireless networking, cloud computing, and online social networking. For each application, we formulate the corresponding problem as a Chinese restaurant game and analyze how agents learn and make strategic decisions in the problem. The proposed method is compared with four common-sense methods in terms of agents' utilities and the overall system performance through simulations. We find that the proposed Chinese restaurant game theoretic approach indeed helps agents make better decisions and improves the overall system performance. Furthermore, agents with different decision orders have different advantages in terms of their utilities, which also verifies the conclusions drawn in Part I of this two-part paper.", "source": "arxiv/ml"}
{"id": "arxiv:1203", "title": "Chinese Restaurant Game - Part I: Theory of Learning with Negative Network Externality", "text": "In a social network, agents are intelligent and have the capability to make decisions to maximize their utilities. They can either make wise decisions by taking advantages of other agents' experiences through learning, or make decisions earlier to avoid competitions from huge crowds. Both these two effects, social learning and negative network externality, play important roles in the decision process of an agent. While there are existing works on either social learning or negative network externality, a general study on considering both these two contradictory effects is still limited. We find that the Chinese restaurant process, a popular random process, provides a well-defined structure to model the decision process of an agent under these two effects. By introducing the strategic behavior into the non-strategic Chinese restaurant process, in Part I of this two-part paper, we propose a new game, called Chinese Restaurant Game, to formulate the social learning problem with negative network externality. Through analyzing the proposed Chinese restaurant game, we derive the optimal strategy of each agent and provide a recursive method to achieve the optimal strategy. How social learning and negative network externality influence each other under various settings is also studied through simulations.", "source": "arxiv/ml"}
{"id": "arxiv:1204", "title": "Adaptive Forgetting Factor Fictitious Play", "text": "It is now well known that decentralised optimisation can be formulated as a potential game, and game-theoretical learning algorithms can be used to find an optimum. One of the most common learning techniques in game theory is fictitious play. However fictitious play is founded on an implicit assumption that opponents' strategies are stationary. We present a novel variation of fictitious play that allows the use of a more realistic model of opponent strategy. It uses a heuristic approach, from the online streaming data literature, to adaptively update the weights assigned to recently observed actions. We compare the results of the proposed algorithm with those of stochastic and geometric fictitious play in a simple strategic form game, a vehicle target assignment game and a disaster management problem. In all the tests the rate of convergence of the proposed algorithm was similar or better than the variations of fictitious play we compared it with. The new algorithm therefore improves the performance of game-theoretical learning in decentralised optimisation.", "source": "arxiv/ml"}
{"id": "arxiv:1205", "title": "Low-rank optimization with trace norm penalty", "text": "The paper addresses the problem of low-rank trace norm minimization. We propose an algorithm that alternates between fixed-rank optimization and rank-one updates. The fixed-rank optimization is characterized by an efficient factorization that makes the trace norm differentiable in the search space and the computation of duality gap numerically tractable. The search space is nonlinear but is equipped with a particular Riemannian structure that leads to efficient computations. We present a second-order trust-region algorithm with a guaranteed quadratic rate of convergence. Overall, the proposed optimization scheme converges super-linearly to the global solution while maintaining complexity that is linear in the number of rows and columns of the matrix. To compute a set of solutions efficiently for a grid of regularization parameters we propose a predictor-corrector approach that outperforms the naive warm-restart approach on the fixed-rank quotient manifold. The performance of the proposed algorithm is illustrated on problems of low-rank matrix completion and multivariate linear regression.", "source": "arxiv/ml"}
{"id": "arxiv:1206", "title": "Random Differential Privacy", "text": "We propose a relaxed privacy definition called {\\em random differential privacy} (RDP). Differential privacy requires that adding any new observation to a database will have small effect on the output of the data-release procedure. Random differential privacy requires that adding a {\\em randomly drawn new observation} to a database will have small effect on the output. We show an analog of the composition property of differentially private procedures which applies to our new definition. We show how to release an RDP histogram and we show that RDP histograms are much more accurate than histograms obtained using ordinary differential privacy. We finally show an analog of the global sensitivity framework for the release of functions under our privacy definition.", "source": "arxiv/ml"}
{"id": "arxiv:1207", "title": "Robust Learning via Cause-Effect Models", "text": "We consider the problem of function estimation in the case where the data distribution may shift between training and test time, and additional information about it may be available at test time. This relates to popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning. This working paper discusses how these tasks could be tackled depending on the kind of changes of the distributions. It argues that knowledge of an underlying causal direction can facilitate several of these tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1208", "title": "A new order theory of set systems and better quasi-orderings", "text": "By reformulating a learning process of a set system L as a game between Teacher (presenter of data) and Learner (updater of the abstract independent set), we define the order type dim L of L to be the order type of the game tree. The theory of this new order type and continuous, monotone function between set systems corresponds to the theory of well quasi-orderings (WQOs). As Nash-Williams developed the theory of WQOs to the theory of better quasi-orderings (BQOs), we introduce a set system that has order type and corresponds to a BQO. We prove that the class of set systems corresponding to BQOs is closed by any monotone function. In (Shinohara and Arimura. \"Inductive inference of unbounded unions of pattern languages from positive data.\" Theoretical Computer Science, pp. 191-209, 2000), for any set system L, they considered the class of arbitrary (finite) unions of members of L. From viewpoint of WQOs and BQOs, we characterize the set systems L such that the class of arbitrary (finite) unions of members of L has order type. The characterization shows that the order structure of the set system L with respect to the set-inclusion is not important for the resulting set system having order type. We point out continuous, monotone function of set systems is similar to positive reduction to Jockusch-Owings' weakly semirecursive sets.", "source": "arxiv/ml"}
{"id": "arxiv:1209", "title": "Analysis and Extension of Arc-Cosine Kernels for Large Margin Classification", "text": "We investigate a recently proposed family of positive-definite kernels that mimic the computation in large neural networks. We examine the properties of these kernels using tools from differential geometry; specifically, we analyze the geometry of surfaces in Hilbert space that are induced by these kernels. When this geometry is described by a Riemannian manifold, we derive results for the metric, curvature, and volume element. Interestingly, though, we find that the simplest kernel in this family does not admit such an interpretation. We explore two variations of these kernels that mimic computation in neural networks with different activation functions. We experiment with these new kernels on several data sets and highlight their general trends in performance for classification.", "source": "arxiv/ml"}
{"id": "arxiv:1210", "title": "Nonnegative Matrix Factorization for Semi-supervised Dimensionality Reduction", "text": "We show how to incorporate information from labeled examples into nonnegative matrix factorization (NMF), a popular unsupervised learning algorithm for dimensionality reduction. In addition to mapping the data into a space of lower dimensionality, our approach aims to preserve the nonnegative components of the data that are important for classification. We identify these components from the support vectors of large-margin classifiers and derive iterative updates to preserve them in a semi-supervised version of NMF. These updates have a simple multiplicative form like their unsupervised counterparts; they are also guaranteed at each iteration to decrease their loss function---a weighted sum of I-divergences that captures the trade-off between unsupervised and supervised learning. We evaluate these updates for dimensionality reduction when they are used as a precursor to linear classification. In this role, we find that they yield much better performance than their unsupervised counterparts. We also find one unexpected benefit of the low dimensional representations discovered by our approach: often they yield more accurate classifiers than both ordinary and transductive SVMs trained in the original input space.", "source": "arxiv/ml"}
{"id": "arxiv:1211", "title": "Strongly Convex Programming for Exact Matrix Completion and Robust Principal Component Analysis", "text": "The common task in matrix completion (MC) and robust principle component analysis (RPCA) is to recover a low-rank matrix from a given data matrix. These problems gained great attention from various areas in applied sciences recently, especially after the publication of the pioneering works of Cand`es et al.. One fundamental result in MC and RPCA is that nuclear norm based convex optimizations lead to the exact low-rank matrix recovery under suitable conditions. In this paper, we extend this result by showing that strongly convex optimizations can guarantee the exact low-rank matrix recovery as well. The result in this paper not only provides sufficient conditions under which the strongly convex models lead to the exact low-rank matrix recovery, but also guides us on how to choose suitable parameters in practical algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1212", "title": "Clustering and Latent Semantic Indexing Aspects of the Nonnegative Matrix Factorization", "text": "This paper provides a theoretical support for clustering aspect of the nonnegative matrix factorization (NMF). By utilizing the Karush-Kuhn-Tucker optimality conditions, we show that NMF objective is equivalent to graph clustering objective, so clustering aspect of the NMF has a solid justification. Different from previous approaches which usually discard the nonnegativity constraints, our approach guarantees the stationary point being used in deriving the equivalence is located on the feasible region in the nonnegative orthant. Additionally, since clustering capability of a matrix decomposition technique can sometimes imply its latent semantic indexing (LSI) aspect, we will also evaluate LSI aspect of the NMF by showing its capability in solving the synonymy and polysemy problems in synthetic datasets. And more extensive evaluation will be conducted by comparing LSI performances of the NMF and the singular value decomposition (SVD), the standard LSI method, using some standard datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1213", "title": "epsilon-Samples of Kernels", "text": "We study the worst case error of kernel density estimates via subset approximation. A kernel density estimate of a distribution is the convolution of that distribution with a fixed kernel (e.g. Gaussian kernel). Given a subset (i.e. a point set) of the input distribution, we can compare the kernel density estimates of the input distribution with that of the subset and bound the worst case error. If the maximum error is eps, then this subset can be thought of as an eps-sample (aka an eps-approximation) of the range space defined with the input distribution as the ground set and the fixed kernel representing the family of ranges. Interestingly, in this case the ranges are not binary, but have a continuous range (for simplicity we focus on kernels with range of [0,1]); these allow for smoother notions of range spaces. It turns out, the use of this smoother family of range spaces has an added benefit of greatly decreasing the size required for eps-samples. For instance, in the plane the size is O((1/eps^{4/3}) log^{2/3}(1/eps)) for disks (based on VC-dimension arguments) but is only O((1/eps) sqrt{log (1/eps)}) for Gaussian kernels and for kernels with bounded slope that only affect a bounded domain. These bounds are accomplished by studying the discrepancy of these \"kernel\" range spaces, and here the improvement in bounds are even more pronounced. In the plane, we show the discrepancy is O(sqrt{log n}) for these kernels, whereas for balls there is a lower bound of Omega(n^{1/4}).", "source": "arxiv/ml"}
{"id": "arxiv:1214", "title": "Evaluation of Performance Measures for Classifiers Comparison", "text": "The selection of the best classification algorithm for a given dataset is a very widespread problem, occuring each time one has to choose a classifier to solve a real-world problem. It is also a complex task with many important methodological decisions to make. Among those, one of the most crucial is the choice of an appropriate measure in order to properly assess the classification performance and rank the algorithms. In this article, we focus on this specific task. We present the most popular measures and compare their behavior through discrimination plots. We then discuss their properties from a more theoretical perspective. It turns out several of them are equivalent for classifiers comparison purposes. Futhermore. they can also lead to interpretation problems. Among the numerous measures proposed over the years, it appears that the classical overall success rate and marginal rates are the more suitable for classifier comparison task.", "source": "arxiv/ml"}
{"id": "arxiv:1215", "title": "Online Learning for Classification of Low-rank Representation Features and Its Applications in Audio Segment Classification", "text": "In this paper, a novel framework based on trace norm minimization for audio segment is proposed. In this framework, both the feature extraction and classification are obtained by solving corresponding convex optimization problem with trace norm regularization. For feature extraction, robust principle component analysis (robust PCA) via minimization a combination of the nuclear norm and the $\\ell_1$-norm is used to extract low-rank features which are robust to white noise and gross corruption for audio segments. These low-rank features are fed to a linear classifier where the weight and bias are learned by solving similar trace norm constrained problems. For this classifier, most methods find the weight and bias in batch-mode learning, which makes them inefficient for large-scale problems. In this paper, we propose an online framework using accelerated proximal gradient method. This framework has a main advantage in memory cost. In addition, as a result of the regularization formulation of matrix classification, the Lipschitz constant was given explicitly, and hence the step size estimation of general proximal gradient method was omitted in our approach. Experiments on real data sets for laugh/non-laugh and applause/non-applause classification indicate that this novel framework is effective and noise robust.", "source": "arxiv/ml"}
{"id": "arxiv:1216", "title": "A geometric analysis of subspace clustering with outliers", "text": "This paper considers the problem of clustering a collection of unlabeled data points assumed to lie near a union of lower-dimensional planes. As is common in computer vision or unsupervised learning applications, we do not know in advance how many subspaces there are nor do we have any information about their dimensions. We develop a novel geometric analysis of an algorithm named sparse subspace clustering (SSC) [In IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 (2009) 2790-2797. IEEE], which significantly broadens the range of problems where it is provably effective. For instance, we show that SSC can recover multiple subspaces, each of dimension comparable to the ambient dimension. We also prove that SSC can correctly cluster data points even when the subspaces of interest intersect. Further, we develop an extension of SSC that succeeds when the data set is corrupted with possibly overwhelmingly many outliers. Underlying our analysis are clear geometric insights, which may bear on other sparse recovery problems. A numerical study complements our theoretical analysis and demonstrates the effectiveness of these methods.", "source": "arxiv/ml"}
{"id": "arxiv:1217", "title": "Performance Analysis of Enhanced Clustering Algorithm for Gene Expression Data", "text": "Microarrays are made it possible to simultaneously monitor the expression profiles of thousands of genes under various experimental conditions. It is used to identify the co-expressed genes in specific cells or tissues that are actively used to make proteins. This method is used to analysis the gene expression, an important task in bioinformatics research. Cluster analysis of gene expression data has proved to be a useful tool for identifying co-expressed genes, biologically relevant groupings of genes and samples. In this paper we applied K-Means with Automatic Generations of Merge Factor for ISODATA- AGMFI. Though AGMFI has been applied for clustering of Gene Expression Data, this proposed Enhanced Automatic Generations of Merge Factor for ISODATA- EAGMFI Algorithms overcome the drawbacks of AGMFI in terms of specifying the optimal number of clusters and initialization of good cluster centroids. Experimental results on Gene Expression Data show that the proposed EAGMFI algorithms could identify compact clusters with perform well in terms of the Silhouette Coefficients cluster measure.", "source": "arxiv/ml"}
{"id": "arxiv:1218", "title": "A Scalable Multiclass Algorithm for Node Classification", "text": "We introduce a scalable algorithm, MUCCA, for multiclass node classification in weighted graphs. Unlike previously proposed methods for the same task, MUCCA works in time linear in the number of nodes. Our approach is based on a game-theoretic formulation of the problem in which the test labels are expressed as a Nash Equilibrium of a certain game. However, in order to achieve scalability, we find the equilibrium on a spanning tree of the original graph. Experiments on real-world data reveal that MUCCA is much faster than its competitors while achieving a similar predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:1219", "title": "Additive Gaussian Processes", "text": "We introduce a Gaussian process model of functions which are additive. An additive function is one which decomposes into a sum of low-dimensional functions, each depending on only a subset of the input variables. Additive GPs generalize both Generalized Additive Models, and the standard GP models which use squared-exponential kernels. Hyperparameter learning in this model can be seen as Bayesian Hierarchical Kernel Learning (HKL). We introduce an expressive but tractable parameterization of the kernel function, which allows efficient evaluation of all input interaction terms, whose number is exponential in the input dimension. The additional structure discoverable by this model results in increased interpretability, as well as state-of-the-art predictive power in regression tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1220", "title": "Alignment Based Kernel Learning with a Continuous Set of Base Kernels", "text": "The success of kernel-based learning methods depend on the choice of kernel. Recently, kernel learning methods have been proposed that use data to select the most appropriate kernel, usually by combining a set of base kernels. We introduce a new algorithm for kernel learning that combines a {\\em continuous set of base kernels}, without the common step of discretizing the space of base kernels. We demonstrate that our new method achieves state-of-the-art performance across a variety of real-world datasets. Furthermore, we explicitly demonstrate the importance of combining the right dictionary of kernels, which is problematic for methods based on a finite set of base kernels chosen a priori. Our method is not the first approach to work with continuously parameterized kernels. However, we show that our method requires substantially less computation than previous such approaches, and so is more amenable to multiple dimensional parameterizations of base kernels, which we demonstrate.", "source": "arxiv/ml"}
{"id": "arxiv:1221", "title": "Using Artificial Bee Colony Algorithm for MLP Training on Earthquake Time Series Data Prediction", "text": "Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial problems with the backpropagation (BP) algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome ABC algorithm used in this work to train MLP learning the complex behaviour of earthquake time series data trained by BP, the performance of MLP-ABC is benchmarked against MLP training with the standard BP. The experimental result shows that MLP-ABC performance is better than MLP-BP for time series data.", "source": "arxiv/ml"}
{"id": "arxiv:1222", "title": "Modeling transition dynamics in MDPs with RKHS embeddings of conditional distributions", "text": "We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert space. Such representations bypass the need for estimating transition probabilities, and apply to any domain on which kernels can be defined. Our approach avoids the need to approximate intractable integrals since expectations are represented as RKHS inner products whose computation has linear complexity in the sample size. Thus, we can efficiently perform value function estimation in a wide variety of settings, including finite state spaces, continuous states spaces, and partially observable tasks where only sensor measurements are available. A second advantage of the approach is that we learn the conditional distribution representation from a training sample, and do not require an exhaustive exploration of the state space. We prove convergence of our approach either to the optimal policy, or to the closest projection of the optimal policy in our model class, under reasonable assumptions. In experiments, we demonstrate the performance of our algorithm on a learning task in a continuous state space (the under-actuated pendulum), and on a navigation problem where only images from a sensor are observed. We compare with least-squares policy iteration where a Gaussian process is used for value function estimation. Our algorithm achieves better performance in both tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1223", "title": "Combining One-Class Classifiers via Meta-Learning", "text": "Selecting the best classifier among the available ones is a difficult task, especially when only instances of one class exist. In this work we examine the notion of combining one-class classifiers as an alternative for selecting the best classifier. In particular, we propose two new one-class classification performance measures to weigh classifiers and show that a simple ensemble that implements these measures can outperform the most popular one-class ensembles. Furthermore, we propose a new one-class ensemble scheme, TUPSO, which uses meta-learning to combine one-class classifiers. Our experiments demonstrate the superiority of TUPSO over all other tested ensembles and show that the TUPSO performance is statistically indistinguishable from that of the hypothetical best classifier.", "source": "arxiv/ml"}
{"id": "arxiv:1224", "title": "POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem", "text": "Most of computer science focuses on automatically solving given computational problems. I focus on automatically inventing or discovering problems in a way inspired by the playful behavior of animals and humans, to train a more and more general problem solver from scratch in an unsupervised fashion. Consider the infinite set of all computable descriptions of tasks with possibly computable solutions. The novel algorithmic framework POWERPLAY (2011) continually searches the space of possible pairs of new tasks and modifications of the current problem solver, until it finds a more powerful problem solver that provably solves all previously learned tasks plus the new one, while the unmodified predecessor does not. Wow-effects are achieved by continually making previously learned skills more efficient such that they require less time and space. New skills may (partially) re-use previously learned skills. POWERPLAY's search orders candidate pairs of tasks and solver modifications by their conditional computational (time & space) complexity, given the stored experience so far. The new task and its corresponding task-solving skill are those first found and validated. The computational costs of validating new tasks need not grow with task repertoire size. POWERPLAY's ongoing search for novelty keeps breaking the generalization abilities of its present solver. This is related to Goedel's sequence of increasingly powerful formal theories based on adding formerly unprovable statements to the axioms without affecting previously provable theorems. The continually increasing repertoire of problem solving procedures can be exploited by a parallel search for solutions to additional externally posed tasks. POWERPLAY may be viewed as a greedy but practical implementation of basic principles of creativity. A first experimental analysis can be found in separate papers [53,54].", "source": "arxiv/ml"}
{"id": "arxiv:1225", "title": "Similarity-based Learning via Data Driven Embeddings", "text": "We consider the problem of classification using similarity/distance functions over data. Specifically, we propose a framework for defining the goodness of a (dis)similarity function with respect to a given learning task and propose algorithms that have guaranteed generalization properties when working with such good functions. Our framework unifies and generalizes the frameworks proposed by [Balcan-Blum ICML 2006] and [Wang et al ICML 2007]. An attractive feature of our framework is its adaptability to data - we do not promote a fixed notion of goodness but rather let data dictate it. We show, by giving theoretical guarantees that the goodness criterion best suited to a problem can itself be learned which makes our approach applicable to a variety of domains and problems. We propose a landmarking-based approach to obtaining a classifier from such learned goodness criteria. We then provide a novel diversity based heuristic to perform task-driven selection of landmark points instead of random selection. We demonstrate the effectiveness of our goodness criteria learning method as well as the landmark selection heuristic on a variety of similarity-based learning datasets and benchmark UCI datasets on which our method consistently outperforms existing approaches by a significant margin.", "source": "arxiv/ml"}
{"id": "arxiv:1226", "title": "Finding Density Functionals with Machine Learning", "text": "Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of non-interacting fermions in 1d, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is within the interpolation region. Via principal component analysis, a projected functional derivative finds highly accurate self-consistent densities. Challenges for application of our method to real electronic structure problems are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:1227", "title": "A Study on Using Uncertain Time Series Matching Algorithms in MapReduce Applications", "text": "In this paper, we study CPU utilization time patterns of several Map-Reduce applications. After extracting running patterns of several applications, the patterns with their statistical information are saved in a reference database to be later used to tweak system parameters to efficiently execute unknown applications in future. To achieve this goal, CPU utilization patterns of new applications along with its statistical information are compared with the already known ones in the reference database to find/predict their most probable execution patterns. Because of different patterns lengths, the Dynamic Time Warping (DTW) is utilized for such comparison; a statistical analysis is then applied to DTWs' outcomes to select the most suitable candidates. Moreover, under a hypothesis, another algorithm is proposed to classify applications under similar CPU utilization patterns. Three widely used text processing applications (WordCount, Distributed Grep, and Terasort) and another application (Exim Mainlog parsing) are used to evaluate our hypothesis in tweaking system parameters in executing similar applications. Results were very promising and showed effectiveness of our approach on 5-node Map-Reduce platform", "source": "arxiv/ml"}
{"id": "arxiv:1228", "title": "Minimax Rates for Homology Inference", "text": "Often, high dimensional data lie close to a low-dimensional submanifold and it is of interest to understand the geometry of these submanifolds. The homology groups of a manifold are important topological invariants that provide an algebraic summary of the manifold. These groups contain rich topological information, for instance, about the connected components, holes, tunnels and sometimes the dimension of the manifold. In this paper, we consider the statistical problem of estimating the homology of a manifold from noisy samples under several different noise models. We derive upper and lower bounds on the minimax risk for this problem. Our upper bounds are based on estimators which are constructed from a union of balls of appropriate radius around carefully selected points. In each case we establish complementary lower bounds using Le Cam's lemma.", "source": "arxiv/ml"}
{"id": "arxiv:1229", "title": "High-Rank Matrix Completion and Subspace Clustering with Missing Data", "text": "This paper considers the problem of completing a matrix with many missing entries under the assumption that the columns of the matrix belong to a union of multiple low-rank subspaces. This generalizes the standard low-rank matrix completion problem to situations in which the matrix rank can be quite high or even full rank. Since the columns belong to a union of subspaces, this problem may also be viewed as a missing-data version of the subspace clustering problem. Let X be an n x N matrix whose (complete) columns lie in a union of at most k subspaces, each of rank <= r < n, and assume N >> kn. The main result of the paper shows that under mild assumptions each column of X can be perfectly recovered with high probability from an incomplete version so long as at least CrNlog^2(n) entries of X are observed uniformly at random, with C>1 a constant depending on the usual incoherence conditions, the geometrical arrangement of subspaces, and the distribution of columns over the subspaces. The result is illustrated with numerical experiments and an application to Internet distance matrix completion and topology identification.", "source": "arxiv/ml"}
{"id": "arxiv:1230", "title": "Bayesian Active Learning for Classification and Preference Learning", "text": "Information theoretic active learning has been widely studied for probabilistic models. For simple regression an optimal myopic policy is easily tractable. However, for other tasks and with more complex models, such as classification with nonparametric models, the optimal solution is harder to compute. Current approaches make approximations to achieve tractability. We propose an approach that expresses information gain in terms of predictive entropies, and apply this method to the Gaussian Process Classifier (GPC). Our approach makes minimal approximations to the full information theoretic objective. Our experimental performance compares favourably to many popular active learning algorithms, and has equal or lower computational complexity. We compare well to decision theoretic approaches also, which are privy to more information and require much more computational time. Secondly, by developing further a reformulation of binary preference learning to a classification problem, we extend our algorithm to Gaussian Process preference learning.", "source": "arxiv/ml"}
{"id": "arxiv:1231", "title": "Building high-level features using large scale unsupervised learning", "text": "We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel images downloaded from the Internet). We train this network using model parallelism and asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not. Control experiments show that this feature detector is robust not only to translation but also to scaling and out-of-plane rotation. We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained our network to obtain 15.8% accuracy in recognizing 20,000 object categories from ImageNet, a leap of 70% relative improvement over the previous state-of-the-art.", "source": "arxiv/ml"}
{"id": "arxiv:1232", "title": "Sparse Recovery from Nonlinear Measurements with Applications in Bad Data Detection for Power Networks", "text": "In this paper, we consider the problem of sparse recovery from nonlinear measurements, which has applications in state estimation and bad data detection for power networks. An iterative mixed $\\ell_1$ and $\\ell_2$ convex program is used to estimate the true state by locally linearizing the nonlinear measurements. When the measurements are linear, through using the almost Euclidean property for a linear subspace, we derive a new performance bound for the state estimation error under sparse bad data and additive observation noise. As a byproduct, in this paper we provide sharp bounds on the almost Euclidean property of a linear subspace, using the \"escape-through-the-mesh\" theorem from geometric functional analysis. When the measurements are nonlinear, we give conditions under which the solution of the iterative algorithm converges to the true state even though the locally linearized measurements may not be the actual nonlinear measurements. We numerically evaluate our iterative convex programming approach to perform bad data detections in nonlinear electrical power networks problems. We are able to use semidefinite programming to verify the conditions for convergence of the proposed iterative sparse recovery algorithms from nonlinear measurements.", "source": "arxiv/ml"}
{"id": "arxiv:1233", "title": "Two-Manifold Problems", "text": "Recently, there has been much interest in spectral approaches to learning manifolds---so-called kernel eigenmap methods. These methods have had some successes, but their applicability is limited because they are not robust to noise. To address this limitation, we look at two-manifold problems, in which we simultaneously reconstruct two related manifolds, each representing a different view of the same data. By solving these interconnected learning problems together and allowing information to flow between them, two-manifold algorithms are able to succeed where a non-integrated approach would fail: each view allows us to suppress noise in the other, reducing bias in the same way that an instrumental variable allows us to remove bias in a {linear} dimensionality reduction problem. We propose a class of algorithms for two-manifold problems, based on spectral decomposition of cross-covariance operators in Hilbert space. Finally, we discuss situations where two-manifold problems are useful, and demonstrate that solving a two-manifold problem can aid in learning a nonlinear dynamical system from limited data.", "source": "arxiv/ml"}
{"id": "arxiv:1234", "title": "High-dimensional Sparse Inverse Covariance Estimation using Greedy Methods", "text": "In this paper we consider the task of estimating the non-zero pattern of the sparse inverse covariance matrix of a zero-mean Gaussian random vector from a set of iid samples. Note that this is also equivalent to recovering the underlying graph structure of a sparse Gaussian Markov Random Field (GMRF). We present two novel greedy approaches to solving this problem. The first estimates the non-zero covariates of the overall inverse covariance matrix using a series of global forward and backward greedy steps. The second estimates the neighborhood of each node in the graph separately, again using greedy forward and backward steps, and combines the intermediate neighborhoods to form an overall estimate. The principal contribution of this paper is a rigorous analysis of the sparsistency, or consistency in recovering the sparsity pattern of the inverse covariance matrix. Surprisingly, we show that both the local and global greedy methods learn the full structure of the model with high probability given just $O(d\\log(p))$ samples, which is a \\emph{significant} improvement over state of the art $\\ell_1$-regularized Gaussian MLE (Graphical Lasso) that requires $O(d^2\\log(p))$ samples. Moreover, the restricted eigenvalue and smoothness conditions imposed by our greedy methods are much weaker than the strong irrepresentable conditions required by the $\\ell_1$-regularization based methods. We corroborate our results with extensive simulations and examples, comparing our local and global greedy methods to the $\\ell_1$-regularized Gaussian MLE as well as the Neighborhood Greedy method to that of nodewise $\\ell_1$-regularized linear regression (Neighborhood Lasso).", "source": "arxiv/ml"}
{"id": "arxiv:1235", "title": "T-Learning", "text": "Traditional Reinforcement Learning (RL) has focused on problems involving many states and few actions, such as simple grid worlds. Most real world problems, however, are of the opposite type, Involving Few relevant states and many actions. For example, to return home from a conference, humans identify only few subgoal states such as lobby, taxi, airport etc. Each valid behavior connecting two such states can be viewed as an action, and there are trillions of them. Assuming the subgoal identification problem is already solved, the quality of any RL method---in real-world settings---depends less on how well it scales with the number of states than on how well it scales with the number of actions. This is where our new method T-Learning excels, by evaluating the relatively few possible transits from one state to another in a policy-independent way, rather than a huge number of state-action pairs, or states in traditional policy-dependent ways. Illustrative experiments demonstrate that performance improvements of T-Learning over Q-learning can be arbitrarily large.", "source": "arxiv/ml"}
{"id": "arxiv:1236", "title": "Collaborative Filtering via Group-Structured Dictionary Learning", "text": "Structured sparse coding and the related structured dictionary learning problems are novel research areas in machine learning. In this paper we present a new application of structured dictionary learning for collaborative filtering based recommender systems. Our extensive numerical experiments demonstrate that the presented technique outperforms its state-of-the-art competitors and has several advantages over approaches that do not put structured constraints on the dictionary elements.", "source": "arxiv/ml"}
{"id": "arxiv:1237", "title": "Scikit-learn: Machine Learning in Python", "text": "Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.org.", "source": "arxiv/ml"}
{"id": "arxiv:1238", "title": "Random Forests for Metric Learning with Implicit Pairwise Position Dependence", "text": "Metric learning makes it plausible to learn distances for complex distributions of data from labeled data. However, to date, most metric learning methods are based on a single Mahalanobis metric, which cannot handle heterogeneous data well. Those that learn multiple metrics throughout the space have demonstrated superior accuracy, but at the cost of computational efficiency. Here, we take a new angle to the metric learning problem and learn a single metric that is able to implicitly adapt its distance function throughout the feature space. This metric adaptation is accomplished by using a random forest-based classifier to underpin the distance function and incorporate both absolute pairwise position and standard relative position into the representation. We have implemented and tested our method against state of the art global and multi-metric methods on a variety of data sets. Overall, the proposed method outperforms both types of methods in terms of accuracy (consistently ranked first) and is an order of magnitude faster than state of the art multi-metric methods (16x faster in the worst case).", "source": "arxiv/ml"}
{"id": "arxiv:1239", "title": "Sparse Nonparametric Graphical Models", "text": "We present some nonparametric methods for graphical modeling. In the discrete case, where the data are binary or drawn from a finite alphabet, Markov random fields are already essentially nonparametric, since the cliques can take only a finite number of values. Continuous data are different. The Gaussian graphical model is the standard parametric model for continuous data, but it makes distributional assumptions that are often unrealistic. We discuss two approaches to building more flexible graphical models. One allows arbitrary graphs and a nonparametric extension of the Gaussian; the other uses kernel density estimation and restricts the graphs to trees and forests. Examples of both methods are presented. We also discuss possible future research directions for nonparametric graphical modeling.", "source": "arxiv/ml"}
{"id": "arxiv:1240", "title": "A Topic Modeling Toolbox Using Belief Propagation", "text": "Latent Dirichlet allocation (LDA) is an important hierarchical Bayesian model for probabilistic topic modeling, which attracts worldwide interests and touches on many important applications in text mining, computer vision and computational biology. This paper introduces a topic modeling toolbox (TMBP) based on the belief propagation (BP) algorithms. TMBP toolbox is implemented by MEX C++/Matlab/Octave for either Windows 7 or Linux. Compared with existing topic modeling packages, the novelty of this toolbox lies in the BP algorithms for learning LDA-based topic models. The current version includes BP algorithms for latent Dirichlet allocation (LDA), author-topic models (ATM), relational topic models (RTM), and labeled LDA (LaLDA). This toolbox is an ongoing project and more BP-based algorithms for various topic models will be added in the near future. Interested users may also extend BP algorithms for learning more complicated topic models. The source codes are freely available under the GNU General Public Licence, Version 1.0 at https://mloss.org/software/view/399/.", "source": "arxiv/ml"}
{"id": "arxiv:1241", "title": "Constrained variable clustering and the best basis problem in functional data analysis", "text": "Functional data analysis involves data described by regular functions rather than by a finite number of real valued variables. While some robust data analysis methods can be applied directly to the very high dimensional vectors obtained from a fine grid sampling of functional data, all methods benefit from a prior simplification of the functions that reduces the redundancy induced by the regularity. In this paper we propose to use a clustering approach that targets variables rather than individual to design a piecewise constant representation of a set of functions. The contiguity constraint induced by the functional nature of the variables allows a polynomial complexity algorithm to give the optimal solution.", "source": "arxiv/ml"}
{"id": "arxiv:1242", "title": "Clustering Dynamic Web Usage Data", "text": "Most classification methods are based on the assumption that data conforms to a stationary distribution. The machine learning domain currently suffers from a lack of classification techniques that are able to detect the occurrence of a change in the underlying data distribution. Ignoring possible changes in the underlying concept, also known as concept drift, may degrade the performance of the classification model. Often these changes make the model inconsistent and regular updatings become necessary. Taking the temporal dimension into account during the analysis of Web usage data is a necessity, since the way a site is visited may indeed evolve due to modifications in the structure and content of the site, or even due to changes in the behavior of certain user groups. One solution to this problem, proposed in this article, is to update models using summaries obtained by means of an evolutionary approach based on an intelligent clustering approach. We carry out various clustering strategies that are applied on time sub-periods. To validate our approach we apply two external evaluation criteria which compare different partitions from the same data set. Our experiments show that the proposed approach is efficient to detect the occurrence of changes.", "source": "arxiv/ml"}
{"id": "arxiv:1243", "title": "A Thermodynamical Approach for Probability Estimation", "text": "The issue of discrete probability estimation for samples of small size is addressed in this study. The maximum likelihood method often suffers over-fitting when insufficient data is available. Although the Bayesian approach can avoid over-fitting by using prior distributions, it still has problems with objective analysis. In response to these drawbacks, a new theoretical framework based on thermodynamics, where energy and temperature are introduced, was developed. Entropy and likelihood are placed at the center of this method. The key principle of inference for probability mass functions is the minimum free energy, which is shown to unify the two principles of maximum likelihood and maximum entropy. Our method can robustly estimate probability functions from small size data.", "source": "arxiv/ml"}
{"id": "arxiv:1244", "title": "The Interaction of Entropy-Based Discretization and Sample Size: An Empirical Study", "text": "An empirical investigation of the interaction of sample size and discretization - in this case the entropy-based method CAIM (Class-Attribute Interdependence Maximization) - was undertaken to evaluate the impact and potential bias introduced into data mining performance metrics due to variation in sample size as it impacts the discretization process. Of particular interest was the effect of discretizing within cross-validation folds averse to outside discretization folds. Previous publications have suggested that discretizing externally can bias performance results; however, a thorough review of the literature found no empirical evidence to support such an assertion. This investigation involved construction of over 117,000 models on seven distinct datasets from the UCI (University of California-Irvine) Machine Learning Library and multiple modeling methods across a variety of configurations of sample size and discretization, with each unique \"setup\" being independently replicated ten times. The analysis revealed a significant optimistic bias as sample sizes decreased and discretization was employed. The study also revealed that there may be a relationship between the interaction that produces such bias and the numbers and types of predictor attributes, extending the \"curse of dimensionality\" concept from feature selection into the discretization realm. Directions for further exploration are laid out, as well some general guidelines about the proper application of discretization in light of these results.", "source": "arxiv/ml"}
{"id": "arxiv:1245", "title": "Feature Selection via Regularized Trees", "text": "We propose a tree regularization framework, which enables many tree models to perform feature selection efficiently. The key idea of the regularization framework is to penalize selecting a new feature for splitting when its gain (e.g. information gain) is similar to the features used in previous splits. The regularization framework is applied on random forest and boosted trees here, and can be easily applied to other tree models. Experimental studies show that the regularized trees can select high-quality feature subsets with regard to both strong and weak classifiers. Because tree models can naturally deal with categorical and numerical variables, missing values, different scales between variables, interactions and nonlinearities etc., the tree regularization framework provides an effective and efficient feature selection solution for many practical problems.", "source": "arxiv/ml"}
{"id": "arxiv:1246", "title": "Customers Behavior Modeling by Semi-Supervised Learning in Customer Relationship Management", "text": "Leveraging the power of increasing amounts of data to analyze customer base for attracting and retaining the most valuable customers is a major problem facing companies in this information age. Data mining technologies extract hidden information and knowledge from large data stored in databases or data warehouses, thereby supporting the corporate decision making process. CRM uses data mining (one of the elements of CRM) techniques to interact with customers. This study investigates the use of a technique, semi-supervised learning, for the management and analysis of customer-related data warehouse and information. The idea of semi-supervised learning is to learn not only from the labeled training data, but to exploit also the structural information in additionally available unlabeled data. The proposed semi-supervised method is a model by means of a feed-forward neural network trained by a back propagation algorithm (multi-layer perceptron) in order to predict the category of an unknown customer (potential customers). In addition, this technique can be used with Rapid Miner tools for both labeled and unlabeled data.", "source": "arxiv/ml"}
{"id": "arxiv:1247", "title": "Adaptive Context Tree Weighting", "text": "We describe an adaptive context tree weighting (ACTW) algorithm, as an extension to the standard context tree weighting (CTW) algorithm. Unlike the standard CTW algorithm, which weights all observations equally regardless of the depth, ACTW gives increasing weight to more recent observations, aiming to improve performance in cases where the input sequence is from a non-stationary distribution. Data compression results show ACTW variants improving over CTW on merged files from standard compression benchmark tests while never being significantly worse on any individual file.", "source": "arxiv/ml"}
{"id": "arxiv:1248", "title": "Automatic Detection of Diabetes Diagnosis using Feature Weighted Support Vector Machines based on Mutual Information and Modified Cuckoo Search", "text": "Diabetes is a major health problem in both developing and developed countries and its incidence is rising dramatically. In this study, we investigate a novel automatic approach to diagnose Diabetes disease based on Feature Weighted Support Vector Machines (FW-SVMs) and Modified Cuckoo Search (MCS). The proposed model consists of three stages: Firstly, PCA is applied to select an optimal subset of features out of set of all the features. Secondly, Mutual Information is employed to construct the FWSVM by weighting different features based on their degree of importance. Finally, since parameter selection plays a vital role in classification accuracy of SVMs, MCS is applied to select the best parameter values. The proposed MI-MCS-FWSVM method obtains 93.58% accuracy on UCI dataset. The experimental results demonstrate that our method outperforms the previous methods by not only giving more accurate results but also significantly speeding up the classification procedure.", "source": "arxiv/ml"}
{"id": "arxiv:1249", "title": "Stochastic Low-Rank Kernel Learning for Regression", "text": "We present a novel approach to learn a kernel-based regression function. It is based on the useof conical combinations of data-based parameterized kernels and on a new stochastic convex optimization procedure of which we establish convergence guarantees. The overall learning procedure has the nice properties that a) the learned conical combination is automatically designed to perform the regression task at hand and b) the updates implicated by the optimization procedure are quite inexpensive. In order to shed light on the appositeness of our learning strategy, we present empirical results from experiments conducted on various benchmark datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1250", "title": "Sparse Reward Processes", "text": "We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Consequently, the agent is intrinsically motivated to explore its environment beyond the degree necessary to solve the current task it has at hand. We develop a decision theoretic setting that generalises standard reinforcement learning tasks and captures this intuition. More precisely, we consider a multi-stage stochastic game between a learning agent and an opponent. We posit that the setting is a good model for the problem of life-long learning in uncertain environments, where while resources must be spent learning about currently important tasks, there is also the need to allocate effort towards learning about aspects of the world which are not relevant at the moment. This is due to the fact that unpredictable future events may lead to a change of priorities for the decision maker. Thus, in some sense, the model \"explains\" the necessity of curiosity. Apart from introducing the general formalism, the paper provides algorithms. These are evaluated experimentally in some exemplary domains. In addition, performance bounds are proven for some cases of this problem.", "source": "arxiv/ml"}
{"id": "arxiv:1251", "title": "Joint Approximation of Information and Distributed Link-Scheduling Decisions in Wireless Networks", "text": "For a large multi-hop wireless network, nodes are preferable to make distributed and localized link-scheduling decisions with only interactions among a small number of neighbors. However, for a slowly decaying channel and densely populated interferers, a small size neighborhood often results in nontrivial link outages and is thus insufficient for making optimal scheduling decisions. A question arises how to deal with the information outside a neighborhood in distributed link-scheduling. In this work, we develop joint approximation of information and distributed link scheduling. We first apply machine learning approaches to model distributed link-scheduling with complete information. We then characterize the information outside a neighborhood in form of residual interference as a random loss variable. The loss variable is further characterized by either a Mean Field approximation or a normal distribution based on the Lyapunov central limit theorem. The approximated information outside a neighborhood is incorporated in a factor graph. This results in joint approximation and distributed link-scheduling in an iterative fashion. Link-scheduling decisions are first made at each individual node based on the approximated loss variables. Loss variables are then updated and used for next link-scheduling decisions. The algorithm repeats between these two phases until convergence. Interactive iterations among these variables are implemented with a message-passing algorithm over a factor graph. Simulation results show that using learned information outside a neighborhood jointly with distributed link-scheduling reduces the outage probability close to zero even for a small neighborhood.", "source": "arxiv/ml"}
{"id": "arxiv:1252", "title": "Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach", "text": "We study the task of cleaning scanned text documents that are strongly corrupted by dirt such as manual line strokes, spilled ink etc. We aim at autonomously removing dirt from a single letter-size page based only on the information the page contains. Our approach, therefore, has to learn character representations without supervision and requires a mechanism to distinguish learned representations from irregular patterns. To learn character representations, we use a probabilistic generative model parameterizing pattern features, feature variances, the features' planar arrangements, and pattern frequencies. The latent variables of the model describe pattern class, pattern position, and the presence or absence of individual pattern features. The model parameters are optimized using a novel variational EM approximation. After learning, the parameters represent, independently of their absolute position, planar feature arrangements and their variances. A quality measure defined based on the learned representation then allows for an autonomous discrimination between regular character patterns and the irregular patterns making up the dirt. The irregular patterns can thus be removed to clean the document. For a full Latin alphabet we found that a single page does not contain sufficiently many character examples. However, even if heavily corrupted by dirt, we show that a page containing a lower number of character types can efficiently and autonomously be cleaned solely based on the structural regularity of the characters it contains. In different examples using characters from different alphabets, we demonstrate generality of the approach and discuss its implications for future developments.", "source": "arxiv/ml"}
{"id": "arxiv:1253", "title": "Acoustical Quality Assessment of the Classroom Environment", "text": "Teaching is one of the most important factors affecting any education system. Many research efforts have been conducted to facilitate the presentation modes used by instructors in classrooms as well as provide means for students to review lectures through web browsers. Other studies have been made to provide acoustical design recommendations for classrooms like room size and reverberation times. However, using acoustical features of classrooms as a way to provide education systems with feedback about the learning process was not thoroughly investigated in any of these studies. We propose a system that extracts different sound features of students and instructors, and then uses machine learning techniques to evaluate the acoustical quality of any learning environment. We infer conclusions about the students' satisfaction with the quality of lectures. Using classifiers instead of surveys and other subjective ways of measures can facilitate and speed such experiments which enables us to perform them continuously. We believe our system enables education systems to continuously review and improve their teaching strategies and acoustical quality of classrooms.", "source": "arxiv/ml"}
{"id": "arxiv:1254", "title": "Combining Heterogeneous Classifiers for Relational Databases", "text": "Most enterprise data is distributed in multiple relational databases with expert-designed schema. Using traditional single-table machine learning techniques over such data not only incur a computational penalty for converting to a 'flat' form (mega-join), even the human-specified semantic information present in the relations is lost. In this paper, we present a practical, two-phase hierarchical meta-classification algorithm for relational databases with a semantic divide and conquer approach. We propose a recursive, prediction aggregation technique over heterogeneous classifiers applied on individual database tables. The proposed algorithm was evaluated on three diverse datasets, namely TPCH, PKDD and UCI benchmarks and showed considerable reduction in classification time without any loss of prediction accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:1255", "title": "A Spiking Neural Learning Classifier System", "text": "Learning Classifier Systems (LCS) are population-based reinforcement learners used in a wide variety of applications. This paper presents a LCS where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. We employ a constructivist model of growth of both neurons and dendrites that realise flexible learning by evolving structures of sufficient complexity to solve a well-known problem involving continuous, real-valued inputs. Additionally, we extend the system to enable temporal state decomposition. By allowing our LCS to chain together sequences of heterogeneous actions into macro-actions, it is shown to perform optimally in a problem where traditional methods can fail to find a solution in a reasonable amount of time. Our final system is tested on a simulated robotics platform.", "source": "arxiv/ml"}
{"id": "arxiv:1256", "title": "Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery", "text": "We consider the problem of using a factor model we call {\\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure and employ a variational EM training algorithm. Prior work on approximate inference for this model has not prioritized the ability to exploit parallel architectures and scale to enormous problem sizes. We present an inference procedure appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the ssRBM on the CIFAR-10 dataset. We evaluate our approach's potential for semi-supervised learning on subsets of CIFAR-10. We demonstrate state-of-the art self-taught learning performance on the STL-10 dataset and use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models' Transfer Learning Challenge.", "source": "arxiv/ml"}
{"id": "arxiv:1257", "title": "On the Lagrangian Biduality of Sparsity Minimization Problems", "text": "Recent results in Compressive Sensing have shown that, under certain conditions, the solution to an underdetermined system of linear equations with sparsity-based regularization can be accurately recovered by solving convex relaxations of the original problem. In this work, we present a novel primal-dual analysis on a class of sparsity minimization problems. We show that the Lagrangian bidual (i.e., the Lagrangian dual of the Lagrangian dual) of the sparsity minimization problems can be used to derive interesting convex relaxations: the bidual of the $\\ell_0$-minimization problem is the $\\ell_1$-minimization problem; and the bidual of the $\\ell_{0,1}$-minimization problem for enforcing group sparsity on structured data is the $\\ell_{1,\\infty}$-minimization problem. The analysis provides a means to compute per-instance non-trivial lower bounds on the (group) sparsity of the desired solutions. In a real-world application, the bidual relaxation improves the performance of a sparsity-based classification framework applied to robust face recognition.", "source": "arxiv/ml"}
{"id": "arxiv:1258", "title": "Adaptive Policies for Sequential Sampling under Incomplete Information and a Cost Constraint", "text": "We consider the problem of sequential sampling from a finite number of independent statistical populations to maximize the expected infinite horizon average outcome per period, under a constraint that the expected average sampling cost does not exceed an upper bound. The outcome distributions are not known. We construct a class of consistent adaptive policies, under which the average outcome converges with probability 1 to the true value under complete information for all distributions with finite means. We also compare the rate of convergence for various policies in this class using simulation.", "source": "arxiv/ml"}
{"id": "arxiv:1259", "title": "A metric learning perspective of SVM: on the relation of SVM and LMNN", "text": "Support Vector Machines, SVMs, and the Large Margin Nearest Neighbor algorithm, LMNN, are two very popular learning algorithms with quite different learning biases. In this paper we bring them into a unified view and show that they have a much stronger relation than what is commonly thought. We analyze SVMs from a metric learning perspective and cast them as a metric learning problem, a view which helps us uncover the relations of the two algorithms. We show that LMNN can be seen as learning a set of local SVM-like models in a quadratic space. Along the way and inspired by the metric-based interpretation of SVM s we derive a novel variant of SVMs, epsilon-SVM, to which LMNN is even more similar. We give a unified view of LMNN and the different SVM variants. Finally we provide some preliminary experiments on a number of benchmark datasets in which show that epsilon-SVM compares favorably both with respect to LMNN and SVM.", "source": "arxiv/ml"}
{"id": "arxiv:1260", "title": "A probabilistic methodology for multilabel classification", "text": "Multilabel classification is a relatively recent subfield of machine learning. Unlike to the classical approach, where instances are labeled with only one category, in multilabel classification, an arbitrary number of categories is chosen to label an instance. Due to the problem complexity (the solution is one among an exponential number of alternatives), a very common solution (the binary method) is frequently used, learning a binary classifier for every category, and combining them all afterwards. The assumption taken in this solution is not realistic, and in this work we give examples where the decisions for all the labels are not taken independently, and thus, a supervised approach should learn those existing relationships among categories to make a better classification. Therefore, we show here a generic methodology that can improve the results obtained by a set of independent probabilistic binary classifiers, by using a combination procedure with a classifier trained on the co-occurrences of the labels. We show an exhaustive experimentation in three different standard corpora of labeled documents (Reuters-21578, Ohsumed-23 and RCV1), which present noticeable improvements in all of them, when using our methodology, in three probabilistic base classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:1261", "title": "Adaptive Shortest-Path Routing under Unknown and Stochastically Varying Link States", "text": "We consider the adaptive shortest-path routing problem in wireless networks under unknown and stochastically varying link states. In this problem, we aim to optimize the quality of communication between a source and a destination through adaptive path selection. Due to the randomness and uncertainties in the network dynamics, the quality of each link varies over time according to a stochastic process with unknown distributions. After a path is selected for communication, the aggregated quality of all links on this path (e.g., total path delay) is observed. The quality of each individual link is not observable. We formulate this problem as a multi-armed bandit with dependent arms. We show that by exploiting arm dependencies, a regret polynomial with network size can be achieved while maintaining the optimal logarithmic order with time. This is in sharp contrast with the exponential regret order with network size offered by a direct application of the classic MAB policies that ignore arm dependencies. Furthermore, our results are obtained under a general model of link-quality distributions (including heavy-tailed distributions) and find applications in cognitive radio and ad hoc networks with unknown and dynamic communication environments.", "source": "arxiv/ml"}
{"id": "arxiv:1262", "title": "Unsupervised Classification Using Immune Algorithm", "text": "Unsupervised classification algorithm based on clonal selection principle named Unsupervised Clonal Selection Classification (UCSC) is proposed in this paper. The new proposed algorithm is data driven and self-adaptive, it adjusts its parameters to the data to make the classification operation as fast as possible. The performance of UCSC is evaluated by comparing it with the well known K-means algorithm using several artificial and real-life data sets. The experiments show that the proposed UCSC algorithm is more reliable and has high classification precision comparing to traditional classification methods such as K-means.", "source": "arxiv/ml"}
{"id": "arxiv:1263", "title": "An Efficient Primal-Dual Prox Method for Non-Smooth Optimization", "text": "We study the non-smooth optimization problems in machine learning, where both the loss function and the regularizer are non-smooth functions. Previous studies on efficient empirical loss minimization assume either a smooth loss function or a strongly convex regularizer, making them unsuitable for non-smooth optimization. We develop a simple yet efficient method for a family of non-smooth optimization problems where the dual form of the loss function is bilinear in primal and dual variables. We cast a non-smooth optimization problem into a minimax optimization problem, and develop a primal dual prox method that solves the minimax optimization problem at a rate of $O(1/T)$ {assuming that the proximal step can be efficiently solved}, significantly faster than a standard subgradient descent method that has an $O(1/\\sqrt{T})$ convergence rate. Our empirical study verifies the efficiency of the proposed method for various non-smooth optimization problems that arise ubiquitously in machine learning by comparing it to the state-of-the-art first order methods.", "source": "arxiv/ml"}
{"id": "arxiv:1264", "title": "On Constrained Spectral Clustering and Its Applications", "text": "Constrained clustering has been well-studied for algorithms such as $K$-means and hierarchical clustering. However, how to satisfy many constraints in these algorithmic settings has been shown to be intractable. One alternative to encode many constraints is to use spectral clustering, which remains a developing area. In this paper, we propose a flexible framework for constrained spectral clustering. In contrast to some previous efforts that implicitly encode Must-Link and Cannot-Link constraints by modifying the graph Laplacian or constraining the underlying eigenspace, we present a more natural and principled formulation, which explicitly encodes the constraints as part of a constrained optimization problem. Our method offers several practical advantages: it can encode the degree of belief in Must-Link and Cannot-Link constraints; it guarantees to lower-bound how well the given constraints are satisfied using a user-specified threshold; it can be solved deterministically in polynomial time through generalized eigendecomposition. Furthermore, by inheriting the objective function from spectral clustering and encoding the constraints explicitly, much of the existing analysis of unconstrained spectral clustering techniques remains valid for our formulation. We validate the effectiveness of our approach by empirical results on both artificial and real datasets. We also demonstrate an innovative use of encoding large number of constraints: transfer learning via constraints.", "source": "arxiv/ml"}
{"id": "arxiv:1265", "title": "Discrete and fuzzy dynamical genetic programming in the XCSF learning classifier system", "text": "A number of representation schemes have been presented for use within learning classifier systems, ranging from binary encodings to neural networks. This paper presents results from an investigation into using discrete and fuzzy dynamical system representations within the XCSF learning classifier system. In particular, asynchronous random Boolean networks are used to represent the traditional condition-action production system rules in the discrete case and asynchronous fuzzy logic networks in the continuous-valued case. It is shown possible to use self-adaptive, open-ended evolution to design an ensemble of such dynamical systems within XCSF to solve a number of well-known test problems.", "source": "arxiv/ml"}
{"id": "arxiv:1266", "title": "A Comparison Between Data Mining Prediction Algorithms for Fault Detection(Case study: Ahanpishegan co.)", "text": "In the current competitive world, industrial companies seek to manufacture products of higher quality which can be achieved by increasing reliability, maintainability and thus the availability of products. On the other hand, improvement in products lifecycle is necessary for achieving high reliability. Typically, maintenance activities are aimed to reduce failures of industrial machinery and minimize the consequences of such failures. So the industrial companies try to improve their efficiency by using different fault detection techniques. One strategy is to process and analyze previous generated data to predict future failures. The purpose of this paper is to detect wasted parts using different data mining algorithms and compare the accuracy of these algorithms. A combination of thermal and physical characteristics has been used and the algorithms were implemented on Ahanpishegan's current data to estimate the availability of its produced parts. Keywords: Data Mining, Fault Detection, Availability, Prediction Algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1267", "title": "Real-time jam-session support system", "text": "We propose a method for the problem of real time chord accompaniment of improvised music. Our implementation can learn an underlying structure of the musical performance and predict next chord. The system uses Hidden Markov Model to find the most probable chord sequence for the played melody and then a Variable Order Markov Model is used to a) learn the structure (if any) and b) predict next chord. We implemented our system in Java and MAX/Msp and compared and evaluated using objective (prediction accuracy) and subjective (questionnaire) evaluation methods.", "source": "arxiv/ml"}
{"id": "arxiv:1268", "title": "Active Learning of Custering with Side Information Using $\\eps$-Smooth Relative Regret Approximations", "text": "Clustering is considered a non-supervised learning setting, in which the goal is to partition a collection of data points into disjoint clusters. Often a bound $k$ on the number of clusters is given or assumed by the practitioner. Many versions of this problem have been defined, most notably $k$-means and $k$-median. An underlying problem with the unsupervised nature of clustering it that of determining a similarity function. One approach for alleviating this difficulty is known as clustering with side information, alternatively, semi-supervised clustering. Here, the practitioner incorporates side information in the form of \"must be clustered\" or \"must be separated\" labels for data point pairs. Each such piece of information comes at a \"query cost\" (often involving human response solicitation). The collection of labels is then incorporated in the usual clustering algorithm as either strict or as soft constraints, possibly adding a pairwise constraint penalty function to the chosen clustering objective. Our work is mostly related to clustering with side information. We ask how to choose the pairs of data points. Our analysis gives rise to a method provably better than simply choosing them uniformly at random. Roughly speaking, we show that the distribution must be biased so as more weight is placed on pairs incident to elements in smaller clusters in some optimal solution. Of course we do not know the optimal solution, hence we don't know the bias. Using the recently introduced method of $\\eps$-smooth relative regret approximations of Ailon, Begleiter and Ezra, we can show an iterative process that improves both the clustering and the bias in tandem. The process provably converges to the optimal solution faster (in terms of query cost) than an algorithm selecting pairs uniformly.", "source": "arxiv/ml"}
{"id": "arxiv:1269", "title": "Random Feature Maps for Dot Product Kernels", "text": "Approximating non-linear kernels using feature maps has gained a lot of interest in recent years due to applications in reducing training and testing times of SVM classifiers and other kernel based learning algorithms. We extend this line of work and present low distortion embeddings for dot product kernels into linear Euclidean spaces. We base our results on a classical result in harmonic analysis characterizing all dot product kernels and use it to define randomized feature maps into explicit low dimensional Euclidean spaces in which the native dot product provides an approximation to the dot product kernel with high confidence.", "source": "arxiv/ml"}
{"id": "arxiv:1270", "title": "Empowerment for Continuous Agent-Environment Systems", "text": "This paper develops generalizations of empowerment to continuous states. Empowerment is a recently introduced information-theoretic quantity motivated by hypotheses about the efficiency of the sensorimotor loop in biological organisms, but also from considerations stemming from curiosity-driven learning. Empowemerment measures, for agent-environment systems with stochastic transitions, how much influence an agent has on its environment, but only that influence that can be sensed by the agent sensors. It is an information-theoretic generalization of joint controllability (influence on environment) and observability (measurement by sensors) of the environment by the agent, both controllability and observability being usually defined in control theory as the dimensionality of the control/observation spaces. Earlier work has shown that empowerment has various interesting and relevant properties, e.g., it allows us to identify salient states using only the dynamics, and it can act as intrinsic reward without requiring an external reward. However, in this previous work empowerment was limited to the case of small-scale and discrete domains and furthermore state transition probabilities were assumed to be known. The goal of this paper is to extend empowerment to the significantly more important and relevant case of continuous vector-valued state spaces and initially unknown state transition probabilities. The continuous state space is addressed by Monte-Carlo approximation; the unknown transitions are addressed by model learning and prediction for which we apply Gaussian processes regression with iterated forecasting. In a number of well-known continuous control tasks we examine the dynamics induced by empowerment and include an application to exploration and online model learning.", "source": "arxiv/ml"}
{"id": "arxiv:1271", "title": "Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-like Exploration", "text": "We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achieve low sample complexity. To achieve low sample complexity, since the environment is unknown, an agent must intelligently balance exploration and exploitation, and must be able to rapidly generalize from observations. While in the past a number of related sample efficient RL algorithms have been proposed, to allow theoretical analysis, mainly model-learners with weak generalization capabilities were considered. Here, we separate function approximation in the model learner (which does require samples) from the interpolation in the planner (which does not require samples). For model-learning we apply Gaussian processes regression (GP) which is able to automatically adjust itself to the complexity of the problem (via Bayesian hyperparameter selection) and, in practice, often able to learn a highly accurate model from very little data. In addition, a GP provides a natural way to determine the uncertainty of its predictions, which allows us to implement the \"optimism in the face of uncertainty\" principle used to efficiently control exploration. Our method is evaluated on four common benchmark domains.", "source": "arxiv/ml"}
{"id": "arxiv:1272", "title": "Feature Selection for Value Function Approximation Using Bayesian Model Selection", "text": "Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of the main challenges in scaling RL to real-world applications. Here we consider the Gaussian process based framework GPTD for approximate policy evaluation, and propose feature selection through marginal likelihood optimization of the associated hyperparameters. Our approach has two appealing benefits: (1) given just sample transitions, we can solve the policy evaluation problem fully automatically (without looking at the learning task, and, in theory, independent of the dimensionality of the state space), and (2) model selection allows us to consider more sophisticated kernels, which in turn enable us to identify relevant subspaces and eliminate irrelevant state variables such that we can achieve substantial computational savings and improved prediction performance.", "source": "arxiv/ml"}
{"id": "arxiv:1273", "title": "Learning RoboCup-Keepaway with Kernels", "text": "We apply kernel-based methods to solve the difficult reinforcement learning problem of 3vs2 keepaway in RoboCup simulated soccer. Key challenges in keepaway are the high-dimensionality of the state space (rendering conventional discretization-based function approximation like tilecoding infeasible), the stochasticity due to noise and multiple learning agents needing to cooperate (meaning that the exact dynamics of the environment are unknown) and real-time learning (meaning that an efficient online implementation is required). We employ the general framework of approximate policy iteration with least-squares-based policy evaluation. As underlying function approximator we consider the family of regularization networks with subset of regressors approximation. The core of our proposed solution is an efficient recursive implementation with automatic supervised selection of relevant basis functions. Simulation results indicate that the behavior learned through our approach clearly outperforms the best results obtained earlier with tilecoding by Stone et al. (2005).", "source": "arxiv/ml"}
{"id": "arxiv:1274", "title": "Kernels on Sample Sets via Nonparametric Divergence Estimates", "text": "Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest. Here we consider extending machine learning algorithms to operate on groups of data points. We suggest treating a group of data points as an i.i.d. sample set from an underlying feature distribution for that group. Our approach employs kernel machines with a kernel on i.i.d. sample sets of vectors. We define certain kernel functions on pairs of distributions, and then use a nonparametric estimator to consistently estimate those functions based on sample sets. The projection of the estimated Gram matrix to the cone of symmetric positive semi-definite matrices enables us to use kernel machines for classification, regression, anomaly detection, and low-dimensional embedding in the space of distributions. We present several numerical experiments both on real and simulated datasets to demonstrate the advantages of our new approach.", "source": "arxiv/ml"}
{"id": "arxiv:1275", "title": "Minimax Rates of Estimation for Sparse PCA in High Dimensions", "text": "We study sparse principal components analysis in the high-dimensional setting, where $p$ (the number of variables) can be much larger than $n$ (the number of observations). We prove optimal, non-asymptotic lower and upper bounds on the minimax estimation error for the leading eigenvector when it belongs to an $\\ell_q$ ball for $q \\in [0,1]$. Our bounds are sharp in $p$ and $n$ for all $q \\in [0, 1]$ over a wide class of distributions. The upper bound is obtained by analyzing the performance of $\\ell_q$-constrained PCA. In particular, our results provide convergence rates for $\\ell_1$-constrained PCA.", "source": "arxiv/ml"}
{"id": "arxiv:1276", "title": "A Reconstruction Error Formulation for Semi-Supervised Multi-task and Multi-view Learning", "text": "A significant challenge to make learning techniques more suitable for general purpose use is to move beyond i) complete supervision, ii) low dimensional data, iii) a single task and single view per instance. Solving these challenges allows working with \"Big Data\" problems that are typically high dimensional with multiple (but possibly incomplete) labelings and views. While other work has addressed each of these problems separately, in this paper we show how to address them together, namely semi-supervised dimension reduction for multi-task and multi-view learning (SSDR-MML), which performs optimization for dimension reduction and label inference in semi-supervised setting. The proposed framework is designed to handle both multi-task and multi-view learning settings, and can be easily adapted to many useful applications. Information obtained from all tasks and views is combined via reconstruction errors in a linear fashion that can be efficiently solved using an alternating optimization scheme. Our formulation has a number of advantages. We explicitly model the information combining mechanism as a data structure (a weight/nearest-neighbor matrix) which allows investigating fundamental questions in multi-task and multi-view learning. We address one such question by presenting a general measure to quantify the success of simultaneous learning of multiple tasks or from multiple views. We show that our SSDR-MML approach can outperform many state-of-the-art baseline methods and demonstrate the effectiveness of connecting dimension reduction and learning.", "source": "arxiv/ml"}
{"id": "arxiv:1277", "title": "Cramer Rao-Type Bounds for Sparse Bayesian Learning", "text": "In this paper, we derive Hybrid, Bayesian and Marginalized Cram\\'{e}r-Rao lower bounds (HCRB, BCRB and MCRB) for the single and multiple measurement vector Sparse Bayesian Learning (SBL) problem of estimating compressible vectors and their prior distribution parameters. We assume the unknown vector to be drawn from a compressible Student-t prior distribution. We derive CRBs that encompass the deterministic or random nature of the unknown parameters of the prior distribution and the regression noise variance. We extend the MCRB to the case where the compressible vector is distributed according to a general compressible prior distribution, of which the generalized Pareto distribution is a special case. We use the derived bounds to uncover the relationship between the compressibility and Mean Square Error (MSE) in the estimates. Further, we illustrate the tightness and utility of the bounds through simulations, by comparing them with the MSE performance of two popular SBL-based estimators. It is found that the MCRB is generally the tightest among the bounds derived and that the MSE performance of the Expectation-Maximization (EM) algorithm coincides with the MCRB for the compressible vector. Through simulations, we demonstrate the dependence of the MSE performance of SBL based estimators on the compressibility of the vector for several values of the number of observations and at different signal powers.", "source": "arxiv/ml"}
{"id": "arxiv:1278", "title": "rFerns: An Implementation of the Random Ferns Method for General-Purpose Machine Learning", "text": "In this paper I present an extended implementation of the Random ferns algorithm contained in the R package rFerns. It differs from the original by the ability of consuming categorical and numerical attributes instead of only binary ones. Also, instead of using simple attribute subspace ensemble it employs bagging and thus produce error approximation and variable importance measure modelled after Random forest algorithm. I also present benchmarks' results which show that although Random ferns' accuracy is mostly smaller than achieved by Random forest, its speed and good quality of importance measure it provides make rFerns a reasonable choice for a specific applications.", "source": "arxiv/ml"}
{"id": "arxiv:1279", "title": "Contextual Bandit Learning with Predictable Rewards", "text": "Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a realizability assumption: there exists a function in a (known) function class, always capable of predicting the expected reward, given the action and context. Under this assumption, we show three things. We present a new algorithm---Regressor Elimination--- with a regret similar to the agnostic setting (i.e. in the absence of realizability assumption). We prove a new lower bound showing no algorithm can achieve superior performance in the worst case even with the realizability assumption. However, we do show that for any set of policies (mapping contexts to actions), there is a distribution over rewards (given context) such that our new algorithm has constant regret unlike the previous approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1280", "title": "Information Forests", "text": "We describe Information Forests, an approach to classification that generalizes Random Forests by replacing the splitting criterion of non-leaf nodes from a discriminative one -- based on the entropy of the label distribution -- to a generative one -- based on maximizing the information divergence between the class-conditional distributions in the resulting partitions. The basic idea consists of deferring classification until a measure of \"classification confidence\" is sufficiently high, and instead breaking down the data so as to maximize this measure. In an alternative interpretation, Information Forests attempt to partition the data into subsets that are \"as informative as possible\" for the purpose of the task, which is to classify the data. Classification confidence, or informative content of the subsets, is quantified by the Information Divergence. Our approach relates to active learning, semi-supervised learning, mixed generative/discriminative learning.", "source": "arxiv/ml"}
{"id": "arxiv:1281", "title": "On the Performance of Maximum Likelihood Inverse Reinforcement Learning", "text": "Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL specially suitable for the problem of apprenticeship learning. The task description is encoded in the form of a reward function of a Markov decision process (MDP). Several algorithms have been proposed to find the reward function corresponding to a set of demonstrations. One of the algorithms that has provided best results in different applications is a gradient method to optimize a policy squared error criterion. On a parallel line of research, other authors have presented recently a gradient approximation of the maximum likelihood estimate of the reward signal. In general, both approaches approximate the gradient estimate and the criteria at different stages to make the algorithm tractable and efficient. In this work, we provide a detailed description of the different methods to highlight differences in terms of reward estimation, policy similarity and computational costs. We also provide experimental results to evaluate the differences in performance of the methods.", "source": "arxiv/ml"}
{"id": "arxiv:1282", "title": "Predicting Contextual Sequences via Submodular Function Maximization", "text": "Sequence optimization, where the items in a list are ordered to maximize some reward has many applications such as web advertisement placement, search, and control libraries in robotics. Previous work in sequence optimization produces a static ordering that does not take any features of the item or context of the problem into account. In this work, we propose a general approach to order the items within the sequence based on the context (e.g., perceptual information, environment description, and goals). We take a simple, efficient, reduction-based approach where the choice and order of the items is established by repeatedly learning simple classifiers or regressors for each \"slot\" in the sequence. Our approach leverages recent work on submodular function maximization to provide a formal regret reduction from submodular sequence optimization to simple cost-sensitive prediction. We apply our contextual sequence prediction algorithm to optimize control libraries and demonstrate results on two robotics problems: manipulator trajectory prediction and mobile robot path planning.", "source": "arxiv/ml"}
{"id": "arxiv:1283", "title": "Active Bayesian Optimization: Minimizing Minimizer Entropy", "text": "The ultimate goal of optimization is to find the minimizer of a target function.However, typical criteria for active optimization often ignore the uncertainty about the minimizer. We propose a novel criterion for global optimization and an associated sequential active learning strategy using Gaussian processes.Our criterion is the reduction of uncertainty in the posterior distribution of the function minimizer. It can also flexibly incorporate multiple global minimizers. We implement a tractable approximation of the criterion and demonstrate that it obtains the global minimizer accurately compared to conventional Bayesian optimization criteria.", "source": "arxiv/ml"}
{"id": "arxiv:1284", "title": "Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers", "text": "Scene parsing, or semantic segmentation, consists in labeling each pixel in an image with the category of the object it belongs to. It is a challenging task that involves the simultaneous detection, segmentation and recognition of all the objects in the image. The scene parsing method proposed here starts by computing a tree of segments from a graph of pixel dissimilarities. Simultaneously, a set of dense feature vectors is computed which encodes regions of multiple sizes centered on each pixel. The feature extractor is a multiscale convolutional network trained from raw pixels. The feature vectors associated with the segments covered by each node in the tree are aggregated and fed to a classifier which produces an estimate of the distribution of object categories contained in the segment. A subset of tree nodes that cover the image are then selected so as to maximize the average \"purity\" of the class distributions, hence maximizing the overall likelihood that each segment will contain a single object. The convolutional network feature extractor is trained end-to-end from raw pixels, alleviating the need for engineered features. After training, the system is parameter free. The system yields record accuracies on the Stanford Background Dataset (8 classes), the Sift Flow Dataset (33 classes) and the Barcelona Dataset (170 classes) while being an order of magnitude faster than competing approaches, producing a 320 \\times 240 image labeling in less than 1 second.", "source": "arxiv/ml"}
{"id": "arxiv:1285", "title": "Craniofacial reconstruction as a prediction problem using a Latent Root Regression model", "text": "In this paper, we present a computer-assisted method for facial reconstruction. This method provides an estimation of the facial shape associated with unidentified skeletal remains. Current computer-assisted methods using a statistical framework rely on a common set of extracted points located on the bone and soft-tissue surfaces. Most of the facial reconstruction methods then consist of predicting the position of the soft-tissue surface points, when the positions of the bone surface points are known. We propose to use Latent Root Regression for prediction. The results obtained are then compared to those given by Principal Components Analysis linear models. In conjunction, we have evaluated the influence of the number of skull landmarks used. Anatomical skull landmarks are completed iteratively by points located upon geodesics which link these anatomical landmarks, thus enabling us to artificially increase the number of skull points. Facial points are obtained using a mesh-matching algorithm between a common reference mesh and individual soft-tissue surface meshes. The proposed method is validated in term of accuracy, based on a leave-one-out cross-validation test applied to a homogeneous database. Accuracy measures are obtained by computing the distance between the original face surface and its reconstruction. Finally, these results are discussed referring to current computer-assisted reconstruction facial techniques.", "source": "arxiv/ml"}
{"id": "arxiv:1286", "title": "Towards minimax policies for online linear optimization with bandit feedback", "text": "We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\\sqrt{d n \\log N}$ for any finite action set with $N$ actions, under the assumption that the instantaneous loss is bounded by 1. This shaves off an extraneous $\\sqrt{d}$ factor compared to previous works, and gives a regret bound of order $d \\sqrt{n \\log n}$ for any compact set of actions. Without further assumptions on the action set, this last bound is minimax optimal up to a logarithmic factor. Interestingly, our result also shows that the minimax regret for bandit linear optimization with expert advice in $d$ dimension is the same as for the basic $d$-armed bandit with expert advice. Our second contribution is to show how to use the Mirror Descent algorithm to obtain computationally efficient strategies with minimax optimal regret bounds in specific examples. More precisely we study two canonical action sets: the hypercube and the Euclidean ball. In the former case, we obtain the first computationally efficient algorithm with a $d \\sqrt{n}$ regret, thus improving by a factor $\\sqrt{d \\log n}$ over the best known result for a computationally efficient algorithm. In the latter case, our approach gives the first algorithm with a $\\sqrt{d n \\log n}$ regret, again shaving off an extraneous $\\sqrt{d}$ compared to previous works.", "source": "arxiv/ml"}
{"id": "arxiv:1287", "title": "Mirror Descent Meets Fixed Share (and feels no regret)", "text": "Mirror descent with an entropic regularizer is known to achieve shifting regret bounds that are logarithmic in the dimension. This is done using either a carefully designed projection or by a weight sharing technique. Via a novel unified analysis, we show that these two approaches deliver essentially equivalent bounds on a notion of regret generalizing shifting, adaptive, discounted, and other related regrets. Our analysis also captures and extends the generalized weight sharing technique of Bousquet and Warmuth, and can be refined in several ways, including improvements for small losses and adaptive tuning of parameters.", "source": "arxiv/ml"}
{"id": "arxiv:1288", "title": "An efficient high-quality hierarchical clustering algorithm for automatic inference of software architecture from the source code of a software system", "text": "It is a high-quality algorithm for hierarchical clustering of large software source code. This effectively allows to break the complexity of tens of millions lines of source code, so that a human software engineer can comprehend a software system at high level by means of looking at its architectural diagram that is reconstructed automatically from the source code of the software system. The architectural diagram shows a tree of subsystems having OOP classes in its leaves (in the other words, a nested software decomposition). The tool reconstructs the missing (inconsistent/incomplete/inexistent) architectural documentation for a software system from its source code. This facilitates software maintenance: change requests can be performed substantially faster. Simply speaking, this unique tool allows to lift the comprehensible grain of object-oriented software systems from OOP class-level to subsystem-level. It is estimated that a commercial tool, developed on the basis of this work, will reduce software maintenance expenses 10 times on the current needs, and will allow to implement next-generation software systems which are currently too complex to be within the range of human comprehension, therefore can't yet be designed or implemented. Implemented prototype in Open Source: http://sourceforge.net/p/insoar/code-0/1/tree/", "source": "arxiv/ml"}
{"id": "arxiv:1289", "title": "Near-optimal Coresets For Least-Squares Regression", "text": "We study (constrained) least-squares regression as well as multiple response least-squares regression and ask the question of whether a subset of the data, a coreset, suffices to compute a good approximate solution to the regression. We give deterministic, low order polynomial-time algorithms to construct such coresets with approximation guarantees, together with lower bounds indicating that there is not much room for improvement upon our results.", "source": "arxiv/ml"}
{"id": "arxiv:1290", "title": "Finding a most biased coin with fewest flips", "text": "We study the problem of learning a most biased coin among a set of coins by tossing the coins adaptively. The goal is to minimize the number of tosses until we identify a coin i* whose posterior probability of being most biased is at least 1-delta for a given delta. Under a particular probabilistic model, we give an optimal algorithm, i.e., an algorithm that minimizes the expected number of future tosses. The problem is closely related to finding the best arm in the multi-armed bandit problem using adaptive strategies. Our algorithm employs an optimal adaptive strategy -- a strategy that performs the best possible action at each step after observing the outcomes of all previous coin tosses. Consequently, our algorithm is also optimal for any starting history of outcomes. To our knowledge, this is the first algorithm that employs an optimal adaptive strategy under a Bayesian setting for this problem. Our proof of optimality employs tools from the field of Markov games.", "source": "arxiv/ml"}
{"id": "arxiv:1291", "title": "Guaranteed clustering and biclustering via semidefinite programming", "text": "Identifying clusters of similar objects in data plays a significant role in a wide range of applications. As a model problem for clustering, we consider the densest k-disjoint-clique problem, whose goal is to identify the collection of k disjoint cliques of a given weighted complete graph maximizing the sum of the densities of the complete subgraphs induced by these cliques. In this paper, we establish conditions ensuring exact recovery of the densest k cliques of a given graph from the optimal solution of a particular semidefinite program. In particular, the semidefinite relaxation is exact for input graphs corresponding to data consisting of k large, distinct clusters and a smaller number of outliers. This approach also yields a semidefinite relaxation for the biclustering problem with similar recovery guarantees. Given a set of objects and a set of features exhibited by these objects, biclustering seeks to simultaneously group the objects and features according to their expression levels. This problem may be posed as partitioning the nodes of a weighted bipartite complete graph such that the sum of the densities of the resulting bipartite complete subgraphs is maximized. As in our analysis of the densest k-disjoint-clique problem, we show that the correct partition of the objects and features can be recovered from the optimal solution of a semidefinite program in the case that the given data consists of several disjoint sets of objects exhibiting similar features. Empirical evidence from numerical experiments supporting these theoretical guarantees is also provided.", "source": "arxiv/ml"}
{"id": "arxiv:1292", "title": "Active Diagnosis via AUC Maximization: An Efficient Approach for Multiple Fault Identification in Large Scale, Noisy Networks", "text": "The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary states of a set of objects (e.g., faulty or working) by sequentially selecting, and observing, (noisy) responses to binary valued queries. Current algorithms in this area rely on loopy belief propagation for active query selection. These algorithms have an exponential time complexity, making them slow and even intractable in large networks. We propose a rank-based greedy algorithm that sequentially chooses queries such that the area under the ROC curve of the rank-based output is maximized. The AUC criterion allows us to make a simplifying assumption that significantly reduces the complexity of active query selection (from exponential to near quadratic), with little or no compromise on the performance quality.", "source": "arxiv/ml"}
{"id": "arxiv:1293", "title": "Semi-supervised Learning with Density Based Distances", "text": "We present a simple, yet effective, approach to Semi-Supervised Learning. Our approach is based on estimating density-based distances (DBD) using a shortest path calculation on a graph. These Graph-DBD estimates can then be used in any distance-based supervised learning method, such as Nearest Neighbor methods and SVMs with RBF kernels. In order to apply the method to very large data sets, we also present a novel algorithm which integrates nearest neighbor computations into the shortest path search and can find exact shortest paths even in extremely large dense graphs. Significant runtime improvement over the commonly used Laplacian regularization method is then shown on a large scale dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1294", "title": "Near-Optimal Target Learning With Stochastic Binary Signals", "text": "We study learning in a noisy bisection model: specifically, Bayesian algorithms to learn a target value V given access only to noisy realizations of whether V is less than or greater than a threshold theta. At step t = 0, 1, 2, ..., the learner sets threshold theta t and observes a noisy realization of sign(V - theta t). After T steps, the goal is to output an estimate V^ which is within an eta-tolerance of V . This problem has been studied, predominantly in environments with a fixed error probability q < 1/2 for the noisy realization of sign(V - theta t). In practice, it is often the case that q can approach 1/2, especially as theta -> V, and there is little known when this happens. We give a pseudo-Bayesian algorithm which provably converges to V. When the true prior matches our algorithm's Gaussian prior, we show near-optimal expected performance. Our methods extend to the general multiple-threshold setting where the observation noisily indicates which of k >= 2 regions V belongs to.", "source": "arxiv/ml"}
{"id": "arxiv:1295", "title": "Smoothing Proximal Gradient Method for General Structured Sparse Learning", "text": "We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of such penalties as our motivating examples: 1) overlapping group lasso penalty, based on the l1/l2 mixed-norm penalty, and 2) graph-guided fusion penalty. For both types of penalties, due to their non-separability, developing an efficient optimization method has remained a challenging problem. In this paper, we propose a general optimization approach, called smoothing proximal gradient method, which can solve the structured sparse regression problems with a smooth convex loss and a wide spectrum of structured-sparsity-inducing penalties. Our approach is based on a general smoothing technique of Nesterov. It achieves a convergence rate faster than the standard first-order method, subgradient method, and is much more scalable than the most widely used interior-point method. Numerical results are reported to demonstrate the efficiency and scalability of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1296", "title": "Ensembles of Kernel Predictors", "text": "This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corresponding hypothesis sets, the introduction and analysis of a learning algorithm based on these hypothesis sets, and a series of experiments using ensembles of kernel predictors with several data sets. Both convex combinations of kernel-based hypotheses and more general Lq-regularized nonnegative combinations are analyzed. These theoretical, algorithmic, and empirical results are compared with those achieved by using learning kernel techniques, which can be viewed as another approach for solving the same problem.", "source": "arxiv/ml"}
{"id": "arxiv:1297", "title": "Active Learning for Developing Personalized Treatment", "text": "The personalization of treatment via bio-markers and other risk categories has drawn increasing interest among clinical scientists. Personalized treatment strategies can be learned using data from clinical trials, but such trials are very costly to run. This paper explores the use of active learning techniques to design more efficient trials, addressing issues such as whom to recruit, at what point in the trial, and which treatment to assign, throughout the duration of the trial. We propose a minimax bandit model with two different optimization criteria, and discuss the computational challenges and issues pertaining to this approach. We evaluate our active learning policies using both simulated data, and data modeled after a clinical trial for treating depressed individuals, and contrast our methods with other plausible active learning policies.", "source": "arxiv/ml"}
{"id": "arxiv:1298", "title": "Boosting as a Product of Experts", "text": "In this paper, we derive a novel probabilistic model of boosting as a Product of Experts. We re-derive the boosting algorithm as a greedy incremental model selection procedure which ensures that addition of new experts to the ensemble does not decrease the likelihood of the data. These learning rules lead to a generic boosting algorithm - POE- Boost which turns out to be similar to the AdaBoost algorithm under certain assumptions on the expert probabilities. The paper then extends the POEBoost algorithm to POEBoost.CS which handles hypothesis that produce probabilistic predictions. This new algorithm is shown to have better generalization performance compared to other state of the art algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1299", "title": "PAC-Bayesian Policy Evaluation for Reinforcement Learning", "text": "Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution. This paper introduces the first PAC-Bayesian bound for the batch reinforcement learning problem with function approximation. We show how this bound can be used to perform model-selection in a transfer learning scenario. Our empirical results confirm that PAC-Bayesian policy evaluation is able to leverage prior distributions when they are informative and, unlike standard Bayesian RL approaches, ignore them when they are misleading.", "source": "arxiv/ml"}
{"id": "arxiv:1300", "title": "Hierarchical Affinity Propagation", "text": "Affinity propagation is an exemplar-based clustering algorithm that finds a set of data-points that best exemplify the data, and associates each datapoint with one exemplar. We extend affinity propagation in a principled way to solve the hierarchical clustering problem, which arises in a variety of domains including biology, sensor networks and decision making in operational research. We derive an inference algorithm that operates by propagating information up and down the hierarchy, and is efficient despite the high-order potentials required for the graphical model formulation. We demonstrate that our method outperforms greedy techniques that cluster one layer at a time. We show that on an artificial dataset designed to mimic the HIV-strain mutation dynamics, our method outperforms related methods. For real HIV sequences, where the ground truth is not available, we show our method achieves better results, in terms of the underlying objective function, and show the results correspond meaningfully to geographical location and strain subtypes. Finally we report results on using the method for the analysis of mass spectra, showing it performs favorably compared to state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:1301", "title": "Generalized Fisher Score for Feature Selection", "text": "Fisher score is one of the most widely used supervised feature selection methods. However, it selects each feature independently according to their scores under the Fisher criterion, which leads to a suboptimal subset of features. In this paper, we present a generalized Fisher score to jointly select features. It aims at finding an subset of features, which maximize the lower bound of traditional Fisher score. The resulting feature selection problem is a mixed integer programming, which can be reformulated as a quadratically constrained linear programming (QCLP). It is solved by cutting plane algorithm, in each iteration of which a multiple kernel learning problem is solved alternatively by multivariate ridge regression and projected gradient descent. Experiments on benchmark data sets indicate that the proposed method outperforms Fisher score as well as many other state-of-the-art feature selection methods.", "source": "arxiv/ml"}
{"id": "arxiv:1302", "title": "Active Semi-Supervised Learning using Submodular Functions", "text": "We consider active, semi-supervised learning in an offline transductive setting. We show that a previously proposed error bound for active learning on undirected weighted graphs can be generalized by replacing graph cut with an arbitrary symmetric submodular function. Arbitrary non-symmetric submodular functions can be used via symmetrization. Different choices of submodular functions give different versions of the error bound that are appropriate for different kinds of problems. Moreover, the bound is deterministic and holds for adversarially chosen labels. We show exactly minimizing this error bound is NP-complete. However, we also introduce for any submodular function an associated active semi-supervised learning method that approximately minimizes the corresponding error bound. We show that the error bound is tight in the sense that there is no other bound of the same form which is better. Our theoretical results are supported by experiments on real data.", "source": "arxiv/ml"}
{"id": "arxiv:1303", "title": "Bregman divergence as general framework to estimate unnormalized statistical models", "text": "We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent estimation methods such as noise-contrastive estimation, ratio matching, and score matching belong to the proposed framework, and explain their interconnection based on supervised learning. Further, we discuss the role of boosting in unsupervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:1304", "title": "Sequential Inference for Latent Force Models", "text": "Latent force models (LFMs) are hybrid models combining mechanistic principles with non-parametric components. In this article, we shall show how LFMs can be equivalently formulated and solved using the state variable approach. We shall also show how the Gaussian process prior used in LFMs can be equivalently formulated as a linear statespace model driven by a white noise process and how inference on the resulting model can be efficiently implemented using Kalman filter and smoother. Then we shall show how the recently proposed switching LFM can be reformulated using the state variable approach, and how we can construct a probabilistic model for the switches by formulating a similar switching LFM as a switching linear dynamic system (SLDS). We illustrate the performance of the proposed methodology in simulated scenarios and apply it to inferring the switching points in GPS data collected from car movement data in urban environment.", "source": "arxiv/ml"}
{"id": "arxiv:1305", "title": "What Cannot be Learned with Bethe Approximations", "text": "We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Bethe approximation. We show that there exists a regime of empirical marginals where such Bethe learning will fail. By failure we mean that the empirical marginals cannot be recovered from the approximated maximum likelihood parameters (i.e., moment matching is not achieved). We provide several conditions on empirical marginals that yield outer and inner bounds on the set of Bethe learnable marginals. An interesting implication of our results is that there exists a large class of marginals that cannot be obtained as stable fixed points of belief propagation. Taken together our results provide a novel approach to analyzing learning with Bethe approximations and highlight when it can be expected to work or fail.", "source": "arxiv/ml"}
{"id": "arxiv:1306", "title": "Sum-Product Networks: A New Deep Architecture", "text": "The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs). SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges. We show that if an SPN is complete and consistent it represents the partition function and all marginals of some graphical model, and give semantics to its nodes. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also strictly more general. We then propose learning algorithms for SPNs, based on backpropagation and EM. Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks. For example, SPNs perform image completion better than state-of-the-art deep networks for this task. SPNs also have intriguing potential connections to the architecture of the cortex.", "source": "arxiv/ml"}
{"id": "arxiv:1307", "title": "Lipschitz Parametrization of Probabilistic Graphical Models", "text": "We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the Kullback-Leibler divergence that allows understanding methods that penalize the lp-norm of differences of parameters as the minimization of that upper bound. The expected log-likelihood is lower bounded by the negative lp-norm, which allows understanding the generalization ability of probabilistic models. The exponential of the negative lp-norm is involved in the lower bound of the Bayes error rate, which shows that it is reasonable to use parameters as features in algorithms that rely on metric spaces (e.g. classification, dimensionality reduction, clustering). Our results do not rely on specific algorithms for learning the structure or parameters. We show preliminary results for activity recognition and temporal segmentation.", "source": "arxiv/ml"}
{"id": "arxiv:1308", "title": "Efficient Probabilistic Inference with Partial Ranking Queries", "text": "Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, typically forces one to make structural assumptions, such as smoothness, sparsity, or probabilistic independence about these underlying distributions. We approach the modeling problem from the computational principle that one should make structural assumptions which allow for efficient calculation of typical probabilistic queries. For ranking models, \"typical\" queries predominantly take the form of partial ranking queries (e.g., given a user's top-k favorite movies, what are his preferences over remaining movies?). In this paper, we argue that riffled independence factorizations proposed in recent literature [7, 8] are a natural structural assumption for ranking distributions, allowing for particularly efficient processing of partial ranking queries.", "source": "arxiv/ml"}
{"id": "arxiv:1309", "title": "Noisy-OR Models with Latent Confounding", "text": "Given a set of experiments in which varying subsets of observed variables are subject to intervention, we consider the problem of identifiability of causal models exhibiting latent confounding. While identifiability is trivial when each experiment intervenes on a large number of variables, the situation is more complicated when only one or a few variables are subject to intervention per experiment. For linear causal models with latent variables Hyttinen et al. (2010) gave precise conditions for when such data are sufficient to identify the full model. While their result cannot be extended to discrete-valued variables with arbitrary cause-effect relationships, we show that a similar result can be obtained for the class of causal models whose conditional probability distributions are restricted to a `noisy-OR' parameterization. We further show that identification is preserved under an extension of the model that allows for negative influences, and present learning algorithms that we test for accuracy, scalability and robustness.", "source": "arxiv/ml"}
{"id": "arxiv:1310", "title": "Discovering causal structures in binary exclusive-or skew acyclic models", "text": "Discovering causal relations among observed variables in a given data set is a main topic in studies of statistics and artificial intelligence. Recently, some techniques to discover an identifiable causal structure have been explored based on non-Gaussianity of the observed data distribution. However, most of these are limited to continuous data. In this paper, we present a novel causal model for binary data and propose a new approach to derive an identifiable causal structure governing the data based on skew Bernoulli distributions of external noise. Experimental evaluation shows excellent performance for both artificial and real world data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1311", "title": "Detecting low-complexity unobserved causes", "text": "We describe a method that infers whether statistical dependences between two observed variables X and Y are due to a \"direct\" causal link or only due to a connecting causal path that contains an unobserved variable of low complexity, e.g., a binary variable. This problem is motivated by statistical genetics. Given a genetic marker that is correlated with a phenotype of interest, we want to detect whether this marker is causal or it only correlates with a causal one. Our method is based on the analysis of the location of the conditional distributions P(Y|x) in the simplex of all distributions of Y. We report encouraging results on semi-empirical data.", "source": "arxiv/ml"}
{"id": "arxiv:1312", "title": "Learning Determinantal Point Processes", "text": "Determinantal point processes (DPPs), which arise in random matrix theory and quantum physics, are natural models for subset selection problems where diversity is preferred. Among many remarkable properties, DPPs offer tractable algorithms for exact inference, including computing marginal probabilities and sampling; however, an important open question has been how to learn a DPP from labeled training data. In this paper we propose a natural feature-based parameterization of conditional DPPs, and show how it leads to a convex and efficient learning formulation. We analyze the relationship between our model and binary Markov random fields with repulsive potentials, which are qualitatively similar but computationally intractable. Finally, we apply our approach to the task of extractive summarization, where the goal is to choose a small subset of sentences conveying the most important information from a set of documents. In this task there is a fundamental tradeoff between sentences that are highly relevant to the collection as a whole, and sentences that are diverse and not repetitive. Our parameterization allows us to naturally balance these two characteristics. We evaluate our system on data from the DUC 2003/04 multi-document summarization task, achieving state-of-the-art results.", "source": "arxiv/ml"}
{"id": "arxiv:1313", "title": "Variational Algorithms for Marginal MAP", "text": "Marginal MAP problems are notoriously difficult tasks for graphical models. We derive a general variational framework for solving marginal MAP problems, in which we apply analogues of the Bethe, tree-reweighted, and mean field approximations. We then derive a \"mixed\" message passing algorithm and a convergent alternative using CCCP to solve the BP-type approximations. Theoretically, we give conditions under which the decoded solution is a global or local optimum, and obtain novel upper bounds on solutions. Experimentally we demonstrate that our algorithms outperform related approaches. We also show that EM and variational EM comprise a special case of our framework.", "source": "arxiv/ml"}
{"id": "arxiv:1314", "title": "Asymptotic Efficiency of Deterministic Estimators for Discrete Energy-Based Models: Ratio Matching and Pseudolikelihood", "text": "Standard maximum likelihood estimation cannot be applied to discrete energy-based models in the general case because the computation of exact model probabilities is intractable. Recent research has seen the proposal of several new estimators designed specifically to overcome this intractability, but virtually nothing is known about their theoretical properties. In this paper, we present a generalized estimator that unifies many of the classical and recently proposed estimators. We use results from the standard asymptotic theory for M-estimators to derive a generic expression for the asymptotic covariance matrix of our generalized estimator. We apply these results to study the relative statistical efficiency of classical pseudolikelihood and the recently-proposed ratio matching estimator.", "source": "arxiv/ml"}
{"id": "arxiv:1315", "title": "Reconstructing Pompeian Households", "text": "A database of objects discovered in houses in the Roman city of Pompeii provides a unique view of ordinary life in an ancient city. Experts have used this collection to study the structure of Roman households, exploring the distribution and variability of tasks in architectural spaces, but such approaches are necessarily affected by modern cultural assumptions. In this study we present a data-driven approach to household archeology, treating it as an unsupervised labeling problem. This approach scales to large data sets and provides a more objective complement to human interpretation.", "source": "arxiv/ml"}
{"id": "arxiv:1316", "title": "Conditional Restricted Boltzmann Machines for Structured Output Prediction", "text": "Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not applicable to conditional models and there has been almost no work on training and generating predictions from conditional RBMs for structured output problems. We first argue that standard Contrastive Divergence-based learning may not be suitable for training CRBMs. We then identify two distinct types of structured output prediction problems and propose an improved learning algorithm for each. The first problem type is one where the output space has arbitrary structure but the set of likely output configurations is relatively small, such as in multi-label classification. The second problem is one where the output space is arbitrarily structured but where the output space variability is much greater, such as in image denoising or pixel labeling. We show that the new learning algorithms can work much better than Contrastive Divergence on both types of problems.", "source": "arxiv/ml"}
{"id": "arxiv:1317", "title": "Fractional Moments on Bandit Problems", "text": "Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit problems are one such class of problems in stateless environments that represent this explore/exploit situation. We propose a learning algorithm for bandit problems based on fractional expectation of rewards acquired. The algorithm is theoretically shown to converge on an eta-optimal arm and achieve O(n) sample complexity. Experimental results show the algorithm incurs substantially lower regrets than parameter-optimized eta-greedy and SoftMax approaches and other low sample complexity state-of-the-art techniques.", "source": "arxiv/ml"}
{"id": "arxiv:1318", "title": "Multidimensional counting grids: Inferring word order from disordered bags of words", "text": "Models of bags of words typically assume topic mixing so that the words in a single bag come from a limited number of topics. We show here that many sets of bag of words exhibit a very different pattern of variation than the patterns that are efficiently captured by topic mixing. In many cases, from one bag of words to the next, the words disappear and new ones appear as if the theme slowly and smoothly shifted across documents (providing that the documents are somehow ordered). Examples of latent structure that describe such ordering are easily imagined. For example, the advancement of the date of the news stories is reflected in a smooth change over the theme of the day as certain evolving news stories fall out of favor and new events create new stories. Overlaps among the stories of consecutive days can be modeled by using windows over linearly arranged tight distributions over words. We show here that such strategy can be extended to multiple dimensions and cases where the ordering of data is not readily obvious. We demonstrate that this way of modeling covariation in word occurrences outperforms standard topic models in classification and prediction tasks in applications in biology, text modeling and computer vision.", "source": "arxiv/ml"}
{"id": "arxiv:1319", "title": "Partial Order MCMC for Structure Discovery in Bayesian Networks", "text": "We present a new Markov chain Monte Carlo method for estimating posterior probabilities of structural features in Bayesian networks. The method draws samples from the posterior distribution of partial orders on the nodes; for each sampled partial order, the conditional probabilities of interest are computed exactly. We give both analytical and empirical results that suggest the superiority of the new method compared to previous methods, which sample either directed acyclic graphs or linear orders on the nodes.", "source": "arxiv/ml"}
{"id": "arxiv:1320", "title": "Identifiability of Causal Graphs using Functional Models", "text": "This work addresses the following question: Under what assumptions on the data generating process can one infer the causal graph from the joint distribution? The approach taken by conditional independence-based causal discovery methods is based on two assumptions: the Markov condition and faithfulness. It has been shown that under these assumptions the causal graph can be identified up to Markov equivalence (some arrows remain undirected) using methods like the PC algorithm. In this work we propose an alternative by defining Identifiable Functional Model Classes (IFMOCs). As our main theorem we prove that if the data generating process belongs to an IFMOC, one can identify the complete causal graph. To the best of our knowledge this is the first identifiability result of this kind that is not limited to linear functional relationships. We discuss how the IFMOC assumption and the Markov and faithfulness assumptions relate to each other and explain why we believe that the IFMOC assumption can be tested more easily on given data. We further provide a practical algorithm that recovers the causal graph from finitely many data; experiments on simulated data support the theoretical findings.", "source": "arxiv/ml"}
{"id": "arxiv:1321", "title": "Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions", "text": "Low-dimensional embedding, manifold learning, clustering, classification, and anomaly detection are among the most important problems in machine learning. The existing methods usually consider the case when each instance has a fixed, finite-dimensional feature representation. Here we consider a different setting. We assume that each instance corresponds to a continuous probability distribution. These distributions are unknown, but we are given some i.i.d. samples from each distribution. Our goal is to estimate the distances between these distributions and use these distances to perform low-dimensional embedding, clustering/classification, or anomaly detection for the distributions. We present estimation algorithms, describe how to apply them for machine learning tasks on distributions, and show empirical results on synthetic data, real word images, and astronomical data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1322", "title": "Fast MCMC sampling for Markov jump processes and continuous time Bayesian networks", "text": "Markov jump processes and continuous time Bayesian networks are important classes of continuous time dynamical systems. In this paper, we tackle the problem of inferring unobserved paths in these models by introducing a fast auxiliary variable Gibbs sampler. Our approach is based on the idea of uniformization, and sets up a Markov chain over paths by sampling a finite set of virtual jump times and then running a standard hidden Markov model forward filtering-backward sampling algorithm over states at the set of extant and virtual jump times. We demonstrate significant computational benefits over a state-of-the-art Gibbs sampler on a number of continuous time Bayesian networks.", "source": "arxiv/ml"}
{"id": "arxiv:1323", "title": "New Probabilistic Bounds on Eigenvalues and Eigenvectors of Random Kernel Matrices", "text": "Kernel methods are successful approaches for different machine learning problems. This success is mainly rooted in using feature maps and kernel matrices. Some methods rely on the eigenvalues/eigenvectors of the kernel matrix, while for other methods the spectral information can be used to estimate the excess risk. An important question remains on how close the sample eigenvalues/eigenvectors are to the population values. In this paper, we improve earlier results on concentration bounds for eigenvalues of general kernel matrices. For distance and inner product kernel functions, e.g. radial basis functions, we provide new concentration bounds, which are characterized by the eigenvalues of the sample covariance matrix. Meanwhile, the obstacles for sharper bounds are accounted for and partially addressed. As a case study, we derive a concentration inequality for sample kernel target-alignment.", "source": "arxiv/ml"}
{"id": "arxiv:1324", "title": "An Efficient Algorithm for Computing Interventional Distributions in Latent Variable Causal Models", "text": "Probabilistic inference in graphical models is the task of computing marginal and conditional densities of interest from a factorized representation of a joint probability distribution. Inference algorithms such as variable elimination and belief propagation take advantage of constraints embedded in this factorization to compute such densities efficiently. In this paper, we propose an algorithm which computes interventional distributions in latent variable causal models represented by acyclic directed mixed graphs(ADMGs). To compute these distributions efficiently, we take advantage of a recursive factorization which generalizes the usual Markov factorization for DAGs and the more recent factorization for ADMGs. Our algorithm can be viewed as a generalization of variable elimination to the mixed graph case. We show our algorithm is exponential in the mixed graph generalization of treewidth.", "source": "arxiv/ml"}
{"id": "arxiv:1325", "title": "Learning mixed graphical models from data with p larger than n", "text": "Structure learning of Gaussian graphical models is an extensively studied problem in the classical multivariate setting where the sample size n is larger than the number of random variables p, as well as in the more challenging setting when p>>n. However, analogous approaches for learning the structure of graphical models with mixed discrete and continuous variables when p>>n remain largely unexplored. Here we describe a statistical learning procedure for this problem based on limited-order correlations and assess its performance with synthetic and real data.", "source": "arxiv/ml"}
{"id": "arxiv:1326", "title": "Robust learning Bayesian networks for prior belief", "text": "Recent reports have described that learning Bayesian networks are highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders some unstable or undesirable results. This paper describes some asymptotic analyses of BDeu to explain the reasons for the sensitivity and its effects. Furthermore, this paper presents a proposal for a robust learning score for ESS by eliminating the sensitive factors from the approximation of log-BDeu.", "source": "arxiv/ml"}
{"id": "arxiv:1327", "title": "Sparse matrix-variate Gaussian process blockmodels for network modeling", "text": "We face network data from various sources, such as protein interactions and online social networks. A critical problem is to model network interactions and identify latent groups of network nodes. This problem is challenging due to many reasons. For example, the network nodes are interdependent instead of independent of each other, and the data are known to be very noisy (e.g., missing edges). To address these challenges, we propose a new relational model for network data, Sparse Matrix-variate Gaussian process Blockmodel (SMGB). Our model generalizes popular bilinear generative models and captures nonlinear network interactions using a matrix-variate Gaussian process with latent membership variables. We also assign sparse prior distributions on the latent membership variables to learn sparse group assignments for individual network nodes. To estimate the latent variables efficiently from data, we develop an efficient variational expectation maximization method. We compared our approaches with several state-of-the-art network models on both synthetic and real-world network datasets. Experimental results demonstrate SMGBs outperform the alternative approaches in terms of discovering latent classes or predicting unknown interactions.", "source": "arxiv/ml"}
{"id": "arxiv:1328", "title": "Hierarchical Maximum Margin Learning for Multi-Class Classification", "text": "Due to myriads of classes, designing accurate and efficient classifiers becomes very challenging for multi-class classification. Recent research has shown that class structure learning can greatly facilitate multi-class learning. In this paper, we propose a novel method to learn the class structure for multi-class classification problems. The class structure is assumed to be a binary hierarchical tree. To learn such a tree, we propose a maximum separating margin method to determine the child nodes of any internal node. The proposed method ensures that two classgroups represented by any two sibling nodes are most separable. In the experiments, we evaluate the accuracy and efficiency of the proposed method over other multi-class classification methods on real world large-scale problems. The results show that the proposed method outperforms benchmark methods in terms of accuracy for most datasets and performs comparably with other class structure learning methods in terms of efficiency for all datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1329", "title": "Tightening MRF Relaxations with Planar Subproblems", "text": "We describe a new technique for computing lower-bounds on the minimum energy configuration of a planar Markov Random Field (MRF). Our method successively adds large numbers of constraints and enforces consistency over binary projections of the original problem state space. These constraints are represented in terms of subproblems in a dual-decomposition framework that is optimized using subgradient techniques. The complete set of constraints we consider enforces cycle consistency over the original graph. In practice we find that the method converges quickly on most problems with the addition of a few subproblems and outperforms existing methods for some interesting classes of hard potentials.", "source": "arxiv/ml"}
{"id": "arxiv:1330", "title": "Rank/Norm Regularization with Closed-Form Solutions: Application to Subspace Clustering", "text": "When data is sampled from an unknown subspace, principal component analysis (PCA) provides an effective way to estimate the subspace and hence reduce the dimension of the data. At the heart of PCA is the Eckart-Young-Mirsky theorem, which characterizes the best rank k approximation of a matrix. In this paper, we prove a generalization of the Eckart-Young-Mirsky theorem under all unitarily invariant norms. Using this result, we obtain closed-form solutions for a set of rank/norm regularized problems, and derive closed-form solutions for a general class of subspace clustering problems (where data is modelled by unions of unknown subspaces). From these results we obtain new theoretical insights and promising experimental results.", "source": "arxiv/ml"}
{"id": "arxiv:1331", "title": "Risk Bounds for Infinitely Divisible Distribution", "text": "In this paper, we study the risk bounds for samples independently drawn from an infinitely divisible (ID) distribution. In particular, based on a martingale method, we develop two deviation inequalities for a sequence of random variables of an ID distribution with zero Gaussian component. By applying the deviation inequalities, we obtain the risk bounds based on the covering number for the ID distribution. Finally, we analyze the asymptotic convergence of the risk bound derived from one of the two deviation inequalities and show that the convergence rate of the bound is faster than the result for the generic i.i.d. empirical process (Mendelson, 2003).", "source": "arxiv/ml"}
{"id": "arxiv:1332", "title": "Kernel-based Conditional Independence Test and Application in Causal Discovery", "text": "Conditional independence testing is an important problem, especially in Bayesian network learning and causal discovery. Due to the curse of dimensionality, testing for conditional independence of continuous variables is particularly challenging. We propose a Kernel-based Conditional Independence test (KCI-test), by constructing an appropriate test statistic and deriving its asymptotic distribution under the null hypothesis of conditional independence. The proposed method is computationally efficient and easy to implement. Experimental results show that it outperforms other methods, especially when the conditioning set is large or the sample size is not very large, in which case other methods encounter difficulties.", "source": "arxiv/ml"}
{"id": "arxiv:1333", "title": "Smoothing Multivariate Performance Measures", "text": "A Support Vector Method for multivariate performance measures was recently introduced by Joachims (2005). The underlying optimization problem is currently solved using cutting plane methods such as SVM-Perf and BMRM. One can show that these algorithms converge to an eta accurate solution in O(1/Lambda*e) iterations, where lambda is the trade-off parameter between the regularizer and the loss function. We present a smoothing strategy for multivariate performance scores, in particular precision/recall break-even point and ROCArea. When combined with Nesterov's accelerated gradient algorithm our smoothing strategy yields an optimization algorithm which converges to an eta accurate solution in O(min{1/e,1/sqrt(lambda*e)}) iterations. Furthermore, the cost per iteration of our scheme is the same as that of SVM-Perf and BMRM. Empirical evaluation on a number of publicly available datasets shows that our method converges significantly faster than cutting plane methods without sacrificing generalization ability.", "source": "arxiv/ml"}
{"id": "arxiv:1334", "title": "Sparse Topical Coding", "text": "We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic topic models, STC relaxes the normalization constraint of admixture proportions and the constraint of defining a normalized likelihood function. Such relaxations make STC amenable to: 1) directly control the sparsity of inferred representations by using sparsity-inducing regularizers; 2) be seamlessly integrated with a convex error function (e.g., SVM hinge loss) for supervised learning; and 3) be efficiently learned with a simply structured coordinate descent algorithm. Our results demonstrate the advantages of STC and supervised MedSTC on identifying topical meanings of words and improving classification accuracy and time efficiency.", "source": "arxiv/ml"}
{"id": "arxiv:1335", "title": "Testing whether linear equations are causal: A free probability theory approach", "text": "We propose a method that infers whether linear relations between two high-dimensional variables X and Y are due to a causal influence from X to Y or from Y to X. The earlier proposed so-called Trace Method is extended to the regime where the dimension of the observed variables exceeds the sample size. Based on previous work, we postulate conditions that characterize a causal relation between X and Y. Moreover, we describe a statistical test and argue that both causal directions are typically rejected if there is a common cause. A full theoretical analysis is presented for the deterministic case but our approach seems to be valid for the noisy case, too, for which we additionally present an approach based on a sparsity constraint. The discussed method yields promising results for both simulated and real world data.", "source": "arxiv/ml"}
{"id": "arxiv:1336", "title": "Graphical Models for Bandit Problems", "text": "We introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large, yet succinctly specify the payoffs for any context-action pair. Our main result is an algorithm for such models whose regret is bounded by the number of parameters and whose running time depends only on the treewidth of the graph substructure induced by the action space.", "source": "arxiv/ml"}
{"id": "arxiv:1337", "title": "PAC Bounds for Discounted MDPs", "text": "We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two possible next-states and prove a new bound for a UCRL-style algorithm on the number of time-steps when it is not Probably Approximately Correct (PAC). The new lower bound strengthens previous work by being both more general (it applies to all policies) and tighter. The upper and lower bounds match up to logarithmic factors.", "source": "arxiv/ml"}
{"id": "arxiv:1338", "title": "Generalized Principal Component Analysis (GPCA)", "text": "This paper presents an algebro-geometric solution to the problem of segmenting an unknown number of subspaces of unknown and varying dimensions from sample data points. We represent the subspaces with a set of homogeneous polynomials whose degree is the number of subspaces and whose derivatives at a data point give normal vectors to the subspace passing through the point. When the number of subspaces is known, we show that these polynomials can be estimated linearly from data; hence, subspace segmentation is reduced to classifying one point per subspace. We select these points optimally from the data set by minimizing certain distance function, thus dealing automatically with moderate noise in the data. A basis for the complement of each subspace is then recovered by applying standard PCA to the collection of derivatives (normal vectors). Extensions of GPCA that deal with data in a high- dimensional space and with an unknown number of subspaces are also presented. Our experiments on low-dimensional data show that GPCA outperforms existing algebraic algorithms based on polynomial factorization and provides a good initialization to iterative techniques such as K-subspaces and Expectation Maximization. We also present applications of GPCA to computer vision problems such as face clustering, temporal video segmentation, and 3D motion segmentation from point correspondences in multiple affine views.", "source": "arxiv/ml"}
{"id": "arxiv:1339", "title": "On the Sample Complexity of Predictive Sparse Coding", "text": "The goal of predictive sparse coding is to learn a representation of examples as sparse linear combinations of elements from a dictionary, such that a learned hypothesis linear in the new representation performs well on a predictive task. Predictive sparse coding algorithms recently have demonstrated impressive performance on a variety of supervised tasks, but their generalization properties have not been studied. We establish the first generalization error bounds for predictive sparse coding, covering two settings: 1) the overcomplete setting, where the number of features k exceeds the original dimensionality d; and 2) the high or infinite-dimensional setting, where only dimension-free bounds are useful. Both learning bounds intimately depend on stability properties of the learned sparse encoder, as measured on the training sample. Consequently, we first present a fundamental stability result for the LASSO, a result characterizing the stability of the sparse codes with respect to perturbations to the dictionary. In the overcomplete setting, we present an estimation error bound that decays as \\tilde{O}(sqrt(d k/m)) with respect to d and k. In the high or infinite-dimensional setting, we show a dimension-free bound that is \\tilde{O}(sqrt(k^2 s / m)) with respect to k and s, where s is an upper bound on the number of non-zeros in the sparse code for any training data point.", "source": "arxiv/ml"}
{"id": "arxiv:1340", "title": "The best of both worlds: stochastic and adversarial bandits", "text": "We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3 (Auer et al., SIAM J. on Computing 2002) and the (poly)logarithmic regret of UCB1 (Auer et al., Machine Learning 2002) for stochastic rewards. Adversarial rewards and stochastic rewards are the two main settings in the literature on (non-Bayesian) multi-armed bandits. Prior work on multi-armed bandits treats them separately, and does not attempt to jointly optimize for both. Our result falls into a general theme of achieving good worst-case performance while also taking advantage of \"nice\" problem instances, an important issue in the design of algorithms with partially known inputs.", "source": "arxiv/ml"}
{"id": "arxiv:1341", "title": "(weak) Calibration is Computationally Hard", "text": "We show that the existence of a computationally efficient calibration algorithm, with a low weak calibration rate, would imply the existence of an efficient algorithm for computing approximate Nash equilibria - thus implying the unlikely conclusion that every problem in PPAD is solvable in polynomial time.", "source": "arxiv/ml"}
{"id": "arxiv:1342", "title": "Metabolic cost as an organizing principle for cooperative learning", "text": "This paper investigates how neurons can use metabolic cost to facilitate learning at a population level. Although decision-making by individual neurons has been extensively studied, questions regarding how neurons should behave to cooperate effectively remain largely unaddressed. Under assumptions that capture a few basic features of cortical neurons, we show that constraining reward maximization by metabolic cost aligns the information content of actions with their expected reward. Thus, metabolic cost provides a mechanism whereby neurons encode expected reward into their outputs. Further, aside from reducing energy expenditures, imposing a tight metabolic constraint also increases the accuracy of empirical estimates of rewards, increasing the robustness of distributed learning. Finally, we present two implementations of metabolically constrained learning that confirm our theoretical finding. These results suggest that metabolic cost may be an organizing principle underlying the neural code, and may also provide a useful guide to the design and analysis of other cooperating populations.", "source": "arxiv/ml"}
{"id": "arxiv:1343", "title": "Min Max Generalization for Two-stage Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes", "text": "We study the minmax optimization problem introduced in [22] for computing policies for batch mode reinforcement learning in a deterministic setting. First, we show that this problem is NP-hard. In the two-stage case, we provide two relaxation schemes. The first relaxation scheme works by dropping some constraints in order to obtain a problem that is solvable in polynomial time. The second relaxation scheme, based on a Lagrangian relaxation where all constraints are dualized, leads to a conic quadratic programming problem. We also theoretically prove and empirically illustrate that both relaxation schemes provide better results than those given in [22].", "source": "arxiv/ml"}
{"id": "arxiv:1344", "title": "Classification approach based on association rules mining for unbalanced data", "text": "This paper deals with the binary classification task when the target class has the lower probability of occurrence. In such situation, it is not possible to build a powerful classifier by using standard methods such as logistic regression, classification tree, discriminant analysis, etc. To overcome this short-coming of these methods which yield classifiers with low sensibility, we tackled the classification problem here through an approach based on the association rules learning. This approach has the advantage of allowing the identification of the patterns that are well correlated with the target class. Association rules learning is a well known method in the area of data-mining. It is used when dealing with large database for unsupervised discovery of local patterns that expresses hidden relationships between input variables. In considering association rules from a supervised learning point of view, a relevant set of weak classifiers is obtained from which one derives a classifier that performs well.", "source": "arxiv/ml"}
{"id": "arxiv:1345", "title": "Hybrid Batch Bayesian Optimization", "text": "Bayesian Optimization aims at optimizing an unknown non-convex/concave function that is costly to evaluate. We are interested in application scenarios where concurrent function evaluations are possible. Under such a setting, BO could choose to either sequentially evaluate the function, one input at a time and wait for the output of the function before making the next selection, or evaluate the function at a batch of multiple inputs at once. These two different settings are commonly referred to as the sequential and batch settings of Bayesian Optimization. In general, the sequential setting leads to better optimization performance as each function evaluation is selected with more information, whereas the batch setting has an advantage in terms of the total experimental time (the number of iterations). In this work, our goal is to combine the strength of both settings. Specifically, we systematically analyze Bayesian optimization using Gaussian process as the posterior estimator and provide a hybrid algorithm that, based on the current state, dynamically switches between a sequential policy and a batch policy with variable batch sizes. We provide theoretical justification for our algorithm and present experimental results on eight benchmark BO problems. The results show that our method achieves substantial speedup (up to %78) compared to a pure sequential policy, without suffering any significant performance loss.", "source": "arxiv/ml"}
{"id": "arxiv:1346", "title": "Clustering using Max-norm Constrained Optimization", "text": "We suggest using the max-norm as a convex surrogate constraint for clustering. We show how this yields a better exact cluster recovery guarantee than previously suggested nuclear-norm relaxation, and study the effectiveness of our method, and other related convex relaxations, compared to other clustering approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1347", "title": "Training Restricted Boltzmann Machines on Word Observations", "text": "The restricted Boltzmann machine (RBM) is a flexible tool for modeling complex data, however there have been significant computational difficulties in using RBMs to model high-dimensional multinomial observations. In natural language processing applications, words are naturally modeled by K-ary discrete distributions, where K is determined by the vocabulary size and can easily be in the hundreds of thousands. The conventional approach to training RBMs on word observations is limited because it requires sampling the states of K-way softmax visible units during block Gibbs updates, an operation that takes time linear in K. In this work, we address this issue by employing a more general class of Markov chain Monte Carlo operators on the visible units, yielding updates with computational complexity independent of K. We demonstrate the success of our approach by training RBMs on hundreds of millions of word n-grams using larger vocabularies than previously feasible and using the learned features to improve performance on chunking and sentiment classification tasks, achieving state-of-the-art results on the latter.", "source": "arxiv/ml"}
{"id": "arxiv:1348", "title": "Efficiently Sampling Multiplicative Attribute Graphs Using a Ball-Dropping Process", "text": "We introduce a novel and efficient sampling algorithm for the Multiplicative Attribute Graph Model (MAGM - Kim and Leskovec (2010)}). Our algorithm is \\emph{strictly} more efficient than the algorithm proposed by Yun and Vishwanathan (2012), in the sense that our method extends the \\emph{best} time complexity guarantee of their algorithm to a larger fraction of parameter space. Both in theory and in empirical evaluation on sparse graphs, our new algorithm outperforms the previous one. To design our algorithm, we first define a stochastic \\emph{ball-dropping process} (BDP). Although a special case of this process was introduced as an efficient approximate sampling algorithm for the Kronecker Product Graph Model (KPGM - Leskovec et al. (2010)}), neither \\emph{why} such an approximation works nor \\emph{what} is the actual distribution this process is sampling from has been addressed so far to the best of our knowledge. Our rigorous treatment of the BDP enables us to clarify the rational behind a BDP approximation of KPGM, and design an efficient sampling algorithm for the MAGM.", "source": "arxiv/ml"}
{"id": "arxiv:1349", "title": "Protocols for Learning Classifiers on Distributed Data", "text": "We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the processing of massive distributed datasets. We present several very general sampling-based solutions as well as some two-way protocols which have a provable exponential speed-up over any one-way protocol. We focus on core problems for noiseless data distributed across two or more nodes. The techniques we introduce are reminiscent of active learning, but rather than actively probing labels, nodes actively communicate with each other, each node simultaneously learning the important data from another node.", "source": "arxiv/ml"}
{"id": "arxiv:1350", "title": "Nonlinear Laplacian spectral analysis: Capturing intermittent and low-frequency spatiotemporal patterns in high-dimensional data", "text": "We present a technique for spatiotemporal data analysis called nonlinear Laplacian spectral analysis (NLSA), which generalizes singular spectrum analysis (SSA) to take into account the nonlinear manifold structure of complex data sets. The key principle underlying NLSA is that the functions used to represent temporal patterns should exhibit a degree of smoothness on the nonlinear data manifold M; a constraint absent from classical SSA. NLSA enforces such a notion of smoothness by requiring that temporal patterns belong in low-dimensional Hilbert spaces V_l spanned by the leading l Laplace-Beltrami eigenfunctions on M. These eigenfunctions can be evaluated efficiently in high ambient-space dimensions using sparse graph-theoretic algorithms. Moreover, they provide orthonormal bases to expand a family of linear maps, whose singular value decomposition leads to sets of spatiotemporal patterns at progressively finer resolution on the data manifold. The Riemannian measure of M and an adaptive graph kernel width enhances the capability of NLSA to detect important nonlinear processes, including intermittency and rare events. The minimum dimension of V_l required to capture these features while avoiding overfitting is estimated here using spectral entropy criteria.", "source": "arxiv/ml"}
{"id": "arxiv:1351", "title": "Distributed Power Allocation with SINR Constraints Using Trial and Error Learning", "text": "In this paper, we address the problem of global transmit power minimization in a self-congiguring network where radio devices are subject to operate at a minimum signal to interference plus noise ratio (SINR) level. We model the network as a parallel Gaussian interference channel and we introduce a fully decentralized algorithm (based on trial and error) able to statistically achieve a congiguration where the performance demands are met. Contrary to existing solutions, our algorithm requires only local information and can learn stable and efficient working points by using only one bit feedback. We model the network under two different game theoretical frameworks: normal form and satisfaction form. We show that the converging points correspond to equilibrium points, namely Nash and satisfaction equilibrium. Similarly, we provide sufficient conditions for the algorithm to converge in both formulations. Moreover, we provide analytical results to estimate the algorithm's performance, as a function of the network parameters. Finally, numerical results are provided to validate our theoretical conclusions. Keywords: Learning, power control, trial and error, Nash equilibrium, spectrum sharing.", "source": "arxiv/ml"}
{"id": "arxiv:1352", "title": "Confusion Matrix Stability Bounds for Multiclass Classification", "text": "In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is that we propose to use the confusion matrix of a classifier as a measure of its quality; our contribution is in the line of work which attempts to set up and study the statistical properties of new evaluation measures such as, e.g. ROC curves. In the confusion-based learning framework we propose, we claim that a targetted objective is to minimize the size of the confusion matrix C, measured through its operator norm ||C||. We derive generalization bounds on the (size of the) confusion matrix in an extended framework of uniform stability, adapted to the case of matrix valued loss. Pivotal to our study is a very recent matrix concentration inequality that generalizes McDiarmid's inequality. As an illustration of the relevance of our theoretical results, we show how two SVM learning procedures can be proved to be confusion-friendly. To the best of our knowledge, the present paper is the first that focuses on the confusion matrix from a theoretical point of view.", "source": "arxiv/ml"}
{"id": "arxiv:1353", "title": "PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification", "text": "In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classifier as an error measure; this puts our contribution in the line of work aiming at dealing with performance measure that are richer than mere scalar criterion such as the misclassification rate. Thanks to very recent and beautiful results on matrix concentration inequalities, we derive two bounds showing that the true confusion risk of the Gibbs classifier is upper-bounded by its empirical risk plus a term depending on the number of training examples in each class. To the best of our knowledge, this is the first PAC-Bayes bounds based on confusion matrices.", "source": "arxiv/ml"}
{"id": "arxiv:1354", "title": "A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets", "text": "We propose a new stochastic gradient method for optimizing the sum of a finite set of smooth functions, where the sum is strongly convex. While standard stochastic gradient methods converge at sublinear rates for this problem, the proposed method incorporates a memory of previous gradient values in order to achieve a linear convergence rate. In a machine learning context, numerical experiments indicate that the new algorithm can dramatically outperform standard algorithms, both in terms of optimizing the training error and reducing the test error quickly.", "source": "arxiv/ml"}
{"id": "arxiv:1355", "title": "Learning from Distributions via Support Measure Machines", "text": "This paper presents a kernel-based discriminative learning framework on probability measures. Rather than relying on large collections of vectorial training examples, our framework learns using a collection of probability distributions that have been constructed to meaningfully represent training data. By representing these probability distributions as mean embeddings in the reproducing kernel Hilbert space (RKHS), we are able to apply many standard kernel-based learning techniques in straightforward fashion. To accomplish this, we construct a generalization of the support vector machine (SVM) called a support measure machine (SMM). Our analyses of SMMs provides several insights into their relationship to traditional SVMs. Based on such insights, we propose a flexible SVM (Flex-SVM) that places different kernel functions on each training example. Experimental results on both synthetic and real-world data demonstrate the effectiveness of our proposed framework.", "source": "arxiv/ml"}
{"id": "arxiv:1356", "title": "mlpy: Machine Learning Python", "text": "mlpy is a Python Open Source Machine Learning library built on top of NumPy/SciPy and the GNU Scientific Libraries. mlpy provides a wide range of state-of-the-art machine learning methods for supervised and unsupervised problems and it is aimed at finding a reasonable compromise among modularity, maintainability, reproducibility, usability and efficiency. mlpy is multiplatform, it works with Python 2 and 3 and it is distributed under GPL3 at the website http://mlpy.fbk.eu.", "source": "arxiv/ml"}
{"id": "arxiv:1357", "title": "Inference in Hidden Markov Models with Explicit State Duration Distributions", "text": "In this letter we borrow from the inference techniques developed for unbounded state-cardinality (nonparametric) variants of the HMM and use them to develop a tuning-parameter free, black-box inference procedure for Explicit-state-duration hidden Markov models (EDHMM). EDHMMs are HMMs that have latent states consisting of both discrete state-indicator and discrete state-duration random variables. In contrast to the implicit geometric state duration distribution possessed by the standard HMM, EDHMMs allow the direct parameterisation and estimation of per-state duration distributions. As most duration distributions are defined over the positive integers, truncation or other approximations are usually required to perform EDHMM inference.", "source": "arxiv/ml"}
{"id": "arxiv:1358", "title": "A Bayesian Approach to Discovering Truth from Conflicting Sources for Data Integration", "text": "In practical data integration systems, it is common for the data sources being integrated to provide conflicting information about the same entity. Consequently, a major challenge for data integration is to derive the most complete and accurate integrated records from diverse and sometimes conflicting sources. We term this challenge the truth finding problem. We observe that some sources are generally more reliable than others, and therefore a good model of source quality is the key to solving the truth finding problem. In this work, we propose a probabilistic graphical model that can automatically infer true records and source quality without any supervision. In contrast to previous methods, our principled approach leverages a generative process of two types of errors (false positive and false negative) by modeling two different aspects of source quality. In so doing, ours is also the first approach designed to merge multi-valued attribute types. Our method is scalable, due to an efficient sampling-based inference algorithm that needs very few iterations in practice and enjoys linear time complexity, with an even faster incremental variant. Experiments on two real world datasets show that our new method outperforms existing state-of-the-art approaches to the truth finding problem.", "source": "arxiv/ml"}
{"id": "arxiv:1359", "title": "Scaling Datalog for Machine Learning on Big Data", "text": "In this paper, we present the case for a declarative foundation for data-intensive machine learning systems. Instead of creating a new system for each specific flavor of machine learning task, or hardcoding new optimizations, we argue for the use of recursive queries to program a variety of machine learning systems. By taking this approach, database query optimization techniques can be utilized to identify effective execution plans, and the resulting runtime plans can be executed on a single unified data-parallel query processing engine. As a proof of concept, we consider two programming models--Pregel and Iterative Map-Reduce-Update---from the machine learning domain, and show how they can be captured in Datalog, tuned for a specific task, and then compiled into an optimized physical plan. Experiments performed on a large computing cluster with real data demonstrate that this declarative approach can provide very good performance while offering both increased generality and programming ease.", "source": "arxiv/ml"}
{"id": "arxiv:1360", "title": "Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization", "text": "The use of Reinforcement Learning in real-world scenarios is strongly limited by issues of scale. Most RL learning algorithms are unable to deal with problems composed of hundreds or sometimes even dozens of possible actions, and therefore cannot be applied to many real-world problems. We consider the RL problem in the supervised classification framework where the optimal policy is obtained through a multiclass classifier, the set of classes being the set of actions of the problem. We introduce error-correcting output codes (ECOCs) in this setting and propose two new methods for reducing complexity when using rollouts-based approaches. The first method consists in using an ECOC-based classifier as the multiclass classifier, reducing the learning complexity from O(A2) to O(Alog(A)). We then propose a novel method that profits from the ECOC's coding dictionary to split the initial MDP into O(log(A)) seperate two-action MDPs. This second method reduces learning complexity even further, from O(A2) to O(log(A)), thus rendering problems with large action sets tractable. We finish by experimentally demonstrating the advantages of our approach on a set of benchmark problems, both in speed and performance.", "source": "arxiv/ml"}
{"id": "arxiv:1361", "title": "Application of Gist SVM in Cancer Detection", "text": "In this paper, we study the application of GIST SVM in disease prediction (detection of cancer). Pattern classification problems can be effectively solved by Support vector machines. Here we propose a classifier which can differentiate patients having benign and malignant cancer cells. To improve the accuracy of classification, we propose to determine the optimal size of the training set and perform feature selection. To find the optimal size of the training set, different sizes of training sets are experimented and the one with highest classification rate is selected. The optimal features are selected through their F-Scores.", "source": "arxiv/ml"}
{"id": "arxiv:1362", "title": "Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation", "text": "The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the relative Pearson divergence as a divergence measure, and it is accurately and efficiently estimated by a method of direct density-ratio estimation. Through experiments on artificial and real-world datasets including human-activity sensing, speech, and Twitter messages, we demonstrate the usefulness of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1363", "title": "Algorithms for Learning Kernels Based on Centered Alignment", "text": "This paper presents new and effective algorithms for learning kernels. In particular, as shown by our empirical results, these algorithms consistently outperform the so-called uniform combination solution that has proven to be difficult to improve upon in the past, as well as other algorithms for learning kernels based on convex combinations of base kernels in both classification and regression. Our algorithms are based on the notion of centered alignment which is used as a similarity measure between kernels or kernel matrices. We present a number of novel algorithmic, theoretical, and empirical results for learning kernels based on our notion of centered alignment. In particular, we describe efficient algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP and discuss a one-stage algorithm for learning both a kernel and a hypothesis based on that kernel using an alignment-based regularization. Our theoretical results include a novel concentration bound for centered alignment between kernel matrices, the proof of the existence of effective predictors for kernels with high alignment, both for classification and for regression, and the proof of stability-based generalization bounds for a broad family of algorithms for learning kernels based on centered alignment. We also report the results of experiments with our centered alignment-based algorithms in both classification and regression.", "source": "arxiv/ml"}
{"id": "arxiv:1364", "title": "Learning DNF Expressions from Fourier Spectrum", "text": "Since its introduction by Valiant in 1984, PAC learning of DNF expressions remains one of the central problems in learning theory. We consider this problem in the setting where the underlying distribution is uniform, or more generally, a product distribution. Kalai, Samorodnitsky and Teng (2009) showed that in this setting a DNF expression can be efficiently approximated from its \"heavy\" low-degree Fourier coefficients alone. This is in contrast to previous approaches where boosting was used and thus Fourier coefficients of the target function modified by various distributions were needed. This property is crucial for learning of DNF expressions over smoothed product distributions, a learning model introduced by Kalai et al. (2009) and inspired by the seminal smoothed analysis model of Spielman and Teng (2001). We introduce a new approach to learning (or approximating) a polynomial threshold functions which is based on creating a function with range [-1,1] that approximately agrees with the unknown function on low-degree Fourier coefficients. We then describe conditions under which this is sufficient for learning polynomial threshold functions. Our approach yields a new, simple algorithm for approximating any polynomial-size DNF expression from its \"heavy\" low-degree Fourier coefficients alone. Our algorithm greatly simplifies the proof of learnability of DNF expressions over smoothed product distributions. We also describe an application of our algorithm to learning monotone DNF expressions over product distributions. Building on the work of Servedio (2001), we give an algorithm that runs in time $\\poly((s \\cdot \\log{(s/\\eps)})^{\\log{(s/\\eps)}}, n)$, where $s$ is the size of the target DNF expression and $\\eps$ is the accuracy. This improves on $\\poly((s \\cdot \\log{(ns/\\eps)})^{\\log{(s/\\eps)} \\cdot \\log{(1/\\eps)}}, n)$ bound of Servedio (2001).", "source": "arxiv/ml"}
{"id": "arxiv:1365", "title": "Checking Tests for Read-Once Functions over Arbitrary Bases", "text": "A Boolean function is called read-once over a basis B if it can be expressed by a formula over B where no variable appears more than once. A checking test for a read-once function f over B depending on all its variables is a set of input vectors distinguishing f from all other read-once functions of the same variables. We show that every read-once function f over B has a checking test containing O(n^l) vectors, where n is the number of relevant variables of f and l is the largest arity of functions in B. For some functions, this bound cannot be improved by more than a constant factor. The employed technique involves reconstructing f from its l-variable projections and provides a stronger form of Kuznetsov's classic theorem on read-once representations.", "source": "arxiv/ml"}
{"id": "arxiv:1366", "title": "A Method of Moments for Mixture Models and Hidden Markov Models", "text": "Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics (e.g., the EM algorithm) which are prone to failure, and existing consistent methods are unfavorable due to their high computational and sample complexity which typically scale exponentially with the number of mixture components. This work develops an efficient method of moments approach to parameter estimation for a broad class of high-dimensional mixture models with many components, including multi-view mixtures of Gaussians (such as mixtures of axis-aligned Gaussians) and hidden Markov models. The new method leads to rigorous unsupervised learning results for mixture models that were not achieved by previous works; and, because of its simplicity, it offers a viable alternative to EM for practical deployment.", "source": "arxiv/ml"}
{"id": "arxiv:1367", "title": "Learning High-Dimensional Mixtures of Graphical Models", "text": "We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable corresponding to the mixture components is hidden and each mixture component over the observed variables can have a potentially different Markov graph structure and parameters. We propose a novel approach for estimating the mixture components, and our output is a tree-mixture model which serves as a good approximation to the underlying graphical model mixture. Our method is efficient when the union graph, which is the union of the Markov graphs of the mixture components, has sparse vertex separators between any pair of observed variables. This includes tree mixtures and mixtures of bounded degree graphs. For such models, we prove that our method correctly recovers the union graph structure and the tree structures corresponding to maximum-likelihood tree approximations of the mixture components. The sample and computational complexities of our method scale as $\\poly(p, r)$, for an $r$-component mixture of $p$-variate graphical models. We further extend our results to the case when the union graph has sparse local separators between any pair of observed variables, such as mixtures of locally tree-like graphs, and the mixture components are in the regime of correlation decay.", "source": "arxiv/ml"}
{"id": "arxiv:1368", "title": "Infinite Shift-invariant Grouped Multi-task Learning for Gaussian Processes", "text": "Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task is a phase-shifted periodic time series. In particular, we develop a novel Bayesian nonparametric model capturing a mixture of Gaussian processes where each task is a sum of a group-specific function and a component capturing individual variation, in addition to each task being phase shifted. We develop an efficient \\textsc{em} algorithm to learn the parameters of the model. As a special case we obtain the Gaussian mixture model and \\textsc{em} algorithm for phased-shifted periodic time series. Furthermore, we extend the proposed model by using a Dirichlet Process prior and thereby leading to an infinite mixture model that is capable of doing automatic model selection. A Variational Bayesian approach is developed for inference in this model. Experiments in regression, classification and class discovery demonstrate the performance of the proposed models using both synthetic data and real-world time series data from astrophysics. Our methods are particularly useful when the time series are sparsely and non-synchronously sampled.", "source": "arxiv/ml"}
{"id": "arxiv:1369", "title": "Sparse Subspace Clustering: Algorithm, Theory, and Applications", "text": "In many real-world problems, we are dealing with collections of high-dimensional data, such as images, videos, text and web documents, DNA microarray data, and more. Often, high-dimensional data lie close to low-dimensional structures corresponding to several classes or categories the data belongs to. In this paper, we propose and study an algorithm, called Sparse Subspace Clustering (SSC), to cluster data points that lie in a union of low-dimensional subspaces. The key idea is that, among infinitely many possible representations of a data point in terms of other points, a sparse representation corresponds to selecting a few points from the same subspace. This motivates solving a sparse optimization program whose solution is used in a spectral clustering framework to infer the clustering of data into subspaces. Since solving the sparse optimization program is in general NP-hard, we consider a convex relaxation and show that, under appropriate conditions on the arrangement of subspaces and the distribution of data, the proposed minimization program succeeds in recovering the desired sparse representations. The proposed algorithm can be solved efficiently and can handle data points near the intersections of subspaces. Another key advantage of the proposed algorithm with respect to the state of the art is that it can deal with data nuisances, such as noise, sparse outlying entries, and missing entries, directly by incorporating the model of the data into the sparse optimization program. We demonstrate the effectiveness of the proposed algorithm through experiments on synthetic data as well as the two real-world problems of motion segmentation and face clustering.", "source": "arxiv/ml"}
{"id": "arxiv:1370", "title": "Agnostic System Identification for Model-Based Reinforcement Learning", "text": "A fundamental problem in control is to learn a model of a system from observations that is useful for controller synthesis. To provide good performance guarantees, existing methods must assume that the real system is in the class of models considered during learning. We present an iterative method with strong guarantees even in the agnostic case where the system is not in the class. In particular, we show that any no-regret online learning algorithm can be used to obtain a near-optimal policy, provided some model achieves low training error and access to a good exploration distribution. Our approach applies to both discrete and continuous domains. We demonstrate its efficacy and scalability on a challenging helicopter domain from the literature.", "source": "arxiv/ml"}
{"id": "arxiv:1371", "title": "Learning Random Kernel Approximations for Object Recognition", "text": "Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the kernel as a Fourier expansion, features are generated based on a finite set of random basis projections, sampled from the Fourier transform of the kernel, with inner products that are Monte Carlo approximations of the original kernel. Based on the observation that different kernel-induced Fourier sampling distributions correspond to different kernel parameters, we show that an optimization process in the Fourier domain can be used to identify the different frequency bands that are useful for prediction on training data. Moreover, the application of group Lasso to random feature vectors corresponding to a linear combination of multiple kernels, leads to efficient and scalable reformulations of the standard multiple kernel learning model \\cite{Varma09}. In this paper we develop the linear Fourier approximation methodology for both single and multiple gradient-based kernel learning and show that it produces fast and accurate predictors on a complex dataset such as the Visual Object Challenge 2011 (VOC2011).", "source": "arxiv/ml"}
{"id": "arxiv:1372", "title": "Multiple Operator-valued Kernel Learning", "text": "Positive definite operator-valued kernels generalize the well-known notion of reproducing kernels, and are naturally adapted to multi-output learning situations. This paper addresses the problem of learning a finite linear combination of infinite-dimensional operator-valued kernels which are suitable for extending functional data analysis methods to nonlinear contexts. We study this problem in the case of kernel ridge regression for functional responses with an lr-norm constraint on the combination coefficients. The resulting optimization problem is more involved than those of multiple scalar-valued kernel learning since operator-valued kernels pose more technical and theoretical issues. We propose a multiple operator-valued kernel learning algorithm based on solving a system of linear operator equations by using a block coordinatedescent procedure. We experimentally validate our approach on a functional regression task in the context of finger movement prediction in brain-computer interfaces.", "source": "arxiv/ml"}
{"id": "arxiv:1373", "title": "Graph partitioning advance clustering technique", "text": "Clustering is a common technique for statistical data analysis, Clustering is the process of grouping the data into classes or clusters so that objects within a cluster have high similarity in comparison to one another, but are very dissimilar to objects in other clusters. Dissimilarities are assessed based on the attribute values describing the objects. Often, distance measures are used. Clustering is an unsupervised learning technique, where interesting patterns and structures can be found directly from very large data sets with little or none of the background knowledge. This paper also considers the partitioning of m-dimensional lattice graphs using Fiedler's approach, which requires the determination of the eigenvector belonging to the second smallest Eigenvalue of the Laplacian with K-means partitioning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1374", "title": "Regret Bounds for Deterministic Gaussian Process Bandits", "text": "This paper analyses the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al., 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, (Srinivas et al., 2010) proved that the regret vanishes at the approximate rate of $O(\\frac{1}{\\sqrt{t}})$, where t is the number of observations. To complement their result, we attack the deterministic case and attain a much faster exponential convergence rate. Under some regularity assumptions, we show that the regret decreases asymptotically according to $O(e^{-\\frac{\\tau t}{(\\ln t)^{d/4}}})$ with high probability. Here, d is the dimension of the search space and $\\tau$ is a constant that depends on the behaviour of the objective function near its global maximum.", "source": "arxiv/ml"}
{"id": "arxiv:1375", "title": "Role-Dynamics: Fast Mining of Large Dynamic Networks", "text": "To understand the structural dynamics of a large-scale social, biological or technological network, it may be useful to discover behavioral roles representing the main connectivity patterns present over time. In this paper, we propose a scalable non-parametric approach to automatically learn the structural dynamics of the network and individual nodes. Roles may represent structural or behavioral patterns such as the center of a star, peripheral nodes, or bridge nodes that connect different communities. Our novel approach learns the appropriate structural role dynamics for any arbitrary network and tracks the changes over time. In particular, we uncover the specific global network dynamics and the local node dynamics of a technological, communication, and social network. We identify interesting node and network patterns such as stationary and non-stationary roles, spikes/steps in role-memberships (perhaps indicating anomalies), increasing/decreasing role trends, among many others. Our results indicate that the nodes in each of these networks have distinct connectivity patterns that are non-stationary and evolve considerably over time. Overall, the experiments demonstrate the effectiveness of our approach for fast mining and tracking of the dynamics in large networks. Furthermore, the dynamic structural representation provides a basis for building more sophisticated models and tools that are fast for exploring large dynamic networks.", "source": "arxiv/ml"}
{"id": "arxiv:1376", "title": "Decentralized, Adaptive, Look-Ahead Particle Filtering", "text": "The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for the second set of variables. The DPF can be understood as a variant of the popular Rao-Blackwellized particle filter (RBPF), where the second step is carried out using Monte Carlo approximations instead of analytical inference. As a result, the range of applications of the DPF is broader than the one for the RBPF. In this paper, we improve the DPF in two ways. First, we derive a Monte Carlo approximation of the optimal proposal distribution and, consequently, design and implement a more efficient look-ahead DPF. Although the decentralized filters were initially designed to capitalize on parallel implementation, we show that the look-ahead DPF can outperform the standard particle filter even on a single machine. Second, we propose the use of bandit algorithms to automatically configure the state space decomposition of the DPF.", "source": "arxiv/ml"}
{"id": "arxiv:1377", "title": "Deviation optimal learning using greedy Q-aggregation", "text": "Given a finite family of functions, the goal of model selection aggregation is to construct a procedure that mimics the function from this family that is the closest to an unknown regression function. More precisely, we consider a general regression model with fixed design and measure the distance between functions by the mean squared error at the design points. While procedures based on exponential weights are known to solve the problem of model selection aggregation in expectation, they are, surprisingly, sub-optimal in deviation. We propose a new formulation called Q-aggregation that addresses this limitation; namely, its solution leads to sharp oracle inequalities that are optimal in a minimax sense. Moreover, based on the new formulation, we design greedy Q-aggregation procedures that produce sparse aggregation models achieving the optimal rate. The convergence and performance of these greedy procedures are illustrated and compared with other standard methods on simulated examples.", "source": "arxiv/ml"}
{"id": "arxiv:1378", "title": "A Simple Flood Forecasting Scheme Using Wireless Sensor Networks", "text": "This paper presents a forecasting model designed using WSNs (Wireless Sensor Networks) to predict flood in rivers using simple and fast calculations to provide real-time results and save the lives of people who may be affected by the flood. Our prediction model uses multiple variable robust linear regression which is easy to understand and simple and cost effective in implementation, is speed efficient, but has low resource utilization and yet provides real time predictions with reliable accuracy, thus having features which are desirable in any real world algorithm. Our prediction model is independent of the number of parameters, i.e. any number of parameters may be added or removed based on the on-site requirements. When the water level rises, we represent it using a polynomial whose nature is used to determine if the water level may exceed the flood line in the near future. We compare our work with a contemporary algorithm to demonstrate our improvements over it. Then we present our simulation results for the predicted water level compared to the actual water level.", "source": "arxiv/ml"}
{"id": "arxiv:1379", "title": "On the Necessity of Irrelevant Variables", "text": "This work explores the effects of relevant and irrelevant boolean variables on the accuracy of classifiers. The analysis uses the assumption that the variables are conditionally independent given the class, and focuses on a natural family of learning algorithms for such sources when the relevant variables have a small advantage over random guessing. The main result is that algorithms relying predominately on irrelevant variables have error probabilities that quickly go to 0 in situations where algorithms that limit the use of irrelevant variables have errors bounded below by a positive constant. We also show that accurate learning is possible even when there are so few examples that one cannot determine with high confidence whether or not any individual variable is relevant.", "source": "arxiv/ml"}
{"id": "arxiv:1380", "title": "Differential Privacy for Functions and Functional Data", "text": "Differential privacy is a framework for privately releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We develop methods for releasing functions while preserving differential privacy. Specifically, we show that adding an appropriate Gaussian process to the function of interest yields differential privacy. When the functions lie in the same RKHS as the Gaussian process, then the correct noise level is established by measuring the \"sensitivity\" of the function in the RKHS norm. As examples we consider kernel density estimation, kernel support vector machines, and functions in reproducing kernel Hilbert spaces.", "source": "arxiv/ml"}
{"id": "arxiv:1381", "title": "Graphlet decomposition of a weighted network", "text": "We introduce the graphlet decomposition of a weighted network, which encodes a notion of social information based on social structure. We develop a scalable inference algorithm, which combines EM with Bron-Kerbosch in a novel fashion, for estimating the parameters of the model underlying graphlets using one network sample. We explore some theoretical properties of the graphlet decomposition, including computational complexity, redundancy and expected accuracy. We demonstrate graphlets on synthetic and real data. We analyze messaging patterns on Facebook and criminal associations in the 19th century.", "source": "arxiv/ml"}
{"id": "arxiv:1382", "title": "Mining Education Data to Predict Student's Retention: A comparative Study", "text": "The main objective of higher education is to provide quality education to students. One way to achieve highest level of quality in higher education system is by discovering knowledge for prediction regarding enrolment of students in a course. This paper presents a data mining project to generate predictive models for student retention management. Given new records of incoming students, these predictive models can produce short accurate prediction lists identifying students who tend to need the support from the student retention program most. This paper examines the quality of the predictive models generated by the machine learning algorithms. The results show that some of the machines learning algorithms are able to establish effective predictive models from the existing student retention data.", "source": "arxiv/ml"}
{"id": "arxiv:1383", "title": "Evolving Culture vs Local Minima", "text": "We propose a theory that relates difficulty of learning in deep architectures to culture and language. It is articulated around the following hypotheses: (1) learning in an individual human brain is hampered by the presence of effective local minima; (2) this optimization difficulty is particularly important when it comes to learning higher-level abstractions, i.e., concepts that cover a vast and highly-nonlinear span of sensory configurations; (3) such high-level abstractions are best represented in brains by the composition of many levels of representation, i.e., by deep architectures; (4) a human brain can learn such high-level abstractions if guided by the signals produced by other humans, which act as hints or indirect supervision for these high-level abstractions; and (5), language and the recombination and optimization of mental concepts provide an efficient evolutionary recombination operator, and this gives rise to rapid search in the space of communicable ideas that help humans build up better high-level internal representations of their world. These hypotheses put together imply that human culture and the evolution of ideas have been crucial to counter an optimization difficulty: this optimization difficulty would otherwise make it very difficult for human brains to capture high-level knowledge of the world. The theory is grounded in experimental observations of the difficulties of training deep artificial neural networks. Plausible consequences of this theory for the efficiency of cultural evolutions are sketched.", "source": "arxiv/ml"}
{"id": "arxiv:1384", "title": "Learning, Social Intelligence and the Turing Test - why an \"out-of-the-box\" Turing Machine will not pass the Turing Test", "text": "The Turing Test (TT) checks for human intelligence, rather than any putative general intelligence. It involves repeated interaction requiring learning in the form of adaption to the human conversation partner. It is a macro-level post-hoc test in contrast to the definition of a Turing Machine (TM), which is a prior micro-level definition. This raises the question of whether learning is just another computational process, i.e. can be implemented as a TM. Here we argue that learning or adaption is fundamentally different from computation, though it does involve processes that can be seen as computations. To illustrate this difference we compare (a) designing a TM and (b) learning a TM, defining them for the purpose of the argument. We show that there is a well-defined sequence of problems which are not effectively designable but are learnable, in the form of the bounded halting problem. Some characteristics of human intelligence are reviewed including it's: interactive nature, learning abilities, imitative tendencies, linguistic ability and context-dependency. A story that explains some of these is the Social Intelligence Hypothesis. If this is broadly correct, this points to the necessity of a considerable period of acculturation (social learning in context) if an artificial intelligence is to pass the TT. Whilst it is always possible to 'compile' the results of learning into a TM, this would not be a designed TM and would not be able to continually adapt (pass future TTs). We conclude three things, namely that: a purely \"designed\" TM will never pass the TT; that there is no such thing as a general intelligence since it necessary involves learning; and that learning/adaption and computation should be clearly distinguished.", "source": "arxiv/ml"}
{"id": "arxiv:1385", "title": "Robust Metric Learning by Smooth Optimization", "text": "Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as users' implicit feedbacks and citations among articles. As a result, these constraints are usually noisy and contain many mistakes. In this work, we aim to learn a distance metric from noisy constraints by robust optimization in a worst-case scenario, to which we refer as robust metric learning. We formulate the learning task initially as a combinatorial optimization problem, and show that it can be elegantly transformed to a convex programming problem. We present an efficient learning algorithm based on smooth optimization [7]. It has a worst-case convergence rate of O(1/{\\surd}{\\varepsilon}) for smooth optimization problems, where {\\varepsilon} is the desired error of the approximate solution. Finally, our empirical study with UCI data sets demonstrate the effectiveness of the proposed method in comparison to state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:1386", "title": "Gaussian Process Topic Models", "text": "We introduce Gaussian Process Topic Models (GPTMs), a new family of topic models which can leverage a kernel among documents while extracting correlated topics. GPTMs can be considered a systematic generalization of the Correlated Topic Models (CTMs) using ideas from Gaussian Process (GP) based embedding. Since GPTMs work with both a topic covariance matrix and a document kernel matrix, learning GPTMs involves a novel component-solving a suitable Sylvester equation capturing both topic and document dependencies. The efficacy of GPTMs is demonstrated with experiments evaluating the quality of both topic modeling and embedding.", "source": "arxiv/ml"}
{"id": "arxiv:1387", "title": "Timeline: A Dynamic Hierarchical Dirichlet Process Model for Recovering Birth/Death and Evolution of Topics in Text Stream", "text": "Topic models have proven to be a useful tool for discovering latent structures in document collections. However, most document collections often come as temporal streams and thus several aspects of the latent structure such as the number of topics, the topics' distribution and popularity are time-evolving. Several models exist that model the evolution of some but not all of the above aspects. In this paper we introduce infinite dynamic topic models, iDTM, that can accommodate the evolution of all the aforementioned aspects. Our model assumes that documents are organized into epochs, where the documents within each epoch are exchangeable but the order between the documents is maintained across epochs. iDTM allows for unbounded number of topics: topics can die or be born at any epoch, and the representation of each topic can evolve according to a Markovian dynamics. We use iDTM to analyze the birth and evolution of topics in the NIPS community and evaluated the efficacy of our model on both simulated and real datasets with favorable outcome.", "source": "arxiv/ml"}
{"id": "arxiv:1388", "title": "Bayesian Rose Trees", "text": "Hierarchical structure is ubiquitous in data across many domains. There are many hierarchical clustering methods, frequently used by domain experts, which strive to discover this structure. However, most of these methods limit discoverable hierarchies to those with binary branching structure. This limitation, while computationally convenient, is often undesirable. In this paper we explore a Bayesian hierarchical clustering algorithm that can produce trees with arbitrary branching structure at each node, known as rose trees. We interpret these trees as mixtures over partitions of a data set, and use a computationally efficient, greedy agglomerative algorithm to find the rose trees which have high marginal likelihood given the data. Lastly, we perform experiments which demonstrate that rose trees are better models of data than the typical binary trees returned by other hierarchical clustering algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1389", "title": "An Online Learning-based Framework for Tracking", "text": "We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. However, these solutions can be very sensitive to model mismatches. In this paper, motivated by online learning, we introduce a new framework for tracking. We provide an efficient tracking algorithm for this framework. We provide experimental results comparing our algorithm to the Bayesian algorithm on simulated data. Our experiments show that when there are slight model mismatches, our algorithm outperforms the Bayesian algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1390", "title": "Super-Samples from Kernel Herding", "text": "We extend the herding algorithm to continuous spaces by using the kernel trick. The resulting \"kernel herding\" algorithm is an infinite memory deterministic process that learns to approximate a PDF with a collection of samples. We show that kernel herding decreases the error of expectations of functions in the Hilbert space at a rate O(1/T) which is much faster than the usual O(1/pT) for iid random samples. We illustrate kernel herding by approximating Bayesian predictive distributions.", "source": "arxiv/ml"}
{"id": "arxiv:1391", "title": "Inferring deterministic causal relations", "text": "We consider two variables that are related to each other by an invertible function. While it has previously been shown that the dependence structure of the noise can provide hints to determine which of the two variables is the cause, we presently show that even in the deterministic (noise-free) case, there are asymmetries that can be exploited for causal inference. Our method is based on the idea that if the function and the probability density of the cause are chosen independently, then the distribution of the effect will, in a certain sense, depend on the function. We provide a theoretical analysis of this method, showing that it also works in the low noise regime, and link it to information geometry. We report strong empirical results on various real-world data sets from different domains.", "source": "arxiv/ml"}
{"id": "arxiv:1392", "title": "Inference-less Density Estimation using Copula Bayesian Networks", "text": "We consider learning continuous probabilistic graphical models in the face of missing data. For non-Gaussian models, learning the parameters and structure of such models depends on our ability to perform efficient inference, and can be prohibitive even for relatively modest domains. Recently, we introduced the Copula Bayesian Network (CBN) density model - a flexible framework that captures complex high-dimensional dependency structures while offering direct control over the univariate marginals, leading to improved generalization. In this work we show that the CBN model also offers significant computational advantages when training data is partially observed. Concretely, we leverage on the specialized form of the model to derive a computationally amenable learning objective that is a lower bound on the log-likelihood function. Importantly, our energy-like bound circumvents the need for costly inference of an auxiliary distribution, thus facilitating practical learning of highdimensional densities. We demonstrate the effectiveness of our approach for learning the structure and parameters of a CBN model for two reallife continuous domains.", "source": "arxiv/ml"}
{"id": "arxiv:1393", "title": "Real-Time Scheduling via Reinforcement Learning", "text": "Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution of mission specific tasks such as imaging a room must be balanced against the need to perform more general tasks such as obstacle avoidance. This problem has been addressed by maintaining relative utilization of shared resources among tasks near a user-specified target level. Producing optimal scheduling strategies requires complete prior knowledge of task behavior, which is unlikely to be available in practice. Instead, suitable scheduling strategies must be learned online through interaction with the system. We consider the sample complexity of reinforcement learning in this domain, and demonstrate that while the problem state space is countably infinite, we may leverage the problem's structure to guarantee efficient learning.", "source": "arxiv/ml"}
{"id": "arxiv:1394", "title": "Regularized Maximum Likelihood for Intrinsic Dimension Estimation", "text": "We propose a new method for estimating the intrinsic dimension of a dataset by applying the principle of regularized maximum likelihood to the distances between close neighbors. We propose a regularization scheme which is motivated by divergence minimization principles. We derive the estimator by a Poisson process approximation, argue about its convergence properties and apply it to a number of simulated and real datasets. We also show it has the best overall performance compared with two other intrinsic dimension estimators.", "source": "arxiv/ml"}
{"id": "arxiv:1395", "title": "The Hierarchical Dirichlet Process Hidden Semi-Markov Model", "text": "There is much interest in the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) as a natural Bayesian nonparametric extension of the traditional HMM. However, in many settings the HDP-HMM's strict Markovian constraints are undesirable, particularly if we wish to learn or encode non-geometric state durations. We can extend the HDP-HMM to capture such structure by drawing upon explicit-duration semi-Markovianity, which has been developed in the parametric setting to allow construction of highly interpretable models that admit natural prior information on state durations. In this paper we introduce the explicitduration HDP-HSMM and develop posterior sampling algorithms for efficient inference in both the direct-assignment and weak-limit approximation settings. We demonstrate the utility of the model and our inference methods on synthetic data as well as experiments on a speaker diarization problem and an example of learning the patterns in Morse code.", "source": "arxiv/ml"}
{"id": "arxiv:1396", "title": "Combining Spatial and Telemetric Features for Learning Animal Movement Models", "text": "We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We describe an efficient stochastic gradient algorithm for fitting model parameters to data and demonstrate its effectiveness via asymptotic analysis and synthetic experiments. We also apply our model to real datasets, and show that it outperforms the most popular radio telemetry software package used in ecology. We conclude that integration of different data sources under a single statistical framework, coupled with appropriate parameter and state estimation procedures, produces both accurate location estimates and an interpretable statistical model of animal movement.", "source": "arxiv/ml"}
{"id": "arxiv:1397", "title": "Causal Conclusions that Flip Repeatedly and Their Justification", "text": "Over the past two decades, several consistent procedures have been designed to infer causal conclusions from observational data. We prove that if the true causal network might be an arbitrary, linear Gaussian network or a discrete Bayes network, then every unambiguous causal conclusion produced by a consistent method from non-experimental data is subject to reversal as the sample size increases any finite number of times. That result, called the causal flipping theorem, extends prior results to the effect that causal discovery cannot be reliable on a given sample size. We argue that since repeated flipping of causal conclusions is unavoidable in principle for consistent methods, the best possible discovery methods are consistent methods that retract their earlier conclusions no more than necessary. A series of simulations of various methods across a wide range of sample sizes illustrates concretely both the theorem and the principle of comparing methods in terms of retractions.", "source": "arxiv/ml"}
{"id": "arxiv:1398", "title": "Bayesian exponential family projections for coupled data sources", "text": "Exponential family extensions of principal component analysis (EPCA) have received a considerable amount of attention in recent years, demonstrating the growing need for basic modeling tools that do not assume the squared loss or Gaussian distribution. We extend the EPCA model toolbox by presenting the first exponential family multi-view learning methods of the partial least squares and canonical correlation analysis, based on a unified representation of EPCA as matrix factorization of the natural parameters of exponential family. The models are based on a new family of priors that are generally usable for all such factorizations. We also introduce new inference strategies, and demonstrate how the methods outperform earlier ones when the Gaussianity assumption does not hold.", "source": "arxiv/ml"}
{"id": "arxiv:1399", "title": "Robust LogitBoost and Adaptive Base Class (ABC) LogitBoost", "text": "Logitboost is an influential boosting algorithm for classification. In this paper, we develop robust logitboost to provide an explicit formulation of tree-split criterion for building weak learners (regression trees) for logitboost. This formulation leads to a numerically stable implementation of logitboost. We then propose abc-logitboost for multi-class classification, by combining robust logitboost with the prior work of abc-boost. Previously, abc-boost was implemented as abc-mart using the mart algorithm. Our extensive experiments on multi-class classification compare four algorithms: mart, abcmart, (robust) logitboost, and abc-logitboost, and demonstrate the superiority of abc-logitboost. Comparisons with other learning methods including SVM and deep learning are also available through prior publications.", "source": "arxiv/ml"}
{"id": "arxiv:1400", "title": "Approximating Higher-Order Distances Using Random Projections", "text": "We provide a simple method and relevant theoretical analysis for efficiently estimating higher-order lp distances. While the analysis mainly focuses on l4, our methodology extends naturally to p = 6,8,10..., (i.e., when p is even). Distance-based methods are popular in machine learning. In large-scale applications, storing, computing, and retrieving the distances can be both space and time prohibitive. Efficient algorithms exist for estimating lp distances if 0 < p <= 2. The task for p > 2 is known to be difficult. Our work partially fills this gap.", "source": "arxiv/ml"}
{"id": "arxiv:1401", "title": "Negative Tree Reweighted Belief Propagation", "text": "We introduce a new class of lower bounds on the log partition function of a Markov random field which makes use of a reversed Jensen's inequality. In particular, our method approximates the intractable distribution using a linear combination of spanning trees with negative weights. This technique is a lower-bound counterpart to the tree-reweighted belief propagation algorithm, which uses a convex combination of spanning trees with positive weights to provide corresponding upper bounds. We develop algorithms to optimize and tighten the lower bounds over the non-convex set of valid parameter values. Our algorithm generalizes mean field approaches (including naive and structured mean field approximations), which it includes as a limiting case.", "source": "arxiv/ml"}
{"id": "arxiv:1402", "title": "Parameter-Free Spectral Kernel Learning", "text": "Due to the growing ubiquity of unlabeled data, learning with unlabeled data is attracting increasing attention in machine learning. In this paper, we propose a novel semi-supervised kernel learning method which can seamlessly combine manifold structure of unlabeled data and Regularized Least-Squares (RLS) to learn a new kernel. Interestingly, the new kernel matrix can be obtained analytically with the use of spectral decomposition of graph Laplacian matrix. Hence, the proposed algorithm does not require any numerical optimization solvers. Moreover, by maximizing kernel target alignment on labeled data, we can also learn model parameters automatically with a closed-form solution. For a given graph Laplacian matrix, our proposed method does not need to tune any model parameter including the tradeoff parameter in RLS and the balance parameter for unlabeled data. Extensive experiments on ten benchmark datasets show that our proposed two-stage parameter-free spectral kernel learning algorithm can obtain comparable performance with fine-tuned manifold regularization methods in transductive setting, and outperform multiple kernel learning in supervised setting.", "source": "arxiv/ml"}
{"id": "arxiv:1403", "title": "Dirichlet Process Mixtures of Generalized Mallows Models", "text": "We present a Dirichlet process mixture model over discrete incomplete rankings and study two Gibbs sampling inference techniques for estimating posterior clusterings. The first approach uses a slice sampling subcomponent for estimating cluster parameters. The second approach marginalizes out several cluster parameters by taking advantage of approximations to the conditional posteriors. We empirically demonstrate (1) the effectiveness of this approximation for improving convergence, (2) the benefits of the Dirichlet process model over alternative clustering techniques for ranked data, and (3) the applicability of the approach to exploring large realworld ranking datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1404", "title": "Parametric Return Density Estimation for Reinforcement Learning", "text": "Most conventional Reinforcement Learning (RL) algorithms aim to optimize decision-making rules in terms of the expected returns. However, especially for risk management purposes, other risk-sensitive criteria such as the value-at-risk or the expected shortfall are sometimes preferred in real applications. Here, we describe a parametric method for estimating density of the returns, which allows us to handle various criteria in a unified manner. We first extend the Bellman equation for the conditional expected return to cover a conditional probability density of the returns. Then we derive an extension of the TD-learning algorithm for estimating the return densities in an unknown environment. As test instances, several parametric density estimation algorithms are presented for the Gaussian, Laplace, and skewed Laplace distributions. We show that these algorithms lead to risk-sensitive as well as robust RL paradigms through numerical experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1405", "title": "Algorithms and Complexity Results for Exact Bayesian Structure Learning", "text": "Bayesian structure learning is the NP-hard problem of discovering a Bayesian network that optimally represents a given set of training data. In this paper we study the computational worst-case complexity of exact Bayesian structure learning under graph theoretic restrictions on the super-structure. The super-structure (a concept introduced by Perrier, Imoto, and Miyano, JMLR 2008) is an undirected graph that contains as subgraphs the skeletons of solution networks. Our results apply to several variants of score-based Bayesian structure learning where the score of a network decomposes into local scores of its nodes. Results: We show that exact Bayesian structure learning can be carried out in non-uniform polynomial time if the super-structure has bounded treewidth and in linear time if in addition the super-structure has bounded maximum degree. We complement this with a number of hardness results. We show that both restrictions (treewidth and degree) are essential and cannot be dropped without loosing uniform polynomial time tractability (subject to a complexity-theoretic assumption). Furthermore, we show that the restrictions remain essential if we do not search for a globally optimal network but we aim to improve a given network by means of at most k arc additions, arc deletions, or arc reversals (k-neighborhood local search).", "source": "arxiv/ml"}
{"id": "arxiv:1406", "title": "A Family of Computationally Efficient and Simple Estimators for Unnormalized Statistical Models", "text": "We introduce a new family of estimators for unnormalized statistical models. Our family of estimators is parameterized by two nonlinear functions and uses a single sample from an auxiliary distribution, generalizing Maximum Likelihood Monte Carlo estimation of Geyer and Thompson (1992). The family is such that we can estimate the partition function like any other parameter in the model. The estimation is done by optimizing an algebraically simple, well defined objective function, which allows for the use of dedicated optimization methods. We establish consistency of the estimator family and give an expression for the asymptotic covariance matrix, which enables us to further analyze the influence of the nonlinearities and the auxiliary density on estimation performance. Some estimators in our family are particularly stable for a wide range of auxiliary densities. Interestingly, a specific choice of the nonlinearity establishes a connection between density estimation and classification by nonlinear logistic regression. Finally, the optimal amount of auxiliary samples relative to the given amount of the data is considered from the perspective of computational efficiency.", "source": "arxiv/ml"}
{"id": "arxiv:1407", "title": "Sparse-posterior Gaussian Processes for general likelihoods", "text": "Gaussian processes (GPs) provide a probabilistic nonparametric representation of functions in regression, classification, and other problems. Unfortunately, exact learning with GPs is intractable for large datasets. A variety of approximate GP methods have been proposed that essentially map the large dataset into a small set of basis points. Among them, two state-of-the-art methods are sparse pseudo-input Gaussian process (SPGP) (Snelson and Ghahramani, 2006) and variablesigma GP (VSGP) Walder et al. (2008), which generalizes SPGP and allows each basis point to have its own length scale. However, VSGP was only derived for regression. In this paper, we propose a new sparse GP framework that uses expectation propagation to directly approximate general GP likelihoods using a sparse and smooth basis. It includes both SPGP and VSGP for regression as special cases. Plus as an EP algorithm, it inherits the ability to process data online. As a particular choice of approximating family, we blur each basis point with a Gaussian distribution that has a full covariance matrix representing the data distribution around that basis point; as a result, we can summarize local data manifold information with a small set of basis points. Our experiments demonstrate that this framework outperforms previous GP classification methods on benchmark datasets in terms of minimizing divergence to the non-sparse GP solution as well as lower misclassification rate.", "source": "arxiv/ml"}
{"id": "arxiv:1408", "title": "Irregular-Time Bayesian Networks", "text": "In many fields observations are performed irregularly along time, due to either measurement limitations or lack of a constant immanent rate. While discrete-time Markov models (as Dynamic Bayesian Networks) introduce either inefficient computation or an information loss to reasoning about such processes, continuous-time Markov models assume either a discrete state space (as Continuous-Time Bayesian Networks), or a flat continuous state space (as stochastic differential equations). To address these problems, we present a new modeling class called Irregular-Time Bayesian Networks (ITBNs), generalizing Dynamic Bayesian Networks, allowing substantially more compact representations, and increasing the expressivity of the temporal dynamics. In addition, a globally optimal solution is guaranteed when learning temporal systems, provided that they are fully observed at the same irregularly spaced time-points, and a semiparametric subclass of ITBNs is introduced to allow further adaptation to the irregular nature of the available data.", "source": "arxiv/ml"}
{"id": "arxiv:1409", "title": "Inference by Minimizing Size, Divergence, or their Sum", "text": "We speed up marginal inference by ignoring factors that do not significantly contribute to overall accuracy. In order to pick a suitable subset of factors to ignore, we propose three schemes: minimizing the number of model factors under a bound on the KL divergence between pruned and full models; minimizing the KL divergence under a bound on factor count; and minimizing the weighted sum of KL divergence and factor count. All three problems are solved using an approximation of the KL divergence than can be calculated in terms of marginals computed on a simple seed graph. Applied to synthetic image denoising and to three different types of NLP parsing models, this technique performs marginal inference up to 11 times faster than loopy BP, with graph sizes reduced up to 98%-at comparable error in marginals and parsing accuracy. We also show that minimizing the weighted sum of divergence and size is substantially faster than minimizing either of the other objectives based on the approximation to divergence presented here.", "source": "arxiv/ml"}
{"id": "arxiv:1410", "title": "Modeling Events with Cascades of Poisson Processes", "text": "We present a probabilistic model of events in continuous time in which each event triggers a Poisson process of successor events. The ensemble of observed events is thereby modeled as a superposition of Poisson processes. Efficient inference is feasible under this model with an EM algorithm. Moreover, the EM algorithm can be implemented as a distributed algorithm, permitting the model to be applied to very large datasets. We apply these techniques to the modeling of Twitter messages and the revision history of Wikipedia.", "source": "arxiv/ml"}
{"id": "arxiv:1411", "title": "A Bayesian Matrix Factorization Model for Relational Data", "text": "Relational learning can be used to augment one data source with other correlated sources of information, to improve predictive accuracy. We frame a large class of relational learning problems as matrix factorization problems, and propose a hierarchical Bayesian model. Training our Bayesian model using random-walk Metropolis-Hastings is impractically slow, and so we develop a block Metropolis-Hastings sampler which uses the gradient and Hessian of the likelihood to dynamically tune the proposal. We demonstrate that a predictive model of brain response to stimuli can be improved by augmenting it with side information about the stimuli.", "source": "arxiv/ml"}
{"id": "arxiv:1412", "title": "Variance-Based Rewards for Approximate Bayesian Reinforcement Learning", "text": "The explore{exploit dilemma is one of the central challenges in Reinforcement Learning (RL). Bayesian RL solves the dilemma by providing the agent with information in the form of a prior distribution over environments; however, full Bayesian planning is intractable. Planning with the mean MDP is a common myopic approximation of Bayesian planning. We derive a novel reward bonus that is a function of the posterior distribution over environments, which, when added to the reward in planning with the mean MDP, results in an agent which explores efficiently and effectively. Although our method is similar to existing methods when given an uninformative or unstructured prior, unlike existing methods, our method can exploit structured priors. We prove that our method results in a polynomial sample complexity and empirically demonstrate its advantages in a structured exploration task.", "source": "arxiv/ml"}
{"id": "arxiv:1413", "title": "Bayesian Inference in Monte-Carlo Tree Search", "text": "Monte-Carlo Tree Search (MCTS) methods are drawing great interest after yielding breakthrough results in computer Go. This paper proposes a Bayesian approach to MCTS that is inspired by distributionfree approaches such as UCT [13], yet significantly differs in important respects. The Bayesian framework allows potentially much more accurate (Bayes-optimal) estimation of node values and node uncertainties from a limited number of simulation trials. We further propose propagating inference in the tree via fast analytic Gaussian approximation methods: this can make the overhead of Bayesian inference manageable in domains such as Go, while preserving high accuracy of expected-value estimates. We find substantial empirical outperformance of UCT in an idealized bandit-tree test environment, where we can obtain valuable insights by comparing with known ground truth. Additionally we rigorously prove on-policy and off-policy convergence of the proposed methods.", "source": "arxiv/ml"}
{"id": "arxiv:1414", "title": "Bayesian Model Averaging Using the k-best Bayesian Network Structures", "text": "We study the problem of learning Bayesian network structures from data. We develop an algorithm for finding the k-best Bayesian network structures. We propose to compute the posterior probabilities of hypotheses of interest by Bayesian model averaging over the k-best Bayesian networks. We present empirical results on structural discovery over several real and synthetic data sets and show that the method outperforms the model selection method and the state of-the-art MCMC methods.", "source": "arxiv/ml"}
{"id": "arxiv:1415", "title": "Learning networks determined by the ratio of prior and data", "text": "Recent reports have described that the equivalent sample size (ESS) in a Dirichlet prior plays an important role in learning Bayesian networks. This paper provides an asymptotic analysis of the marginal likelihood score for a Bayesian network. Results show that the ratio of the ESS and sample size determine the penalty of adding arcs in learning Bayesian networks. The number of arcs increases monotonically as the ESS increases; the number of arcs monotonically decreases as the ESS decreases. Furthermore, the marginal likelihood score provides a unified expression of various score metrics by changing prior knowledge.", "source": "arxiv/ml"}
{"id": "arxiv:1416", "title": "Online Semi-Supervised Learning on Quantized Graphs", "text": "In this paper, we tackle the problem of online semi-supervised learning (SSL). When data arrive in a stream, the dual problems of computation and data storage arise for any SSL method. We propose a fast approximate online SSL algorithm that solves for the harmonic solution on an approximate graph. We show, both empirically and theoretically, that good behavior can be achieved by collapsing nearby points into a set of local \"representative points\" that minimize distortion. Moreover, we regularize the harmonic solution to achieve better stability properties. We apply our algorithm to face recognition and optical character recognition applications to show that we can take advantage of the manifold structure to outperform the previous methods. Unlike previous heuristic approaches, we show that our method yields provable performance bounds.", "source": "arxiv/ml"}
{"id": "arxiv:1417", "title": "Speeding up the binary Gaussian process classification", "text": "Gaussian processes (GP) are attractive building blocks for many probabilistic models. Their drawbacks, however, are the rapidly increasing inference time and memory requirement alongside increasing data. The problem can be alleviated with compactly supported (CS) covariance functions, which produce sparse covariance matrices that are fast in computations and cheap to store. CS functions have previously been used in GP regression but here the focus is in a classification problem. This brings new challenges since the posterior inference has to be done approximately. We utilize the expectation propagation algorithm and show how its standard implementation has to be modified to obtain computational benefits from the sparse covariance matrices. We study four CS covariance functions and show that they may lead to substantial speed up in the inference time compared to globally supported functions.", "source": "arxiv/ml"}
{"id": "arxiv:1418", "title": "Primal View on Belief Propagation", "text": "It is known that fixed points of loopy belief propagation (BP) correspond to stationary points of the Bethe variational problem, where we minimize the Bethe free energy subject to normalization and marginalization constraints. Unfortunately, this does not entirely explain BP because BP is a dual rather than primal algorithm to solve the Bethe variational problem -- beliefs are infeasible before convergence. Thus, we have no better understanding of BP than as an algorithm to seek for a common zero of a system of non-linear functions, not explicitly related to each other. In this theoretical paper, we show that these functions are in fact explicitly related -- they are the partial derivatives of a single function of reparameterizations. That means, BP seeks for a stationary point of a single function, without any constraints. This function has a very natural form: it is a linear combination of local log-partition functions, exactly as the Bethe entropy is the same linear combination of local entropies.", "source": "arxiv/ml"}
{"id": "arxiv:1419", "title": "Modeling Multiple Annotator Expertise in the Semi-Supervised Learning Scenario", "text": "Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case, obtaining labels for data points can be expensive and time-consuming (in some circumstances ground-truth may not exist). Semi-supervised learning approaches have shown that utilizing the unlabeled data is often beneficial in these cases. This paper presents a probabilistic semi-supervised model and algorithm that allows for learning from both unlabeled and labeled data in the presence of multiple annotators. We assume that it is known what annotator labeled which data points. The proposed approach produces annotator models that allow us to provide (1) estimates of the true label and (2) annotator variable expertise for both labeled and unlabeled data. We provide numerical comparisons under various scenarios and with respect to standard semi-supervised learning. Experiments showed that the presented approach provides clear advantages over multi-annotator methods that do not use the unlabeled data and over methods that do not use multi-labeler information.", "source": "arxiv/ml"}
{"id": "arxiv:1420", "title": "Hybrid Generative/Discriminative Learning for Automatic Image Annotation", "text": "Automatic image annotation (AIA) raises tremendous challenges to machine learning as it requires modeling of data that are both ambiguous in input and output, e.g., images containing multiple objects and labeled with multiple semantic tags. Even more challenging is that the number of candidate tags is usually huge (as large as the vocabulary size) yet each image is only related to a few of them. This paper presents a hybrid generative-discriminative classifier to simultaneously address the extreme data-ambiguity and overfitting-vulnerability issues in tasks such as AIA. Particularly: (1) an Exponential-Multinomial Mixture (EMM) model is established to capture both the input and output ambiguity and in the meanwhile to encourage prediction sparsity; and (2) the prediction ability of the EMM model is explicitly maximized through discriminative learning that integrates variational inference of graphical models and the pairwise formulation of ordinal regression. Experiments show that our approach achieves both superior annotation performance and better tag scalability.", "source": "arxiv/ml"}
{"id": "arxiv:1421", "title": "Learning Structural Changes of Gaussian Graphical Models in Controlled Experiments", "text": "Graphical models are widely used in scienti fic and engineering research to represent conditional independence structures between random variables. In many controlled experiments, environmental changes or external stimuli can often alter the conditional dependence between the random variables, and potentially produce significant structural changes in the corresponding graphical models. Therefore, it is of great importance to be able to detect such structural changes from data, so as to gain novel insights into where and how the structural changes take place and help the system adapt to the new environment. Here we report an effective learning strategy to extract structural changes in Gaussian graphical model using l1-regularization based convex optimization. We discuss the properties of the problem formulation and introduce an efficient implementation by the block coordinate descent algorithm. We demonstrate the principle of the approach on a numerical simulation experiment, and we then apply the algorithm to the modeling of gene regulatory networks under different conditions and obtain promising yet biologically plausible results.", "source": "arxiv/ml"}
{"id": "arxiv:1422", "title": "Source Separation and Higher-Order Causal Analysis of MEG and EEG", "text": "Separation of the sources and analysis of their connectivity have been an important topic in EEG/MEG analysis. To solve this problem in an automatic manner, we propose a two-layer model, in which the sources are conditionally uncorrelated from each other, but not independent; the dependence is caused by the causality in their time-varying variances (envelopes). The model is identified in two steps. We first propose a new source separation technique which takes into account the autocorrelations (which may be time-varying) and time-varying variances of the sources. The causality in the envelopes is then discovered by exploiting a special kind of multivariate GARCH (generalized autoregressive conditional heteroscedasticity) model. The resulting causal diagram gives the effective connectivity between the separated sources; in our experimental results on MEG data, sources with similar functions are grouped together, with negative influences between groups, and the groups are connected via some interesting sources.", "source": "arxiv/ml"}
{"id": "arxiv:1423", "title": "Invariant Gaussian Process Latent Variable Models and Application in Causal Discovery", "text": "In nonlinear latent variable models or dynamic models, if we consider the latent variables as confounders (common causes), the noise dependencies imply further relations between the observed variables. Such models are then closely related to causal discovery in the presence of nonlinear confounders, which is a challenging problem. However, generally in such models the observation noise is assumed to be independent across data dimensions, and consequently the noise dependencies are ignored. In this paper we focus on the Gaussian process latent variable model (GPLVM), from which we develop an extended model called invariant GPLVM (IGPLVM), which can adapt to arbitrary noise covariances. With the Gaussian process prior put on a particular transformation of the latent nonlinear functions, instead of the original ones, the algorithm for IGPLVM involves almost the same computational loads as that for the original GPLVM. Besides its potential application in causal discovery, IGPLVM has the advantage that its estimated latent nonlinear manifold is invariant to any nonsingular linear transformation of the data. Experimental results on both synthetic and realworld data show its encouraging performance in nonlinear manifold learning and causal discovery.", "source": "arxiv/ml"}
{"id": "arxiv:1424", "title": "A Convex Formulation for Learning Task Relationships in Multi-Task Learning", "text": "Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning. This formulation can be viewed as a novel generalization of the regularization framework for single-task learning. Besides modeling positive task correlation, our method, called multi-task relationship learning (MTRL), can also describe negative task correlation and identify outlier tasks based on the same underlying principle. Under this regularization framework, the objective function of MTRL is convex. For efficiency, we use an alternating method to learn the optimal model parameters for each task as well as the relationships between tasks. We study MTRL in the symmetric multi-task learning setting and then generalize it to the asymmetric setting as well. We also study the relationships between MTRL and some existing multi-task learning methods. Experiments conducted on a toy problem as well as several benchmark data sets demonstrate the effectiveness of MTRL.", "source": "arxiv/ml"}
{"id": "arxiv:1425", "title": "Automatic Tuning of Interactive Perception Applications", "text": "Interactive applications incorporating high-data rate sensing and computer vision are becoming possible due to novel runtime systems and the use of parallel computation resources. To allow interactive use, such applications require careful tuning of multiple application parameters to meet required fidelity and latency bounds. This is a nontrivial task, often requiring expert knowledge, which becomes intractable as resources and application load characteristics change. This paper describes a method for automatic performance tuning that learns application characteristics and effects of tunable parameters online, and constructs models that are used to maximize fidelity for a given latency constraint. The paper shows that accurate latency models can be learned online, knowledge of application structure can be used to reduce the complexity of the learning task, and operating points can be found that achieve 90% of the optimal fidelity by exploring the parameter space only 3% of the time.", "source": "arxiv/ml"}
{"id": "arxiv:1426", "title": "Learning Feature Hierarchies with Centered Deep Boltzmann Machines", "text": "Deep Boltzmann machines are in principle powerful models for extracting the hierarchical structure of data. Unfortunately, attempts to train layers jointly (without greedy layer-wise pretraining) have been largely unsuccessful. We propose a modification of the learning algorithm that initially recenters the output of the activation functions to zero. This modification leads to a better conditioned Hessian and thus makes learning easier. We test the algorithm on real data and demonstrate that our suggestion, the centered deep Boltzmann machine, learns a hierarchy of increasingly abstract representations and a better generative model of data.", "source": "arxiv/ml"}
{"id": "arxiv:1427", "title": "Data Mining: A Prediction for Performance Improvement of Engineering Students using Classification", "text": "Now-a-days the amount of data stored in educational database increasing rapidly. These databases contain hidden information for improvement of students' performance. Educational data mining is used to study the data available in the educational field and bring out the hidden knowledge from it. Classification methods like decision trees, Bayesian network etc can be applied on the educational data for predicting the student's performance in examination. This prediction will help to identify the weak students and help them to score better marks. The C4.5, ID3 and CART decision tree algorithms are applied on engineering student's data to predict their performance in the final exam. The outcome of the decision tree predicted the number of students who are likely to pass, fail or promoted to next year. The results provide steps to improve the performance of the students who were predicted to fail or promoted. After the declaration of the results in the final examination the marks obtained by the students are fed into the system and the results were analyzed for the next session. The comparative analysis of the results states that the prediction has helped the weaker students to improve and brought out betterment in the result.", "source": "arxiv/ml"}
{"id": "arxiv:1428", "title": "Learning loopy graphical models with latent variables: Efficient methods and guarantees", "text": "The problem of structure estimation in graphical models with latent variables is considered. We characterize conditions for tractable graph estimation and develop efficient methods with provable guarantees. We consider models where the underlying Markov graph is locally tree-like, and the model is in the regime of correlation decay. For the special case of the Ising model, the number of samples $n$ required for structural consistency of our method scales as $n=\\Omega(\\theta_{\\min}^{-\\delta\\eta(\\eta+1)-2}\\log p)$, where p is the number of variables, $\\theta_{\\min}$ is the minimum edge potential, $\\delta$ is the depth (i.e., distance from a hidden node to the nearest observed nodes), and $\\eta$ is a parameter which depends on the bounds on node and edge potentials in the Ising model. Necessary conditions for structural consistency under any algorithm are derived and our method nearly matches the lower bound on sample requirements. Further, the proposed method is practical to implement and provides flexibility to control the number of latent variables and the cycle lengths in the output graph.", "source": "arxiv/ml"}
{"id": "arxiv:1429", "title": "Distributed Cooperative Q-learning for Power Allocation in Cognitive Femtocell Networks", "text": "In this paper, we propose a distributed reinforcement learning (RL) technique called distributed power control using Q-learning (DPC-Q) to manage the interference caused by the femtocells on macro-users in the downlink. The DPC-Q leverages Q-Learning to identify the sub-optimal pattern of power allocation, which strives to maximize femtocell capacity, while guaranteeing macrocell capacity level in an underlay cognitive setting. We propose two different approaches for the DPC-Q algorithm: namely, independent, and cooperative. In the former, femtocells learn independently from each other while in the latter, femtocells share some information during learning in order to enhance their performance. Simulation results show that the independent approach is capable of mitigating the interference generated by the femtocells on macro-users. Moreover, the results show that cooperation enhances the performance of the femtocells in terms of speed of convergence, fairness and aggregate femtocell capacity.", "source": "arxiv/ml"}
{"id": "arxiv:1430", "title": "On Training Deep Boltzmann Machines", "text": "The deep Boltzmann machine (DBM) has been an important development in the quest for powerful \"deep\" probabilistic models. To date, simultaneous or joint training of all layers of the DBM has been largely unsuccessful with existing training methods. We introduce a simple regularization scheme that encourages the weight vectors associated with each hidden unit to have similar norms. We demonstrate that this regularization can be easily combined with standard stochastic maximum likelihood to yield an effective training strategy for the simultaneous training of all layers of the deep Boltzmann machine.", "source": "arxiv/ml"}
{"id": "arxiv:1431", "title": "Semi-Supervised Single- and Multi-Domain Regression with Multi-Domain Training", "text": "We address the problems of multi-domain and single-domain regression based on distinct and unpaired labeled training sets for each of the domains and a large unlabeled training set from all domains. We formulate these problems as a Bayesian estimation with partial knowledge of statistical relations. We propose a worst-case design strategy and study the resulting estimators. Our analysis explicitly accounts for the cardinality of the labeled sets and includes the special cases in which one of the labeled sets is very large or, in the other extreme, completely missing. We demonstrate our estimators in the context of removing expressions from facial images and in the context of audio-visual word recognition, and provide comparisons to several recently proposed multi-modal learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1432", "title": "On the Equivalence between Herding and Conditional Gradient Algorithms", "text": "We show that the herding procedure of Welling (2009) takes exactly the form of a standard convex optimization algorithm--namely a conditional gradient algorithm minimizing a quadratic moment discrepancy. This link enables us to invoke convergence results from convex optimization and to consider faster alternatives for the task of approximating integrals in a reproducing kernel Hilbert space. We study the behavior of the different variants through numerical simulations. The experiments indicate that while we can improve over herding on the task of approximating integrals, the original herding algorithm tends to approach more often the maximum entropy distribution, shedding more light on the learning bias behind herding.", "source": "arxiv/ml"}
{"id": "arxiv:1433", "title": "A Novel Training Algorithm for HMMs with Partial and Noisy Access to the States", "text": "This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have \\emph{partial} and \\emph{noisy} access to the hidden state sequence as side information. This access can be seen as \"partial labeling\" of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the \"achievable margin\" defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions.", "source": "arxiv/ml"}
{"id": "arxiv:1434", "title": "Adaptive Mixture Methods Based on Bregman Divergences", "text": "We investigate adaptive mixture methods that linearly combine outputs of $m$ constituent filters running in parallel to model a desired signal. We use \"Bregman divergences\" and obtain certain multiplicative updates to train the linear combination weights under an affine constraint or without any constraints. We use unnormalized relative entropy and relative entropy to define two different Bregman divergences that produce an unnormalized exponentiated gradient update and a normalized exponentiated gradient update on the mixture weights, respectively. We then carry out the mean and the mean-square transient analysis of these adaptive algorithms when they are used to combine outputs of $m$ constituent filters. We illustrate the accuracy of our results and demonstrate the effectiveness of these updates for sparse mixture systems.", "source": "arxiv/ml"}
{"id": "arxiv:1435", "title": "Very Short Literature Survey From Supervised Learning To Surrogate Modeling", "text": "The past century was era of linear systems. Either systems (especially industrial ones) were simple (quasi)linear or linear approximations were accurate enough. In addition, just at the ending decades of the century profusion of computing devices were available, before then due to lack of computational resources it was not easy to evaluate available nonlinear system studies. At the moment both these two conditions changed, systems are highly complex and also pervasive amount of computation strength is cheap and easy to achieve. For recent era, a new branch of supervised learning well known as surrogate modeling (meta-modeling, surface modeling) has been devised which aimed at answering new needs of modeling realm. This short literature survey is on to introduce surrogate modeling to whom is familiar with the concepts of supervised learning. Necessity, challenges and visions of the topic are considered.", "source": "arxiv/ml"}
{"id": "arxiv:1436", "title": "Parallel Matrix Factorization for Binary Response", "text": "Predicting user affinity to items is an important problem in applications like content optimization, computational advertising, and many more. While bilinear random effect models (matrix factorization) provide state-of-the-art performance when minimizing RMSE through a Gaussian response model on explicit ratings data, applying it to imbalanced binary response data presents additional challenges that we carefully study in this paper. Data in many applications usually consist of users' implicit response that are often binary -- clicking an item or not; the goal is to predict click rates, which is often combined with other measures to calculate utilities to rank items at runtime of the recommender systems. Because of the implicit nature, such data are usually much larger than explicit rating data and often have an imbalanced distribution with a small fraction of click events, making accurate click rate prediction difficult. In this paper, we address two problems. First, we show previous techniques to estimate bilinear random effect models with binary data are less accurate compared to our new approach based on adaptive rejection sampling, especially for imbalanced response. Second, we develop a parallel bilinear random effect model fitting framework using Map-Reduce paradigm that scales to massive datasets. Our parallel algorithm is based on a \"divide and conquer\" strategy coupled with an ensemble approach. Through experiments on the benchmark MovieLens data, a small Yahoo! Front Page data set, and a large Yahoo! Front Page data set that contains 8M users and 1B binary observations, we show that careful handling of binary response as well as identifiability issues are needed to achieve good performance for click rate prediction, and that the proposed adaptive rejection sampler and the partitioning as well as ensemble techniques significantly improve model performance.", "source": "arxiv/ml"}
{"id": "arxiv:1437", "title": "$k$-MLE: A fast algorithm for learning statistical mixture models", "text": "We describe $k$-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expected complete) likelihood. Given prescribed mixture weights, the hard clustering $k$-MLE algorithm iteratively assigns data to the most likely weighted component and update the component models using Maximum Likelihood Estimators (MLEs). Using the duality between exponential families and Bregman divergences, we prove that the local convergence of the complete likelihood of $k$-MLE follows directly from the convergence of a dual additively weighted Bregman hard clustering. The inner loop of $k$-MLE can be implemented using any $k$-means heuristic like the celebrated Lloyd's batched or Hartigan's greedy swap updates. We then show how to update the mixture weights by minimizing a cross-entropy criterion that implies to update weights by taking the relative proportion of cluster points, and reiterate the mixture parameter update and mixture weight update processes until convergence. Hard EM is interpreted as a special case of $k$-MLE when both the component update and the weight update are performed successively in the inner loop. To initialize $k$-MLE, we propose $k$-MLE++, a careful initialization of $k$-MLE guaranteeing probabilistically a global bound on the best possible complete likelihood.", "source": "arxiv/ml"}
{"id": "arxiv:1438", "title": "Distribution Free Prediction Bands", "text": "We study distribution free, nonparametric prediction bands with a special focus on their finite sample behavior. First we investigate and develop different notions of finite sample coverage guarantees. Then we give a new prediction band estimator by combining the idea of \"conformal prediction\" (Vovk et al. 2009) with nonparametric conditional density estimation. The proposed estimator, called COPS (Conformal Optimized Prediction Set), always has finite sample guarantee in a stronger sense than the original conformal prediction estimator. Under regularity conditions the estimator converges to an oracle band at a minimax optimal rate. A fast approximation algorithm and a data driven method for selecting the bandwidth are developed. The method is illustrated first in simulated data. Then, an application shows that the proposed method gives desirable prediction intervals in an automatic way, as compared to the classical linear regression modeling.", "source": "arxiv/ml"}
{"id": "arxiv:1439", "title": "A Regularization Approach for Prediction of Edges and Node Features in Dynamic Graphs", "text": "We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure. In this paper, we formulate a hybrid approach that simultaneously learns the structure of the graph and predicts the values of the node-related functions. Our approach is based on the optimization of a joint regularization objective. We empirically test the benefits of the proposed method with both synthetic and real data. The results indicate that joint regularization improves prediction performance over the graph evolution and the node features.", "source": "arxiv/ml"}
{"id": "arxiv:1440", "title": "Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA", "text": "An automated technique has recently been proposed to transfer learning in the hierarchical Bayesian optimization algorithm (hBOA) based on distance-based statistics. The technique enables practitioners to improve hBOA efficiency by collecting statistics from probabilistic models obtained in previous hBOA runs and using the obtained statistics to bias future hBOA runs on similar problems. The purpose of this paper is threefold: (1) test the technique on several classes of NP-complete problems, including MAXSAT, spin glasses and minimum vertex cover; (2) demonstrate that the technique is effective even when previous runs were done on problems of different size; (3) provide empirical evidence that combining transfer learning with other efficiency enhancement techniques can often yield nearly multiplicative speedups.", "source": "arxiv/ml"}
{"id": "arxiv:1441", "title": "A Bayesian Model Committee Approach to Forecasting Global Solar Radiation", "text": "This paper proposes to use a rather new modelling approach in the realm of solar radiation forecasting. In this work, two forecasting models: Autoregressive Moving Average (ARMA) and Neural Network (NN) models are combined to form a model committee. The Bayesian inference is used to affect a probability to each model in the committee. Hence, each model's predictions are weighted by their respective probability. The models are fitted to one year of hourly Global Horizontal Irradiance (GHI) measurements. Another year (the test set) is used for making genuine one hour ahead (h+1) out-of-sample forecast comparisons. The proposed approach is benchmarked against the persistence model. The very first results show an improvement brought by this approach.", "source": "arxiv/ml"}
{"id": "arxiv:1442", "title": "Credal Classification based on AODE and compression coefficients", "text": "Bayesian model averaging (BMA) is an approach to average over alternative models; yet, it usually gets excessively concentrated around the single most probable model, therefore achieving only sub-optimal classification performance. The compression-based approach (Boulle, 2007) overcomes this problem, averaging over the different models by applying a logarithmic smoothing over the models' posterior probabilities. This approach has shown excellent performances when applied to ensembles of naive Bayes classifiers. AODE is another ensemble of models with high performance (Webb, 2005), based on a collection of non-naive classifiers (called SPODE) whose probabilistic predictions are aggregated by simple arithmetic mean. Aggregating the SPODEs via BMA rather than by arithmetic mean deteriorates the performance; instead, we aggregate the SPODEs via the compression coefficients and we show that the resulting classifier obtains a slight but consistent improvement over AODE. However, an important issue in any Bayesian ensemble of models is the arbitrariness in the choice of the prior over the models. We address this problem by the paradigm of credal classification, namely by substituting the unique prior with a set of priors. Credal classifier automatically recognize the prior-dependent instances, namely the instances whose most probable class varies, when different priors are considered; in these cases, credal classifiers remain reliable by returning a set of classes rather than a single class. We thus develop the credal version of both the BMA-based and the compression-based ensemble of SPODEs, substituting the single prior over the models by a set of priors. Experiments show that both credal classifiers provide higher classification reliability than their determinate counterparts; moreover the compression-based credal classifier compares favorably to previous credal classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:1443", "title": "Spectral dimensionality reduction for HMMs", "text": "Hidden Markov Models (HMMs) can be accurately approximated using co-occurrence frequencies of pairs and triples of observations by using a fast spectral method in contrast to the usual slow methods like EM or Gibbs sampling. We provide a new spectral method which significantly reduces the number of model parameters that need to be estimated, and generates a sample complexity that does not depend on the size of the observation vocabulary. We present an elementary proof giving bounds on the relative accuracy of probability estimates from our model. (Correlaries show our bounds can be weakened to provide either L1 bounds or KL bounds which provide easier direct comparisons to previous work.) Our theorem uses conditions that are checkable from the data, instead of putting conditions on the unobservable Markov transition matrix.", "source": "arxiv/ml"}
{"id": "arxiv:1444", "title": "Statistical Mechanics of Dictionary Learning", "text": "Finding a basis matrix (dictionary) by which objective signals are represented sparsely is of major relevance in various scientific and technological fields. We consider a problem to learn a dictionary from a set of training signals. We employ techniques of statistical mechanics of disordered systems to evaluate the size of the training set necessary to typically succeed in the dictionary learning. The results indicate that the necessary size is much smaller than previously estimated, which theoretically supports and/or encourages the use of dictionary learning in practical situations.", "source": "arxiv/ml"}
{"id": "arxiv:1445", "title": "Transforming Graph Representations for Statistical Relational Learning", "text": "Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for graph-based relational data. Since the choice of relational data representation for the nodes, links, and features can dramatically affect the capabilities of SRL algorithms, we survey approaches and opportunities for relational representation transformation designed to improve the performance of these algorithms. This leads us to introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. In particular, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey and compare competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.", "source": "arxiv/ml"}
{"id": "arxiv:1446", "title": "A Lipschitz Exploration-Exploitation Scheme for Bayesian Optimization", "text": "The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the optimizer of the function by asking only a few function evaluations at locations carefully selected based on a posterior model. In this paper, we assume the unknown function is Lipschitz continuous. Leveraging the Lipschitz property, we propose an algorithm with a distinct exploration phase followed by an exploitation phase. The exploration phase aims to select samples that shrink the search space as much as possible. The exploitation phase then focuses on the reduced search space and selects samples closest to the optimizer. Considering the Expected Improvement (EI) as a baseline, we empirically show that the proposed algorithm significantly outperforms EI.", "source": "arxiv/ml"}
{"id": "arxiv:1447", "title": "Near-Optimal Algorithms for Online Matrix Prediction", "text": "In several online prediction problems of recent interest the comparison class is composed of matrices with bounded entries. For example, in the online max-cut problem, the comparison class is matrices which represent cuts of a given graph and in online gambling the comparison class is matrices which represent permutations over n teams. Another important example is online collaborative filtering in which a widely used comparison class is the set of matrices with a small trace norm. In this paper we isolate a property of matrices, which we call (beta,tau)-decomposability, and derive an efficient online learning algorithm, that enjoys a regret bound of O*(sqrt(beta tau T)) for all problems in which the comparison class is composed of (beta,tau)-decomposable matrices. By analyzing the decomposability of cut matrices, triangular matrices, and low trace-norm matrices, we derive near optimal regret bounds for online max-cut, online gambling, and online collaborative filtering. In particular, this resolves (in the affirmative) an open problem posed by Abernethy (2010); Kleinberg et al (2010). Finally, we derive lower bounds for the three problems and show that our upper bounds are optimal up to logarithmic factors. In particular, our lower bound for the online collaborative filtering problem resolves another open problem posed by Shamir and Srebro (2011).", "source": "arxiv/ml"}
{"id": "arxiv:1448", "title": "A New Approach to Speeding Up Topic Modeling", "text": "Latent Dirichlet allocation (LDA) is a widely-used probabilistic topic modeling paradigm, and recently finds many applications in computer vision and computational biology. In this paper, we propose a fast and accurate batch algorithm, active belief propagation (ABP), for training LDA. Usually batch LDA algorithms require repeated scanning of the entire corpus and searching the complete topic space. To process massive corpora having a large number of topics, the training iteration of batch LDA algorithms is often inefficient and time-consuming. To accelerate the training speed, ABP actively scans the subset of corpus and searches the subset of topic space for topic modeling, therefore saves enormous training time in each iteration. To ensure accuracy, ABP selects only those documents and topics that contribute to the largest residuals within the residual belief propagation (RBP) framework. On four real-world corpora, ABP performs around $10$ to $100$ times faster than state-of-the-art batch LDA algorithms with a comparable topic modeling accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:1449", "title": "A New Fuzzy Stacked Generalization Technique and Analysis of its Performance", "text": "In this study, a new Stacked Generalization technique called Fuzzy Stacked Generalization (FSG) is proposed to minimize the difference between N -sample and large-sample classification error of the Nearest Neighbor classifier. The proposed FSG employs a new hierarchical distance learning strategy to minimize the error difference. For this purpose, we first construct an ensemble of base-layer fuzzy k- Nearest Neighbor (k-NN) classifiers, each of which receives a different feature set extracted from the same sample set. The fuzzy membership values computed at the decision space of each fuzzy k-NN classifier are concatenated to form the feature vectors of a fusion space. Finally, the feature vectors are fed to a meta-layer classifier to learn the degree of accuracy of the decisions of the base-layer classifiers for meta-layer classification. Rather than the power of the individual base layer-classifiers, diversity and cooperation of the classifiers become an important issue to improve the overall performance of the proposed FSG. A weak base-layer classifier may boost the overall performance more than a strong classifier, if it is capable of recognizing the samples, which are not recognized by the rest of the classifiers, in its own feature space. The experiments explore the type of the collaboration among the individual classifiers required for an improved performance of the suggested architecture. Experiments on multiple feature real-world datasets show that the proposed FSG performs better than the state of the art ensemble learning algorithms such as Adaboost, Random Subspace and Rotation Forest. On the other hand, compatible performances are observed in the experiments on single feature multi-attribute datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1450", "title": "The Kernelized Stochastic Batch Perceptron", "text": "We present a novel approach for training kernel Support Vector Machines, establish learning runtime guarantees for our method that are better then those of any other known kernelized SVM optimization approach, and show that our method works well in practice compared to existing alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:1451", "title": "Validation of nonlinear PCA", "text": "Linear principal component analysis (PCA) can be extended to a nonlinear PCA by using artificial neural networks. But the benefit of curved components requires a careful control of the model complexity. Moreover, standard techniques for model selection, including cross-validation and more generally the use of an independent test set, fail when applied to nonlinear PCA because of its inherent unsupervised characteristics. This paper presents a new approach for validating the complexity of nonlinear PCA models by using the error in missing data estimation as a criterion for model selection. It is motivated by the idea that only the model of optimal complexity is able to predict missing values with the highest accuracy. While standard test set validation usually favours over-fitted nonlinear PCA models, the proposed model validation approach correctly selects the optimal model complexity.", "source": "arxiv/ml"}
{"id": "arxiv:1452", "title": "Relax and Localize: From Value to Algorithms", "text": "We show a principled way of deriving online learning algorithms from a minimax analysis. Various upper bounds on the minimax value, previously thought to be non-constructive, are shown to yield algorithms. This allows us to seamlessly recover known methods and to derive new ones. Our framework also captures such \"unorthodox\" methods as Follow the Perturbed Leader and the R^2 forecaster. We emphasize that understanding the inherent complexity of the learning problem leads to the development of algorithms. We define local sequential Rademacher complexities and associated algorithms that allow us to obtain faster rates in online learning, similarly to statistical learning theory. Based on these localized complexities we build a general adaptive method that can take advantage of the suboptimality of the observed sequence. We present a number of new algorithms, including a family of randomized methods that use the idea of a \"random playout\". Several new versions of the Follow-the-Perturbed-Leader algorithms are presented, as well as methods based on the Littlestone's dimension, efficient methods for matrix completion with trace norm, and algorithms for the problems of transductive learning and prediction with static experts.", "source": "arxiv/ml"}
{"id": "arxiv:1453", "title": "PID Parameters Optimization by Using Genetic Algorithm", "text": "Time delays are components that make time-lag in systems response. They arise in physical, chemical, biological and economic systems, as well as in the process of measurement and computation. In this work, we implement Genetic Algorithm (GA) in determining PID controller parameters to compensate the delay in First Order Lag plus Time Delay (FOLPD) and compare the results with Iterative Method and Ziegler-Nichols rule results.", "source": "arxiv/ml"}
{"id": "arxiv:1454", "title": "Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback", "text": "Albeit, the implicit feedback based recommendation problem - when only the user history is available but there are no ratings - is the most typical setting in real-world applications, it is much less researched than the explicit feedback case. State-of-the-art algorithms that are efficient on the explicit case cannot be straightforwardly transformed to the implicit case if scalability should be maintained. There are few if any implicit feedback benchmark datasets, therefore new ideas are usually experimented on explicit benchmarks. In this paper, we propose a generic context-aware implicit feedback recommender algorithm, coined iTALS. iTALS apply a fast, ALS-based tensor factorization learning method that scales linearly with the number of non-zero elements in the tensor. The method also allows us to incorporate diverse context information into the model while maintaining its computational efficiency. In particular, we present two such context-aware implementation variants of iTALS. The first incorporates seasonality and enables to distinguish user behavior in different time intervals. The other views the user history as sequential information and has the ability to recognize usage pattern typical to certain group of items, e.g. to automatically tell apart product types or categories that are typically purchased repetitively (collectibles, grocery goods) or once (household appliances). Experiments performed on three implicit datasets (two proprietary ones and an implicit variant of the Netflix dataset) show that by integrating context-aware information with our factorization framework into the state-of-the-art implicit recommender algorithm the recommendation quality improves significantly.", "source": "arxiv/ml"}
{"id": "arxiv:1455", "title": "Distribution-Dependent Sample Complexity of Large Margin Learning", "text": "We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of the data distribution, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the margin-adapted dimension of the data distribution. The upper bounds are universal, and the lower bounds hold for the rich family of sub-Gaussian distributions with independent features. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification. To prove the lower bound, we develop several new tools of independent interest. These include new connections between shattering and hardness of learning, new properties of shattering with linear classifiers, and a new lower bound on the smallest eigenvalue of a random Gram matrix generated by sub-Gaussian variables. Our results can be used to quantitatively compare large margin learning to other learning rules, and to improve the effectiveness of methods that use sample complexity bounds, such as active learning.", "source": "arxiv/ml"}
{"id": "arxiv:1456", "title": "Fast projections onto mixed-norm balls with applications", "text": "Joint sparsity offers powerful structural cues for feature selection, especially for variables that are expected to demonstrate a \"grouped\" behavior. Such behavior is commonly modeled via group-lasso, multitask lasso, and related methods where feature selection is effected via mixed-norms. Several mixed-norm based sparse models have received substantial attention, and for some cases efficient algorithms are also available. Surprisingly, several constrained sparse models seem to be lacking scalable algorithms. We address this deficiency by presenting batch and online (stochastic-gradient) optimization methods, both of which rely on efficient projections onto mixed-norm balls. We illustrate our methods by applying them to the multitask lasso. We conclude by mentioning some open problems.", "source": "arxiv/ml"}
{"id": "arxiv:1457", "title": "Learning Fuzzy {\\beta}-Certain and {\\beta}-Possible rules from incomplete quantitative data by rough sets", "text": "The rough-set theory proposed by Pawlak, has been widely used in dealing with data classification problems. The original rough-set model is, however, quite sensitive to noisy data. Tzung thus proposed deals with the problem of producing a set of fuzzy certain and fuzzy possible rules from quantitative data with a predefined tolerance degree of uncertainty and misclassification. This model allowed, which combines the variable precision rough-set model and the fuzzy set theory, is thus proposed to solve this problem. This paper thus deals with the problem of producing a set of fuzzy certain and fuzzy possible rules from incomplete quantitative data with a predefined tolerance degree of uncertainty and misclassification. A new method, incomplete quantitative data for rough-set model and the fuzzy set theory, is thus proposed to solve this problem. It first transforms each quantitative value into a fuzzy set of linguistic terms using membership functions and then finding incomplete quantitative data with lower and the fuzzy upper approximations. It second calculates the fuzzy {\\beta}-lower and the fuzzy {\\beta}-upper approximations. The certain and possible rules are then generated based on these fuzzy approximations. These rules can then be used to classify unknown objects.", "source": "arxiv/ml"}
{"id": "arxiv:1458", "title": "Minimal model of associative learning for cross-situational lexicon acquisition", "text": "An explanation for the acquisition of word-object mappings is the associative learning in a cross-situational scenario. Here we present analytical results of the performance of a simple associative learning algorithm for acquiring a one-to-one mapping between $N$ objects and $N$ words based solely on the co-occurrence between objects and words. In particular, a learning trial in our learning scenario consists of the presentation of $C + 1 < N$ objects together with a target word, which refers to one of the objects in the context. We find that the learning times are distributed exponentially and the learning rates are given by $\\ln{[\\frac{N(N-1)}{C + (N-1)^{2}}]}$ in the case the $N$ target words are sampled randomly and by $\\frac{1}{N} \\ln [\\frac{N-1}{C}] $ in the case they follow a deterministic presentation sequence. This learning performance is much superior to those exhibited by humans and more realistic learning algorithms in cross-situational experiments. We show that introduction of discrimination limitations using Weber's law and forgetting reduce the performance of the associative algorithm to the human level.", "source": "arxiv/ml"}
{"id": "arxiv:1459", "title": "UCB Algorithm for Exponential Distributions", "text": "We introduce in this paper a new algorithm for Multi-Armed Bandit (MAB) problems. A machine learning paradigm popular within Cognitive Network related topics (e.g., Spectrum Sensing and Allocation). We focus on the case where the rewards are exponentially distributed, which is common when dealing with Rayleigh fading channels. This strategy, named Multiplicative Upper Confidence Bound (MUCB), associates a utility index to every available arm, and then selects the arm with the highest index. For every arm, the associated index is equal to the product of a multiplicative factor by the sample mean of the rewards collected by this arm. We show that the MUCB policy has a low complexity and is order optimal.", "source": "arxiv/ml"}
{"id": "arxiv:1460", "title": "The threshold EM algorithm for parameter learning in bayesian network with incomplete data", "text": "Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning parameter algorithms are suggested foreground EM, Gibbs sampling and RBE algorithms. In order to limit the search space and escape from local maxima produced by executing EM algorithm, this paper presents a learning parameter algorithm that is a fusion of EM and RBE algorithms. This algorithm incorporates the range of a parameter into the EM algorithm. This range is calculated by the first step of RBE algorithm allowing a regularization of each parameter in bayesian network after the maximization step of the EM algorithm. The threshold EM algorithm is applied in brain tumor diagnosis and show some advantages and disadvantages over the EM algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1461", "title": "Density-sensitive semisupervised inference", "text": "Semisupervised methods are techniques for using labeled data $(X_1,Y_1),\\ldots,(X_n,Y_n)$ together with unlabeled data $X_{n+1},\\ldots,X_N$ to make predictions. These methods invoke some assumptions that link the marginal distribution $P_X$ of X to the regression function f(x). For example, it is common to assume that f is very smooth over high density regions of $P_X$. Many of the methods are ad-hoc and have been shown to work in specific examples but are lacking a theoretical foundation. We provide a minimax framework for analyzing semisupervised methods. In particular, we study methods based on metrics that are sensitive to the distribution $P_X$. Our model includes a parameter $\\alpha$ that controls the strength of the semisupervised assumption. We then use the data to adapt to $\\alpha$.", "source": "arxiv/ml"}
{"id": "arxiv:1462", "title": "The asymptotics of ranking algorithms", "text": "We consider the predictive problem of supervised ranking, where the task is to rank sets of candidate items returned in response to queries. Although there exist statistical procedures that come with guarantees of consistency in this setting, these procedures require that individuals provide a complete ranking of all items, which is rarely feasible in practice. Instead, individuals routinely provide partial preference information, such as pairwise comparisons of items, and more practical approaches to ranking have aimed at modeling this partial preference data directly. As we show, however, such an approach raises serious theoretical challenges. Indeed, we demonstrate that many commonly used surrogate losses for pairwise comparison data do not yield consistency; surprisingly, we show inconsistency even in low-noise settings. With these negative results as motivation, we present a new approach to supervised ranking based on aggregation of partial preferences, and we develop $U$-statistic-based empirical risk minimization procedures. We present an asymptotic analysis of these new procedures, showing that they yield consistency results that parallel those available for classification. We complement our theoretical results with an experiment studying the new procedures in a large-scale web-ranking task.", "source": "arxiv/ml"}
{"id": "arxiv:1463", "title": "On Power-law Kernels, corresponding Reproducing Kernel Hilbert Space and Applications", "text": "The role of kernels is central to machine learning. Motivated by the importance of power-law distributions in statistical modeling, in this paper, we propose the notion of power-law kernels to investigate power-laws in learning problem. We propose two power-law kernels by generalizing Gaussian and Laplacian kernels. This generalization is based on distributions, arising out of maximization of a generalized information measure known as nonextensive entropy that is very well studied in statistical mechanics. We prove that the proposed kernels are positive definite, and provide some insights regarding the corresponding Reproducing Kernel Hilbert Space (RKHS). We also study practical significance of both kernels in classification and regression, and present some simulation results.", "source": "arxiv/ml"}
{"id": "arxiv:1464", "title": "Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits", "text": "In budget-limited multi-armed bandit (MAB) problems, the learner's actions are costly and constrained by a fixed budget. Consequently, an optimal exploitation policy may not be to pull the optimal arm repeatedly, as is the case in other variants of MAB, but rather to pull the sequence of different arms that maximises the agent's total reward within the budget. This difference from existing MABs means that new approaches to maximising the total reward are required. Given this, we develop two pulling policies, namely: (i) KUBE; and (ii) fractional KUBE. Whereas the former provides better performance up to 40% in our experimental settings, the latter is computationally less expensive. We also prove logarithmic upper bounds for the regret of both policies, and show that these bounds are asymptotically optimal (i.e. they only differ from the best possible regret by a constant factor).", "source": "arxiv/ml"}
{"id": "arxiv:1465", "title": "Learning Topic Models - Going beyond SVD", "text": "Topic Modeling is an approach used for automatic comprehension and classification of data in a variety of settings, and perhaps the canonical application is in uncovering thematic structure in a corpus of documents. A number of foundational works both in machine learning and in theory have suggested a probabilistic model for documents, whereby documents arise as a convex combination of (i.e. distribution on) a small number of topic vectors, each topic vector being a distribution on words (i.e. a vector of word-frequencies). Similar models have since been used in a variety of application areas; the Latent Dirichlet Allocation or LDA model of Blei et al. is especially popular. Theoretical studies of topic modeling focus on learning the model's parameters assuming the data is actually generated from it. Existing approaches for the most part rely on Singular Value Decomposition(SVD), and consequently have one of two limitations: these works need to either assume that each document contains only one topic, or else can only recover the span of the topic vectors instead of the topic vectors themselves. This paper formally justifies Nonnegative Matrix Factorization(NMF) as a main tool in this context, which is an analog of SVD where all vectors are nonnegative. Using this tool we give the first polynomial-time algorithm for learning topic models without the above two limitations. The algorithm uses a fairly mild assumption about the underlying topic matrix called separability, which is usually found to hold in real-life data. A compelling feature of our algorithm is that it generalizes to models that incorporate topic-topic correlations, such as the Correlated Topic Model and the Pachinko Allocation Model. We hope that this paper will motivate further theoretical results that use NMF as a replacement for SVD - just as NMF has come to replace SVD in many applications.", "source": "arxiv/ml"}
{"id": "arxiv:1466", "title": "A technical study and analysis on fuzzy similarity based models for text classification", "text": "In this new and current era of technology, advancements and techniques, efficient and effective text document classification is becoming a challenging and highly required area to capably categorize text documents into mutually exclusive categories. Fuzzy similarity provides a way to find the similarity of features among various documents. In this paper, a technical review on various fuzzy similarity based models is given. These models are discussed and compared to frame out their use and necessity. A tour of different methodologies is provided which is based upon fuzzy similarity related concerns. It shows that how text and web documents are categorized efficiently into different categories. Various experimental results of these models are also discussed. The technical comparisons among each model's parameters are shown in the form of a 3-D chart. Such study and technical review provide a strong base of research work done on fuzzy similarity based text document categorization.", "source": "arxiv/ml"}
{"id": "arxiv:1467", "title": "A Fuzzy Similarity Based Concept Mining Model for Text Classification", "text": "Text Classification is a challenging and a red hot field in the current scenario and has great importance in text categorization applications. A lot of research work has been done in this field but there is a need to categorize a collection of text documents into mutually exclusive categories by extracting the concepts or features using supervised learning paradigm and different classification algorithms. In this paper, a new Fuzzy Similarity Based Concept Mining Model (FSCMM) is proposed to classify a set of text documents into pre - defined Category Groups (CG) by providing them training and preparing on the sentence, document and integrated corpora levels along with feature reduction, ambiguity removal on each level to achieve high system performance. Fuzzy Feature Category Similarity Analyzer (FFCSA) is used to analyze each extracted feature of Integrated Corpora Feature Vector (ICFV) with the corresponding categories or classes. This model uses Support Vector Machine Classifier (SVMC) to classify correctly the training data patterns into two groups; i. e., + 1 and - 1, thereby producing accurate and correct results. The proposed model works efficiently and effectively with great performance and high - accuracy results.", "source": "arxiv/ml"}
{"id": "arxiv:1468", "title": "Asymptotic Accuracy of Distribution-Based Estimation for Latent Variables", "text": "Hierarchical statistical models are widely employed in information science and data engineering. The models consist of two types of variables: observable variables that represent the given data and latent variables for the unobservable labels. An asymptotic analysis of the models plays an important role in evaluating the learning process; the result of the analysis is applied not only to theoretical but also to practical situations, such as optimal model selection and active learning. There are many studies of generalization errors, which measure the prediction accuracy of the observable variables. However, the accuracy of estimating the latent variables has not yet been elucidated. For a quantitative evaluation of this, the present paper formulates distribution-based functions for the errors in the estimation of the latent variables. The asymptotic behavior is analyzed for both the maximum likelihood and the Bayes methods.", "source": "arxiv/ml"}
{"id": "arxiv:1469", "title": "Robust Nonnegative Matrix Factorization via $L_1$ Norm Regularization", "text": "Nonnegative Matrix Factorization (NMF) is a widely used technique in many applications such as face recognition, motion segmentation, etc. It approximates the nonnegative data in an original high dimensional space with a linear representation in a low dimensional space by using the product of two nonnegative matrices. In many applications data are often partially corrupted with large additive noise. When the positions of noise are known, some existing variants of NMF can be applied by treating these corrupted entries as missing values. However, the positions are often unknown in many real world applications, which prevents the usage of traditional NMF or other existing variants of NMF. This paper proposes a Robust Nonnegative Matrix Factorization (RobustNMF) algorithm that explicitly models the partial corruption as large additive noise without requiring the information of positions of noise. In practice, large additive noise can be used to model outliers. In particular, the proposed method jointly approximates the clean data matrix with the product of two nonnegative matrices and estimates the positions and values of outliers/noise. An efficient iterative optimization algorithm with a solid theoretical justification has been proposed to learn the desired matrix factorization. Experimental results demonstrate the advantages of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1470", "title": "A Simple Explanation of A Spectral Algorithm for Learning Hidden Markov Models", "text": "A simple linear algebraic explanation of the algorithm in \"A Spectral Algorithm for Learning Hidden Markov Models\" (COLT 2009). Most of the content is in Figure 2; the text just makes everything precise in four nearly-trivial claims.", "source": "arxiv/ml"}
{"id": "arxiv:1471", "title": "Concept Modeling with Superwords", "text": "In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term \"representative\" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the vocabulary, and that flexibly adapt their content based on other relevant semantic information such as textual structure or associated image features. We explore a Bayesian nonparametric model based on nested beta processes that allows for inferring an unknown number of strictly sparse concepts. The resulting model provides an inherently different representation of concepts than a standard LDA (or HDP) based topic model, and allows for direct incorporation of semantic features. We demonstrate the utility of this representation on multilingual blog data and the Congressional Record.", "source": "arxiv/ml"}
{"id": "arxiv:1472", "title": "Modeling Relational Data via Latent Factor Blockmodel", "text": "In this paper we address the problem of modeling relational data, which appear in many applications such as social network analysis, recommender systems and bioinformatics. Previous studies either consider latent feature based models but disregarding local structure in the network, or focus exclusively on capturing local structure of objects based on latent blockmodels without coupling with latent characteristics of objects. To combine the benefits of the previous work, we propose a novel model that can simultaneously incorporate the effect of latent features and covariates if any, as well as the effect of latent structure that may exist in the data. To achieve this, we model the relation graph as a function of both latent feature factors and latent cluster memberships of objects to collectively discover globally predictive intrinsic properties of objects and capture latent block structure in the network to improve prediction performance. We also develop an optimization transfer algorithm based on the generalized EM-style strategy to learn the latent factors. We prove the efficacy of our proposed model through the link prediction task and cluster analysis task, and extensive experiments on the synthetic data and several real world datasets suggest that our proposed LFBM model outperforms the other state of the art approaches in the evaluated tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1473", "title": "Probabilistic Latent Tensor Factorization Model for Link Pattern Prediction in Multi-relational Networks", "text": "This paper aims at the problem of link pattern prediction in collections of objects connected by multiple relation types, where each type may play a distinct role. While common link analysis models are limited to single-type link prediction, we attempt here to capture the correlations among different relation types and reveal the impact of various relation types on performance quality. For that, we define the overall relations between object pairs as a \\textit{link pattern} which consists in interaction pattern and connection structure in the network, and then use tensor formalization to jointly model and predict the link patterns, which we refer to as \\textit{Link Pattern Prediction} (LPP) problem. To address the issue, we propose a Probabilistic Latent Tensor Factorization (PLTF) model by introducing another latent factor for multiple relation types and furnish the Hierarchical Bayesian treatment of the proposed probabilistic model to avoid overfitting for solving the LPP problem. To learn the proposed model we develop an efficient Markov Chain Monte Carlo sampling method. Extensive experiments are conducted on several real world datasets and demonstrate significant improvements over several existing state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:1474", "title": "Stochastic Feature Mapping for PAC-Bayes Classification", "text": "Probabilistic generative modeling of data distributions can potentially exploit hidden information which is useful for discriminative classification. This observation has motivated the development of approaches that couple generative and discriminative models for classification. In this paper, we propose a new approach to couple generative and discriminative models in an unified framework based on PAC-Bayes risk theory. We first derive the model-parameter-independent stochastic feature mapping from a practical MAP classifier operating on generative models. Then we construct a linear stochastic classifier equipped with the feature mapping, and derive the explicit PAC-Bayes risk bounds for such classifier for both supervised and semi-supervised learning. Minimizing the risk bound, using an EM-like iterative procedure, results in a new posterior over hidden variables (E-step) and the update rules of model parameters (M-step). The derivation of the posterior is always feasible due to the way of equipping feature mapping and the explicit form of bounding risk. The derived posterior allows the tuning of generative models and subsequently the feature mappings for better classification. The derived update rules of the model parameters are same to those of the uncoupled models as the feature mapping is model-parameter-independent. Our experiments show that the coupling between data modeling generative model and the discriminative classifier via a stochastic feature mapping in this framework leads to a general classification tool with state-of-the-art performance.", "source": "arxiv/ml"}
{"id": "arxiv:1475", "title": "Plug-in martingales for testing exchangeability on-line", "text": "A standard assumption in machine learning is the exchangeability of data, which is equivalent to assuming that the examples are generated from the same probability distribution independently. This paper is devoted to testing the assumption of exchangeability on-line: the examples arrive one by one, and after receiving each example we would like to have a valid measure of the degree to which the assumption of exchangeability has been falsified. Such measures are provided by exchangeability martingales. We extend known techniques for constructing exchangeability martingales and show that our new method is competitive with the martingales introduced before. Finally we investigate the performance of our testing method on two benchmark datasets, USPS and Statlog Satellite data; for the former, the known techniques give satisfactory results, but for the latter our new more flexible method becomes necessary.", "source": "arxiv/ml"}
{"id": "arxiv:1476", "title": "Distributed Learning, Communication Complexity and Privacy", "text": "We consider the problem of PAC-learning from distributed data and analyze fundamental communication complexity questions involved. We provide general upper and lower bounds on the amount of communication needed to learn well, showing that in addition to VC-dimension and covering number, quantities such as the teaching-dimension and mistake-bound of a class play an important role. We also present tight results for a number of common concept classes including conjunctions, parity functions, and decision lists. For linear separators, we show that for non-concentrated distributions, we can use a version of the Perceptron algorithm to learn with much less communication than the number of updates given by the usual margin bound. We also show how boosting can be performed in a generic manner in the distributed setting to achieve communication with only logarithmic dependence on 1/epsilon for any concept class, and demonstrate how recent work on agnostic learning from class-conditional queries can be used to achieve low communication in agnostic settings as well. We additionally present an analysis of privacy, considering both differential privacy and a notion of distributional privacy that is especially appealing in this context.", "source": "arxiv/ml"}
{"id": "arxiv:1477", "title": "Efficient Protocols for Distributed Classification and Optimization", "text": "In distributed learning, the goal is to perform a learning task over data distributed across multiple nodes with minimal (expensive) communication. Prior work (Daume III et al., 2012) proposes a general model that bounds the communication required for learning classifiers while allowing for $\\eps$ training error on linearly separable data adversarially distributed across nodes. In this work, we develop key improvements and extensions to this basic model. Our first result is a two-party multiplicative-weight-update based protocol that uses $O(d^2 \\log{1/\\eps})$ words of communication to classify distributed data in arbitrary dimension $d$, $\\eps$-optimally. This readily extends to classification over $k$ nodes with $O(kd^2 \\log{1/\\eps})$ words of communication. Our proposed protocol is simple to implement and is considerably more efficient than baselines compared, as demonstrated by our empirical results. In addition, we illustrate general algorithm design paradigms for doing efficient learning over distributed data. We show how to solve fixed-dimensional and high dimensional linear programming efficiently in a distributed setting where constraints may be distributed across nodes. Since many learning problems can be viewed as convex optimization problems where constraints are generated by individual points, this models many typical distributed learning scenarios. Our techniques make use of a novel connection from multipass streaming, as well as adapting the multiplicative-weight-update framework more generally to a distributed setting. As a consequence, our methods extend to the wide range of problems solvable using these techniques.", "source": "arxiv/ml"}
{"id": "arxiv:1478", "title": "Learning to Predict the Wisdom of Crowds", "text": "The problem of \"approximating the crowd\" is that of estimating the crowd's majority opinion by querying only a subset of it. Algorithms that approximate the crowd can intelligently stretch a limited budget for a crowdsourcing task. We present an algorithm, \"CrowdSense,\" that works in an online fashion to dynamically sample subsets of labelers based on an exploration/exploitation criterion. The algorithm produces a weighted combination of a subset of the labelers' votes that approximates the crowd's opinion.", "source": "arxiv/ml"}
{"id": "arxiv:1479", "title": "Convolutional Neural Networks Applied to House Numbers Digit Classification", "text": "We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.", "source": "arxiv/ml"}
{"id": "arxiv:1480", "title": "EigenGP: Sparse Gaussian process models with data-dependent eigenfunctions", "text": "Gaussian processes (GPs) provide a nonparametric representation of functions. However, classical GP inference suffers from high computational cost and it is difficult to design nonstationary GP priors in practice. In this paper, we propose a sparse Gaussian process model, EigenGP, based on the Karhunen-Loeve (KL) expansion of a GP prior. We use the Nystrom approximation to obtain data dependent eigenfunctions and select these eigenfunctions by evidence maximization. This selection reduces the number of eigenfunctions in our model and provides a nonstationary covariance function. To handle nonlinear likelihoods, we develop an efficient expectation propagation (EP) inference algorithm, and couple it with expectation maximization for eigenfunction selection. Because the eigenfunctions of a Gaussian kernel are associated with clusters of samples - including both the labeled and unlabeled - selecting relevant eigenfunctions enables EigenGP to conduct semi-supervised learning. Our experimental results demonstrate improved predictive performance of EigenGP over alternative state-of-the-art sparse GP and semisupervised learning methods for regression, classification, and semisupervised classification.", "source": "arxiv/ml"}
{"id": "arxiv:1481", "title": "Learning From An Optimization Viewpoint", "text": "In this dissertation we study statistical and online learning problems from an optimization viewpoint.The dissertation is divided into two parts : I. We first consider the question of learnability for statistical learning problems in the general learning setting. The question of learnability is well studied and fully characterized for binary classification and for real valued supervised learning problems using the theory of uniform convergence. However we show that for the general learning setting uniform convergence theory fails to characterize learnability. To fill this void we use stability of learning algorithms to fully characterize statistical learnability in the general setting. Next we consider the problem of online learning. Unlike the statistical learning framework there is a dearth of generic tools that can be used to establish learnability and rates for online learning problems in general. We provide online analogs to classical tools from statistical learning theory like Rademacher complexity, covering numbers, etc. We further use these tools to fully characterize learnability for online supervised learning problems. II. In the second part, for general classes of convex learning problems, we provide appropriate mirror descent (MD) updates for online and statistical learning of these problems. Further, we show that the the MD is near optimal for online convex learning and for most cases, is also near optimal for statistical convex learning. We next consider the problem of convex optimization and show that oracle complexity can be lower bounded by the so called fat-shattering dimension of the associated linear class. Thus we establish a strong connection between offline convex optimization problems and statistical learning problems. We also show that for a large class of high dimensional optimization problems, MD is in fact near optimal even for convex optimization.", "source": "arxiv/ml"}
{"id": "arxiv:1482", "title": "Message passing with relaxed moment matching", "text": "Bayesian learning is often hampered by large computational expense. As a powerful generalization of popular belief propagation, expectation propagation (EP) efficiently approximates the exact Bayesian computation. Nevertheless, EP can be sensitive to outliers and suffer from divergence for difficult cases. To address this issue, we propose a new approximate inference approach, relaxed expectation propagation (REP). It relaxes the moment matching requirement of expectation propagation by adding a relaxation factor into the KL minimization. We penalize this relaxation with a $l_1$ penalty. As a result, when two distributions in the relaxed KL divergence are similar, the relaxation factor will be penalized to zero and, therefore, we obtain the original moment matching; In the presence of outliers, these two distributions are significantly different and the relaxation factor will be used to reduce the contribution of the outlier. Based on this penalized KL minimization, REP is robust to outliers and can greatly improve the posterior approximation quality over EP. To examine the effectiveness of REP, we apply it to Gaussian process classification, a task known to be suitable to EP. Our classification results on synthetic and UCI benchmark datasets demonstrate significant improvement of REP over EP and Power EP--in terms of algorithmic stability, estimation accuracy and predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:1483", "title": "Discrete Dynamical Genetic Programming in XCS", "text": "A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to neural networks. This paper presents results from an investigation into using a discrete dynamical system representation within the XCS Learning Classifier System. In particular, asynchronous random Boolean networks are used to represent the traditional condition-action production system rules. It is shown possible to use self-adaptive, open-ended evolution to design an ensemble of such discrete dynamical systems within XCS to solve a number of well-known test problems.", "source": "arxiv/ml"}
{"id": "arxiv:1484", "title": "Fuzzy Dynamical Genetic Programming in XCSF", "text": "A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to Neural Networks, and more recently Dynamical Genetic Programming (DGP). This paper presents results from an investigation into using a fuzzy DGP representation within the XCSF Learning Classifier System. In particular, asynchronous Fuzzy Logic Networks are used to represent the traditional condition-action production system rules. It is shown possible to use self-adaptive, open-ended evolution to design an ensemble of such fuzzy dynamical systems within XCSF to solve several well-known continuous-valued test problems.", "source": "arxiv/ml"}
{"id": "arxiv:1485", "title": "Learning in Riemannian Orbifolds", "text": "Learning in Riemannian orbifolds is motivated by existing machine learning algorithms that directly operate on finite combinatorial structures such as point patterns, trees, and graphs. These methods, however, lack statistical justification. This contribution derives consistency results for learning problems in structured domains and thereby generalizes learning in vector spaces and manifolds.", "source": "arxiv/ml"}
{"id": "arxiv:1486", "title": "Supervised feature evaluation by consistency analysis: application to measure sets used to characterise geographic objects", "text": "Nowadays, supervised learning is commonly used in many domains. Indeed, many works propose to learn new knowledge from examples that translate the expected behaviour of the considered system. A key issue of supervised learning concerns the description language used to represent the examples. In this paper, we propose a method to evaluate the feature set used to describe them. Our method is based on the computation of the consistency of the example base. We carried out a case study in the domain of geomatic in order to evaluate the sets of measures used to characterise geographic objects. The case study shows that our method allows to give relevant evaluations of measure sets.", "source": "arxiv/ml"}
{"id": "arxiv:1487", "title": "Designing generalisation evaluation function through human-machine dialogue", "text": "Automated generalisation has known important improvements these last few years. However, an issue that still deserves more study concerns the automatic evaluation of generalised data. Indeed, many automated generalisation systems require the utilisation of an evaluation function to automatically assess generalisation outcomes. In this paper, we propose a new approach dedicated to the design of such a function. This approach allows an imperfectly defined evaluation function to be revised through a man-machine dialogue. The user gives its preferences to the system by comparing generalisation outcomes. Machine Learning techniques are then used to improve the evaluation function. An experiment carried out on buildings shows that our approach significantly improves generalisation evaluation functions defined by users.", "source": "arxiv/ml"}
{"id": "arxiv:1488", "title": "A Privacy-Aware Bayesian Approach for Combining Classifier and Cluster Ensembles", "text": "This paper introduces a privacy-aware Bayesian approach that combines ensembles of classifiers and clusterers to perform semi-supervised and transductive learning. We consider scenarios where instances and their classification/clustering results are distributed across different data sites and have sharing restrictions. As a special case, the privacy aware computation of the model when instances of the target data are distributed across different data sites, is also discussed. Experimental results show that the proposed approach can provide good classification accuracies while adhering to the data/model sharing constraints.", "source": "arxiv/ml"}
{"id": "arxiv:1489", "title": "Supervised Feature Selection in Graphs with Path Coding Penalties and Network Flows", "text": "We consider supervised learning problems where the features are embedded in a graph, such as gene expressions in a gene network. In this context, it is of much interest to automatically select a subgraph with few connected components; by exploiting prior knowledge, one can indeed improve the prediction performance or obtain results that are easier to interpret. Regularization or penalty functions for selecting features in graphs have recently been proposed, but they raise new algorithmic challenges. For example, they typically require solving a combinatorially hard selection problem among all connected subgraphs. In this paper, we propose computationally feasible strategies to select a sparse and well-connected subset of features sitting on a directed acyclic graph (DAG). We introduce structured sparsity penalties over paths on a DAG called \"path coding\" penalties. Unlike existing regularization functions that model long-range interactions between features in a graph, path coding penalties are tractable. The penalties and their proximal operators involve path selection problems, which we efficiently solve by leveraging network flow optimization. We experimentally show on synthetic, image, and genomic data that our approach is scalable and leads to more connected subgraphs than other regularization functions for graphs.", "source": "arxiv/ml"}
{"id": "arxiv:1490", "title": "Regret in Online Combinatorial Optimization", "text": "We address online linear optimization problems when the possible actions of the decision maker are represented by binary vectors. The regret of the decision maker is the difference between her realized loss and the best loss she would have achieved by picking, in hindsight, the best possible action. Our goal is to understand the magnitude of the best possible (minimax) regret. We study the problem under three different assumptions for the feedback the decision maker receives: full information, and the partial information models of the so-called \"semi-bandit\" and \"bandit\" problems. Combining the Mirror Descent algorithm and the INF (Implicitely Normalized Forecaster) strategy, we are able to prove optimal bounds for the semi-bandit case. We also recover the optimal bounds for the full information setting. In the bandit case we discuss existing results in light of a new lower bound, and suggest a conjecture on the optimal regret in that case. Finally we also prove that the standard exponentially weighted average forecaster is provably suboptimal in the setting of online combinatorial optimization.", "source": "arxiv/ml"}
{"id": "arxiv:1491", "title": "Energy-Efficient Building HVAC Control Using Hybrid System LBMPC", "text": "Improving the energy-efficiency of heating, ventilation, and air-conditioning (HVAC) systems has the potential to realize large economic and societal benefits. This paper concerns the system identification of a hybrid system model of a building-wide HVAC system and its subsequent control using a hybrid system formulation of learning-based model predictive control (LBMPC). Here, the learning refers to model updates to the hybrid system model that incorporate the heating effects due to occupancy, solar effects, outside air temperature (OAT), and equipment, in addition to integrator dynamics inherently present in low-level control. Though we make significant modeling simplifications, our corresponding controller that uses this model is able to experimentally achieve a large reduction in energy usage without any degradations in occupant comfort. It is in this way that we justify the modeling simplifications that we have made. We conclude by presenting results from experiments on our building HVAC testbed, which show an average of 1.5MWh of energy savings per day (p = 0.002) with a 95% confidence interval of 1.0MWh to 2.1MWh of energy savings.", "source": "arxiv/ml"}
{"id": "arxiv:1492", "title": "Objective Function Designing Led by User Preferences Acquisition", "text": "Many real world problems can be defined as optimisation problems in which the aim is to maximise an objective function. The quality of obtained solution is directly linked to the pertinence of the used objective function. However, designing such function, which has to translate the user needs, is usually fastidious. In this paper, a method to help user objective functions designing is proposed. Our approach, which is highly interactive, is based on man machine dialogue and more particularly on the comparison of problem instance solutions by the user. We propose an experiment in the domain of cartographic generalisation that shows promising results.", "source": "arxiv/ml"}
{"id": "arxiv:1493", "title": "Knowledge revision in systems based on an informed tree search strategy : application to cartographic generalisation", "text": "Many real world problems can be expressed as optimisation problems. Solving this kind of problems means to find, among all possible solutions, the one that maximises an evaluation function. One approach to solve this kind of problem is to use an informed search strategy. The principle of this kind of strategy is to use problem-specific knowledge beyond the definition of the problem itself to find solutions more efficiently than with an uninformed strategy. This kind of strategy demands to define problem-specific knowledge (heuristics). The efficiency and the effectiveness of systems based on it directly depend on the used knowledge quality. Unfortunately, acquiring and maintaining such knowledge can be fastidious. The objective of the work presented in this paper is to propose an automatic knowledge revision approach for systems based on an informed tree search strategy. Our approach consists in analysing the system execution logs and revising knowledge based on these logs by modelling the revision problem as a knowledge space exploration problem. We present an experiment we carried out in an application domain where informed search strategies are often used: cartographic generalisation.", "source": "arxiv/ml"}
{"id": "arxiv:1494", "title": "Sparse Prediction with the $k$-Support Norm", "text": "We derive a novel norm that corresponds to the tightest convex relaxation of sparsity combined with an $\\ell_2$ penalty. We show that this new {\\em $k$-support norm} provides a tighter relaxation than the elastic net and is thus a good replacement for the Lasso or the elastic net in sparse prediction problems. Through the study of the $k$-support norm, we also bound the looseness of the elastic net, thus shedding new light on it and providing justification for its use.", "source": "arxiv/ml"}
{"id": "arxiv:1495", "title": "Analysis Operator Learning and Its Application to Image Reconstruction", "text": "Exploiting a priori known structural information lies at the core of many image reconstruction methods that can be stated as inverse problems. The synthesis model, which assumes that images can be decomposed into a linear combination of very few atoms of some dictionary, is now a well established tool for the design of image reconstruction algorithms. An interesting alternative is the analysis model, where the signal is multiplied by an analysis operator and the outcome is assumed to be the sparse. This approach has only recently gained increasing interest. The quality of reconstruction methods based on an analysis model severely depends on the right choice of the suitable operator. In this work, we present an algorithm for learning an analysis operator from training images. Our method is based on an $\\ell_p$-norm minimization on the set of full rank matrices with normalized columns. We carefully introduce the employed conjugate gradient method on manifolds, and explain the underlying geometry of the constraints. Moreover, we compare our approach to state-of-the-art methods for image denoising, inpainting, and single image super-resolution. Our numerical results show competitive performance of our general approach in all presented applications compared to the specialized state-of-the-art techniques.", "source": "arxiv/ml"}
{"id": "arxiv:1496", "title": "Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems", "text": "Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of bandit problems dates back to the Thirties, exploration-exploitation trade-offs arise in several modern applications, such as ad placement, website optimization, and packet routing. Mathematically, a multi-armed bandit is defined by the payoff process associated with each option. In this survey, we focus on two extreme cases in which the analysis of regret is particularly simple and elegant: i.i.d. payoffs and adversarial payoffs. Besides the basic setting of finitely many actions, we also analyze some of the most important variants and extensions, such as the contextual bandit model.", "source": "arxiv/ml"}
{"id": "arxiv:1497", "title": "Quantitative Concept Analysis", "text": "Formal Concept Analysis (FCA) begins from a context, given as a binary relation between some objects and some attributes, and derives a lattice of concepts, where each concept is given as a set of objects and a set of attributes, such that the first set consists of all objects that satisfy all attributes in the second, and vice versa. Many applications, though, provide contexts with quantitative information, telling not just whether an object satisfies an attribute, but also quantifying this satisfaction. Contexts in this form arise as rating matrices in recommender systems, as occurrence matrices in text analysis, as pixel intensity matrices in digital image processing, etc. Such applications have attracted a lot of attention, and several numeric extensions of FCA have been proposed. We propose the framework of proximity sets (proxets), which subsume partially ordered sets (posets) as well as metric spaces. One feature of this approach is that it extracts from quantified contexts quantified concepts, and thus allows full use of the available information. Another feature is that the categorical approach allows analyzing any universal properties that the classical FCA and the new versions may have, and thus provides structural guidance for aligning and combining the approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1498", "title": "Geometry of Online Packing Linear Programs", "text": "We consider packing LP's with $m$ rows where all constraint coefficients are normalized to be in the unit interval. The n columns arrive in random order and the goal is to set the corresponding decision variables irrevocably when they arrive so as to obtain a feasible solution maximizing the expected reward. Previous (1 - \\epsilon)-competitive algorithms require the right-hand side of the LP to be Omega((m/\\epsilon^2) log (n/\\epsilon)), a bound that worsens with the number of columns and rows. However, the dependence on the number of columns is not required in the single-row case and known lower bounds for the general case are also independent of n. Our goal is to understand whether the dependence on n is required in the multi-row case, making it fundamentally harder than the single-row version. We refute this by exhibiting an algorithm which is (1 - \\epsilon)-competitive as long as the right-hand sides are Omega((m^2/\\epsilon^2) log (m/\\epsilon)). Our techniques refine previous PAC-learning based approaches which interpret the online decisions as linear classifications of the columns based on sampled dual prices. The key ingredient of our improvement comes from a non-standard covering argument together with the realization that only when the columns of the LP belong to few 1-d subspaces we can obtain small such covers; bounding the size of the cover constructed also relies on the geometry of linear classifiers. General packing LP's are handled by perturbing the input columns, which can be seen as making the learning problem more robust.", "source": "arxiv/ml"}
{"id": "arxiv:1499", "title": "Distributed GraphLab: A Framework for Machine Learning in the Cloud", "text": "While high-level data parallel frameworks, like MapReduce, simplify the design and implementation of large-scale data processing systems, they do not naturally or efficiently support many important data mining and machine learning algorithms and can lead to inefficient learning systems. To help fill this critical void, we introduced the GraphLab abstraction which naturally expresses asynchronous, dynamic, graph-parallel computation while ensuring data consistency and achieving a high degree of parallel performance in the shared-memory setting. In this paper, we extend the GraphLab framework to the substantially more challenging distributed setting while preserving strong data consistency guarantees. We develop graph based extensions to pipelined locking and data versioning to reduce network congestion and mitigate the effect of network latency. We also introduce fault tolerance to the GraphLab abstraction using the classic Chandy-Lamport snapshot algorithm and demonstrate how it can be easily implemented by exploiting the GraphLab abstraction itself. Finally, we evaluate our distributed implementation of the GraphLab abstraction on a large Amazon EC2 deployment and show 1-2 orders of magnitude performance gains over Hadoop-based implementations.", "source": "arxiv/ml"}
{"id": "arxiv:1500", "title": "Feature Selection for Generator Excitation Neurocontroller Development Using Filter Technique", "text": "Essentially, motive behind using control system is to generate suitable control signal for yielding desired response of a physical process. Control of synchronous generator has always remained very critical in power system operation and control. For certain well known reasons power generators are normally operated well below their steady state stability limit. This raises demand for efficient and fast controllers. Artificial intelligence has been reported to give revolutionary outcomes in the field of control engineering. Artificial Neural Network (ANN), a branch of artificial intelligence has been used for nonlinear and adaptive control, utilizing its inherent observability. The overall performance of neurocontroller is dependent upon input features too. Selecting optimum features to train a neurocontroller optimally is very critical. Both quality and size of data are of equal importance for better performance. In this work filter technique is employed to select independent factors for ANN training.", "source": "arxiv/ml"}
{"id": "arxiv:1501", "title": "CELL: Connecting Everyday Life in an archipeLago", "text": "We explore the design of a seamless broadcast communication system that brings together the distributed community of remote secondary education schools. In contrast to higher education, primary and secondary education establishments should remain distributed, in order to maintain a balance of urban and rural life in the developing and the developed world. We plan to deploy an ambient and social interactive TV platform (physical installation, authoring tools, interactive content) that supports social communication in a positive way. In particular, we present the physical design and the conceptual model of the system.", "source": "arxiv/ml"}
{"id": "arxiv:1502", "title": "Dissimilarity Clustering by Hierarchical Multi-Level Refinement", "text": "We introduce in this paper a new way of optimizing the natural extension of the quantization error using in k-means clustering to dissimilarity data. The proposed method is based on hierarchical clustering analysis combined with multi-level heuristic refinement. The method is computationally efficient and achieves better quantization errors than the", "source": "arxiv/ml"}
{"id": "arxiv:1503", "title": "A Conjugate Property between Loss Functions and Uncertainty Sets in Classification Problems", "text": "In binary classification problems, mainly two approaches have been proposed; one is loss function approach and the other is uncertainty set approach. The loss function approach is applied to major learning algorithms such as support vector machine (SVM) and boosting methods. The loss function represents the penalty of the decision function on the training samples. In the learning algorithm, the empirical mean of the loss function is minimized to obtain the classifier. Against a backdrop of the development of mathematical programming, nowadays learning algorithms based on loss functions are widely applied to real-world data analysis. In addition, statistical properties of such learning algorithms are well-understood based on a lots of theoretical works. On the other hand, the learning method using the so-called uncertainty set is used in hard-margin SVM, mini-max probability machine (MPM) and maximum margin MPM. In the learning algorithm, firstly, the uncertainty set is defined for each binary label based on the training samples. Then, the best separating hyperplane between the two uncertainty sets is employed as the decision function. This is regarded as an extension of the maximum-margin approach. The uncertainty set approach has been studied as an application of robust optimization in the field of mathematical programming. The statistical properties of learning algorithms with uncertainty sets have not been intensively studied. In this paper, we consider the relation between the above two approaches. We point out that the uncertainty set is described by using the level set of the conjugate of the loss function. Based on such relation, we study statistical properties of learning algorithms using uncertainty sets.", "source": "arxiv/ml"}
{"id": "arxiv:1504", "title": "Residual Belief Propagation for Topic Modeling", "text": "Fast convergence speed is a desired property for training latent Dirichlet allocation (LDA), especially in online and parallel topic modeling for massive data sets. This paper presents a novel residual belief propagation (RBP) algorithm to accelerate the convergence speed for training LDA. The proposed RBP uses an informed scheduling scheme for asynchronous message passing, which passes fast-convergent messages with a higher priority to influence those slow-convergent messages at each learning iteration. Extensive empirical studies confirm that RBP significantly reduces the training time until convergence while achieves a much lower predictive perplexity than other state-of-the-art training algorithms for LDA, including variational Bayes (VB), collapsed Gibbs sampling (GS), loopy belief propagation (BP), and residual VB (RVB).", "source": "arxiv/ml"}
{"id": "arxiv:1505", "title": "A Spectral Algorithm for Latent Dirichlet Allocation", "text": "The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the words in each document are generated as a mixture of several active topics, as opposed to just one). This increased representational power comes at the cost of a more challenging unsupervised learning problem of estimating the topic probability vectors (the distributions over words for each topic), when only the words are observed and the corresponding topics are hidden. We provide a simple and efficient learning procedure that is guaranteed to recover the parameters for a wide class of mixture models, including the popular latent Dirichlet allocation (LDA) model. For LDA, the procedure correctly recovers both the topic probability vectors and the prior over the topics, using only trigram statistics (i.e., third order moments, which may be estimated with documents containing just three words). The method, termed Excess Correlation Analysis (ECA), is based on a spectral decomposition of low order moments (third and fourth order) via two singular value decompositions (SVDs). Moreover, the algorithm is scalable since the SVD operations are carried out on $k\\times k$ matrices, where $k$ is the number of latent factors (e.g. the number of topics), rather than in the $d$-dimensional observed space (typically $d \\gg k$).", "source": "arxiv/ml"}
{"id": "arxiv:1506", "title": "A Singly-Exponential Time Algorithm for Computing Nonnegative Rank", "text": "Here, we give an algorithm for deciding if the nonnegative rank of a matrix $M$ of dimension $m \\times n$ is at most $r$ which runs in time $(nm)^{O(r^2)}$. This is the first exact algorithm that runs in time singly-exponential in $r$. This algorithm (and earlier algorithms) are built on methods for finding a solution to a system of polynomial inequalities (if one exists). Notably, the best algorithms for this task run in time exponential in the number of variables but polynomial in all of the other parameters (the number of inequalities and the maximum degree). Hence these algorithms motivate natural algebraic questions whose solution have immediate {\\em algorithmic} implications: How many variables do we need to represent the decision problem, does $M$ have nonnegative rank at most $r$? A naive formulation uses $nr + mr$ variables and yields an algorithm that is exponential in $n$ and $m$ even for constant $r$. (Arora, Ge, Kannan, Moitra, STOC 2012) recently reduced the number of variables to $2r^2 2^r$, and here we exponentially reduce the number of variables to $2r^2$ and this yields our main algorithm. In fact, the algorithm that we obtain is nearly-optimal (under the Exponential Time Hypothesis) since an algorithm that runs in time $(nm)^{o(r)}$ would yield a subexponential algorithm for 3-SAT . Our main result is based on establishing a normal form for nonnegative matrix factorization - which in turn allows us to exploit algebraic dependence among a large collection of linear transformations with variable entries. Additionally, we also demonstrate that nonnegative rank cannot be certified by even a very large submatrix of $M$, and this property also follows from the intuition gained from viewing nonnegative rank through the lens of systems of polynomial inequalities.", "source": "arxiv/ml"}
{"id": "arxiv:1507", "title": "$QD$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations", "text": "The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of a remote controller. The paper investigates a distributed reinforcement learning setup with no prior information on the global state transition and local agent cost statistics. Specifically, with the agents' objective consisting of minimizing a network-averaged infinite horizon discounted cost, the paper proposes a distributed version of $Q$-learning, $\\mathcal{QD}$-learning, in which the network agents collaborate by means of local processing and mutual information exchange over a sparse (possibly stochastic) communication network to achieve the network goal. Under the assumption that each agent is only aware of its local online cost data and the inter-agent communication network is \\emph{weakly} connected, the proposed distributed scheme is almost surely (a.s.) shown to yield asymptotically the desired value function and the optimal stationary control policy at each network agent. The analytical techniques developed in the paper to address the mixed time-scale stochastic dynamics of the \\emph{consensus + innovations} form, which arise as a result of the proposed interactive distributed scheme, are of independent interest.", "source": "arxiv/ml"}
{"id": "arxiv:1508", "title": "Complexity Analysis of the Lasso Regularization Path", "text": "The regularization path of the Lasso can be shown to be piecewise linear, making it possible to \"follow\" and explicitly compute the entire path. We analyze in this paper this popular strategy, and prove that its worst case complexity is exponential in the number of variables. We then oppose this pessimistic result to an (optimistic) approximate analysis: We show that an approximate path with at most O(1/sqrt(epsilon)) linear segments can always be obtained, where every point on the path is guaranteed to be optimal up to a relative epsilon-duality gap. We complete our theoretical analysis with a practical algorithm to compute these approximate paths.", "source": "arxiv/ml"}
{"id": "arxiv:1509", "title": "ProPPA: A Fast Algorithm for $\\ell_1$ Minimization and Low-Rank Matrix Completion", "text": "We propose a Projected Proximal Point Algorithm (ProPPA) for solving a class of optimization problems. The algorithm iteratively computes the proximal point of the last estimated solution projected into an affine space which itself is parallel and approaching to the feasible set. We provide convergence analysis theoretically supporting the general algorithm, and then apply it for solving $\\ell_1$-minimization problems and the matrix completion problem. These problems arise in many applications including machine learning, image and signal processing. We compare our algorithm with the existing state-of-the-art algorithms. Experimental results on solving these problems show that our algorithm is very efficient and competitive.", "source": "arxiv/ml"}
{"id": "arxiv:1510", "title": "A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning", "text": "We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kernels $d$ to be combined is very large, multiple kernel learning methods whose computational cost scales linearly in $d$ are intractable. We propose a randomized version of the mirror descent algorithm to overcome this issue, under the objective of minimizing the group $p$-norm penalized empirical risk. The key to achieve the required exponential speed-up is the computationally efficient construction of low-variance estimates of the gradient. We propose importance sampling based estimates, and find that the ideal distribution samples a coordinate with a probability proportional to the magnitude of the corresponding gradient. We show the surprising result that in the case of learning the coefficients of a polynomial kernel, the combinatorial structure of the base kernels to be combined allows the implementation of sampling from this distribution to run in $O(\\log(d))$ time, making the total computational cost of the method to achieve an $\\epsilon$-optimal solution to be $O(\\log(d)/\\epsilon^2)$, thereby allowing our method to operate for very large values of $d$. Experiments with simulated and real data confirm that the new algorithm is computationally more efficient than its state-of-the-art alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:1511", "title": "Minimax Classifier for Uncertain Costs", "text": "Many studies on the cost-sensitive learning assumed that a unique cost matrix is known for a problem. However, this assumption may not hold for many real-world problems. For example, a classifier might need to be applied in several circumstances, each of which associates with a different cost matrix. Or, different human experts have different opinions about the costs for a given problem. Motivated by these facts, this study aims to seek the minimax classifier over multiple cost matrices. In summary, we theoretically proved that, no matter how many cost matrices are involved, the minimax problem can be tackled by solving a number of standard cost-sensitive problems and sub-problems that involve only two cost matrices. As a result, a general framework for achieving minimax classifier over multiple cost matrices is suggested and justified by preliminary empirical studies.", "source": "arxiv/ml"}
{"id": "arxiv:1512", "title": "Hypothesis testing using pairwise distances and associated kernels (with Appendix)", "text": "We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning. The equivalence holds when energy distances are computed with semimetrics of negative type, in which case a kernel may be defined such that the RKHS distance between distributions corresponds exactly to the energy distance. We determine the class of probability distributions for which kernels induced by semimetrics are characteristic (that is, for which embeddings of the distributions to an RKHS are injective). Finally, we investigate the performance of this family of kernels in two-sample and independence tests: we show in particular that the energy distance most commonly employed in statistics is just one member of a parametric family of kernels, and that other choices from this family can yield more powerful tests.", "source": "arxiv/ml"}
{"id": "arxiv:1513", "title": "Greedy Multiple Instance Learning via Codebook Learning and Nearest Neighbor Voting", "text": "Multiple instance learning (MIL) has attracted great attention recently in machine learning community. However, most MIL algorithms are very slow and cannot be applied to large datasets. In this paper, we propose a greedy strategy to speed up the multiple instance learning process. Our contribution is two fold. First, we propose a density ratio model, and show that maximizing a density ratio function is the low bound of the DD model under certain conditions. Secondly, we make use of a histogram ratio between positive bags and negative bags to represent the density ratio function and find codebooks separately for positive bags and negative bags by a greedy strategy. For testing, we make use of a nearest neighbor strategy to classify new bags. We test our method on both small benchmark datasets and the large TRECVID MED11 dataset. The experimental results show that our method yields comparable accuracy to the current state of the art, while being up to at least one order of magnitude faster.", "source": "arxiv/ml"}
{"id": "arxiv:1514", "title": "Generative Maximum Entropy Learning for Multiclass Classification", "text": "Maximum entropy approach to classification is very well studied in applied statistics and machine learning and almost all the methods that exists in literature are discriminative in nature. In this paper, we introduce a maximum entropy classification method with feature selection for large dimensional data such as text datasets that is generative in nature. To tackle the curse of dimensionality of large data sets, we employ conditional independence assumption (Naive Bayes) and we perform feature selection simultaneously, by enforcing a `maximum discrimination' between estimated class conditional densities. For two class problems, in the proposed method, we use Jeffreys ($J$) divergence to discriminate the class conditional densities. To extend our method to the multi-class case, we propose a completely new approach by considering a multi-distribution divergence: we replace Jeffreys divergence by Jensen-Shannon ($JS$) divergence to discriminate conditional densities of multiple classes. In order to reduce computational complexity, we employ a modified Jensen-Shannon divergence ($JS_{GM}$), based on AM-GM inequality. We show that the resulting divergence is a natural generalization of Jeffreys divergence to a multiple distributions case. As far as the theoretical justifications are concerned we show that when one intends to select the best features in a generative maximum entropy approach, maximum discrimination using $J-$divergence emerges naturally in binary classification. Performance and comparative study of the proposed algorithms have been demonstrated on large dimensional text and gene expression datasets that show our methods scale up very well with large dimensional datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1515", "title": "Weighted Patterns as a Tool for Improving the Hopfield Model", "text": "We generalize the standard Hopfield model to the case when a weight is assigned to each input pattern. The weight can be interpreted as the frequency of the pattern occurrence at the input of the network. In the framework of the statistical physics approach we obtain the saddle-point equation allowing us to examine the memory of the network. In the case of unequal weights our model does not lead to the catastrophic destruction of the memory due to its overfilling (that is typical for the standard Hopfield model). The real memory consists only of the patterns with weights exceeding a critical value that is determined by the weights distribution. We obtain the algorithm allowing us to find this critical value for an arbitrary distribution of the weights, and analyze in detail some particular weights distributions. It is shown that the memory decreases as compared to the case of the standard Hopfield model. However, in our model the network can learn online without the catastrophic destruction of the memory.", "source": "arxiv/ml"}
{"id": "arxiv:1516", "title": "Variable Selection for Latent Dirichlet Allocation", "text": "In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discriminative. We compare three models, vsLDA, LDA with symmetric priors, and LDA with asymmetric priors, on heldout likelihood, MCMC chain consistency, and document classification. The performance of vsLDA is better than symmetric LDA for likelihood and classification, better than asymmetric LDA for consistency and classification, and about the same in the other comparisons.", "source": "arxiv/ml"}
{"id": "arxiv:1517", "title": "On the Complexity of Trial and Error", "text": "Motivated by certain applications from physics, biochemistry, economics, and computer science, in which the objects under investigation are not accessible because of various limitations, we propose a trial-and-error model to examine algorithmic issues in such situations. Given a search problem with a hidden input, we are asked to find a valid solution, to find which we can propose candidate solutions (trials), and use observed violations (errors), to prepare future proposals. In accordance with our motivating applications, we consider the fairly broad class of constraint satisfaction problems, and assume that errors are signaled by a verification oracle in the format of the index of a violated constraint (with the content of the constraint still hidden). Our discoveries are summarized as follows. On one hand, despite the seemingly very little information provided by the verification oracle, efficient algorithms do exist for a number of important problems. For the Nash, Core, Stable Matching, and SAT problems, the unknown-input versions are as hard as the corresponding known-input versions, up to a factor of polynomial. We further give almost tight bounds on the latter two problems' trial complexities. On the other hand, there are problems whose complexities are substantially increased in the unknown-input model. In particular, no time-efficient algorithms exist (under standard hardness assumptions) for Graph Isomorphism and Group Isomorphism problems. The tools used to achieve these results include order theory, strong ellipsoid method, and some non-standard reductions. Our model investigates the value of information, and our results demonstrate that the lack of input information can introduce various levels of extra difficulty. The model exhibits intimate connections with (and we hope can also serve as a useful supplement to) certain existing learning and complexity theories.", "source": "arxiv/ml"}
{"id": "arxiv:1518", "title": "Convex Relaxation for Combinatorial Penalties", "text": "In this paper, we propose an unifying view of several recently proposed structured sparsity-inducing norms. We consider the situation of a model simultaneously (a) penalized by a set- function de ned on the support of the unknown parameter vector which represents prior knowledge on supports, and (b) regularized in Lp-norm. We show that the natural combinatorial optimization problems obtained may be relaxed into convex optimization problems and introduce a notion, the lower combinatorial envelope of a set-function, that characterizes the tightness of our relaxations. We moreover establish links with norms based on latent representations including the latent group Lasso and block-coding, and with norms obtained from submodular functions.", "source": "arxiv/ml"}
{"id": "arxiv:1519", "title": "Sparse group lasso and high dimensional multinomial classification", "text": "The sparse group lasso optimization problem is solved using a coordinate gradient descent algorithm. The algorithm is applicable to a broad class of convex loss functions. Convergence of the algorithm is established, and the algorithm is used to investigate the performance of the multinomial sparse group lasso classifier. On three different real data examples the multinomial group lasso clearly outperforms multinomial lasso in terms of achieved classification error rate and in terms of including fewer features for the classification. The run-time of our sparse group lasso implementation is of the same order of magnitude as the multinomial lasso algorithm implemented in the R package glmnet. Our implementation scales well with the problem size. One of the high dimensional examples considered is a 50 class classification problem with 10k features, which amounts to estimating 500k parameters. The implementation is available as the R package msgl.", "source": "arxiv/ml"}
{"id": "arxiv:1520", "title": "Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Noninvasive Fetal ECG via Block Sparse Bayesian Learning", "text": "Fetal ECG (FECG) telemonitoring is an important branch in telemedicine. The design of a telemonitoring system via a wireless body-area network with low energy consumption for ambulatory use is highly desirable. As an emerging technique, compressed sensing (CS) shows great promise in compressing/reconstructing data with low energy consumption. However, due to some specific characteristics of raw FECG recordings such as non-sparsity and strong noise contamination, current CS algorithms generally fail in this application. This work proposes to use the block sparse Bayesian learning (BSBL) framework to compress/reconstruct non-sparse raw FECG recordings. Experimental results show that the framework can reconstruct the raw recordings with high quality. Especially, the reconstruction does not destroy the interdependence relation among the multichannel recordings. This ensures that the independent component analysis decomposition of the reconstructed recordings has high fidelity. Furthermore, the framework allows the use of a sparse binary sensing matrix with much fewer nonzero entries to compress recordings. Particularly, each column of the matrix can contain only two nonzero entries. This shows the framework, compared to other algorithms such as current CS algorithms and wavelet algorithms, can greatly reduce code execution in CPU in the data compression stage.", "source": "arxiv/ml"}
{"id": "arxiv:1521", "title": "Detecting Spammers via Aggregated Historical Data Set", "text": "The battle between email service providers and senders of mass unsolicited emails (Spam) continues to gain traction. Vast numbers of Spam emails are sent mainly from automatic botnets distributed over the world. One method for mitigating Spam in a computationally efficient manner is fast and accurate blacklisting of the senders. In this work we propose a new sender reputation mechanism that is based on an aggregated historical data-set which encodes the behavior of mail transfer agents over time. A historical data-set is created from labeled logs of received emails. We use machine learning algorithms to build a model that predicts the \\emph{spammingness} of mail transfer agents in the near future. The proposed mechanism is targeted mainly at large enterprises and email service providers and can be used for updating both the black and the white lists. We evaluate the proposed mechanism using 9.5M anonymized log entries obtained from the biggest Internet service provider in Europe. Experiments show that proposed method detects more than 94% of the Spam emails that escaped the blacklist (i.e., TPR), while having less than 0.5% false-alarms. Therefore, the effectiveness of the proposed method is much higher than of previously reported reputation mechanisms, which rely on emails logs. In addition, the proposed method, when used for updating both the black and white lists, eliminated the need in automatic content inspection of 4 out of 5 incoming emails, which resulted in dramatic reduction in the filtering computational load.", "source": "arxiv/ml"}
{"id": "arxiv:1522", "title": "Dynamic Multi-Relational Chinese Restaurant Process for Analyzing Influences on Users in Social Media", "text": "We study the problem of analyzing influence of various factors affecting individual messages posted in social media. The problem is challenging because of various types of influences propagating through the social media network that act simultaneously on any user. Additionally, the topic composition of the influencing factors and the susceptibility of users to these influences evolve over time. This problem has not studied before, and off-the-shelf models are unsuitable for this purpose. To capture the complex interplay of these various factors, we propose a new non-parametric model called the Dynamic Multi-Relational Chinese Restaurant Process. This accounts for the user network for data generation and also allows the parameters to evolve over time. Designing inference algorithms for this model suited for large scale social-media data is another challenge. To this end, we propose a scalable and multi-threaded inference algorithm based on online Gibbs Sampling. Extensive evaluations on large-scale Twitter and Facebook data show that the extracted topics when applied to authorship and commenting prediction outperform state-of-the-art baselines. More importantly, our model produces valuable insights on topic trends and user personality trends, beyond the capability of existing approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1523", "title": "Risk estimation for matrix recovery with spectral regularization", "text": "In this paper, we develop an approach to recursively estimate the quadratic risk for matrix recovery problems regularized with spectral functions. Toward this end, in the spirit of the SURE theory, a key step is to compute the (weak) derivative and divergence of a solution with respect to the observations. As such a solution is not available in closed form, but rather through a proximal splitting algorithm, we propose to recursively compute the divergence from the sequence of iterates. A second challenge that we unlocked is the computation of the (weak) derivative of the proximity operator of a spectral function. To show the potential applicability of our approach, we exemplify it on a matrix completion problem to objectively and automatically select the regularization parameter.", "source": "arxiv/ml"}
{"id": "arxiv:1524", "title": "Graph-based Learning with Unbalanced Clusters", "text": "Graph construction is a crucial step in spectral clustering (SC) and graph-based semi-supervised learning (SSL). Spectral methods applied on standard graphs such as full-RBF, $\\epsilon$-graphs and $k$-NN graphs can lead to poor performance in the presence of proximal and unbalanced data. This is because spectral methods based on minimizing RatioCut or normalized cut on these graphs tend to put more importance on balancing cluster sizes over reducing cut values. We propose a novel graph construction technique and show that the RatioCut solution on this new graph is able to handle proximal and unbalanced data. Our method is based on adaptively modulating the neighborhood degrees in a $k$-NN graph, which tends to sparsify neighborhoods in low density regions. Our method adapts to data with varying levels of unbalancedness and can be naturally used for small cluster detection. We justify our ideas through limit cut analysis. Unsupervised and semi-supervised experiments on synthetic and real data sets demonstrate the superiority of our method.", "source": "arxiv/ml"}
{"id": "arxiv:1525", "title": "Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds", "text": "Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of dimensionality by minimizing a pessimistic bound on the policy loss. This approach turns ADP into an optimization problem, for which we derive new mathematical program formulations and analyze its properties. DRADP improves on the theoretical guarantees of existing ADP methods-it guarantees convergence and L1 norm based error bounds. The empirical evaluation of DRADP shows that the theoretical guarantees translate well into good performance on benchmark problems.", "source": "arxiv/ml"}
{"id": "arxiv:1526", "title": "The Natural Gradient by Analogy to Signal Whitening, and Recipes and Tricks for its Use", "text": "The natural gradient allows for more efficient gradient descent by removing dependencies and biases inherent in a function's parameterization. Several papers present the topic thoroughly and precisely. It remains a very difficult idea to get your head around however. The intent of this note is to provide simple intuition for the natural gradient and its use. We review how an ill conditioned parameter space can undermine learning, introduce the natural gradient by analogy to the more widely understood concept of signal whitening, and present tricks and specific prescriptions for applying the natural gradient to learning problems.", "source": "arxiv/ml"}
{"id": "arxiv:1527", "title": "Hamiltonian Annealed Importance Sampling for partition function estimation", "text": "We introduce an extension to annealed importance sampling that uses Hamiltonian dynamics to rapidly estimate normalization constants. We demonstrate this method by computing log likelihoods in directed and undirected probabilistic image models. We compare the performance of linear generative models with both Gaussian and Laplace priors, product of experts models with Laplace and Student's t experts, the mc-RBM, and a bilinear generative model. We provide code to compare additional models.", "source": "arxiv/ml"}
{"id": "arxiv:1528", "title": "The representer theorem for Hilbert spaces: a necessary and sufficient condition", "text": "A family of regularization functionals is said to admit a linear representer theorem if every member of the family admits minimizers that lie in a fixed finite dimensional subspace. A recent characterization states that a general class of regularization functionals with differentiable regularizer admits a linear representer theorem if and only if the regularization term is a non-decreasing function of the norm. In this report, we improve over such result by replacing the differentiability assumption with lower semi-continuity and deriving a proof that is independent of the dimensionality of the space.", "source": "arxiv/ml"}
{"id": "arxiv:1529", "title": "Hamiltonian Monte Carlo with Reduced Momentum Flips", "text": "Hamiltonian Monte Carlo (or hybrid Monte Carlo) with partial momentum refreshment explores the state space more slowly than it otherwise would due to the momentum reversals which occur on proposal rejection. These cause trajectories to double back on themselves, leading to random walk behavior on timescales longer than the typical rejection time, and leading to slower mixing. I present a technique by which the number of momentum reversals can be reduced. This is accomplished by maintaining the net exchange of probability between states with opposite momenta, but reducing the rate of exchange in both directions such that it is 0 in one direction. An experiment illustrates these reduced momentum flips accelerating mixing for a particular distribution.", "source": "arxiv/ml"}
{"id": "arxiv:1530", "title": "Dynamic Behavioral Mixed-Membership Model for Large Evolving Networks", "text": "The majority of real-world networks are dynamic and extremely large (e.g., Internet Traffic, Twitter, Facebook, ...). To understand the structural behavior of nodes in these large dynamic networks, it may be necessary to model the dynamics of behavioral roles representing the main connectivity patterns over time. In this paper, we propose a dynamic behavioral mixed-membership model (DBMM) that captures the roles of nodes in the graph and how they evolve over time. Unlike other node-centric models, our model is scalable for analyzing large dynamic networks. In addition, DBMM is flexible, parameter-free, has no functional form or parameterization, and is interpretable (identifies explainable patterns). The performance results indicate our approach can be applied to very large networks while the experimental results show that our model uncovers interesting patterns underlying the dynamics of these networks.", "source": "arxiv/ml"}
{"id": "arxiv:1531", "title": "A Converged Algorithm for Tikhonov Regularized Nonnegative Matrix Factorization with Automatic Regularization Parameters Determination", "text": "We present a converged algorithm for Tikhonov regularized nonnegative matrix factorization (NMF). We specially choose this regularization because it is known that Tikhonov regularized least square (LS) is the more preferable form in solving linear inverse problems than the conventional LS. Because an NMF problem can be decomposed into LS subproblems, it can be expected that Tikhonov regularized NMF will be the more appropriate approach in solving NMF problems. The algorithm is derived using additive update rules which have been shown to have convergence guarantee. We equip the algorithm with a mechanism to automatically determine the regularization parameters based on the L-curve, a well-known concept in the inverse problems community, but is rather unknown in the NMF research. The introduction of this algorithm thus solves two inherent problems in Tikhonov regularized NMF algorithm research, i.e., convergence guarantee and regularization parameters determination.", "source": "arxiv/ml"}
{"id": "arxiv:1532", "title": "A Generalized Kernel Approach to Structured Output Learning", "text": "We study the problem of structured output learning from a regression perspective. We first provide a general formulation of the kernel dependency estimation (KDE) problem using operator-valued kernels. We show that some of the existing formulations of this problem are special cases of our framework. We then propose a covariance-based operator-valued kernel that allows us to take into account the structure of the kernel feature space. This kernel operates on the output space and encodes the interactions between the outputs without any reference to the input space. To address this issue, we introduce a variant of our KDE method based on the conditional covariance operator that in addition to the correlation between the outputs takes into account the effects of the input variables. Finally, we evaluate the performance of our KDE approach using both covariance and conditional covariance kernels on two structured output problems, and compare it to the state-of-the-art kernel-based structured output regression methods.", "source": "arxiv/ml"}
{"id": "arxiv:1533", "title": "Modularity-Based Clustering for Network-Constrained Trajectories", "text": "We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental study shows the superiority of the proposed approach over classic hierarchical clustering and gives a brief insight to visualization of the clustering results.", "source": "arxiv/ml"}
{"id": "arxiv:1534", "title": "Efficient Constrained Regret Minimization", "text": "Online learning constitutes a mathematical and compelling framework to analyze sequential decision making problems in adversarial environments. The learner repeatedly chooses an action, the environment responds with an outcome, and then the learner receives a reward for the played action. The goal of the learner is to maximize his total reward. However, there are situations in which, in addition to maximizing the cumulative reward, there are some additional constraints on the sequence of decisions that must be satisfied on average by the learner. In this paper we study an extension to the online learning where the learner aims to maximize the total reward given that some additional constraints need to be satisfied. By leveraging on the theory of Lagrangian method in constrained optimization, we propose Lagrangian exponentially weighted average (LEWA) algorithm, which is a primal-dual variant of the well known exponentially weighted average algorithm, to efficiently solve constrained online decision making problems. Using novel theoretical analysis, we establish the regret and the violation of the constraint bounds in full information and bandit feedback models.", "source": "arxiv/ml"}
{"id": "arxiv:1535", "title": "A Discussion on Parallelization Schemes for Stochastic Vector Quantization Algorithms", "text": "This paper studies parallelization schemes for stochastic Vector Quantization algorithms in order to obtain time speed-ups using distributed resources. We show that the most intuitive parallelization scheme does not lead to better performances than the sequential algorithm. Another distributed scheme is therefore introduced which obtains the expected speed-ups. Then, it is improved to fit implementation on distributed architectures where communications are slow and inter-machines synchronization too costly. The schemes are tested with simulated distributed architectures and, for the last one, with Microsoft Windows Azure platform obtaining speed-ups up to 32 Virtual Machines.", "source": "arxiv/ml"}
{"id": "arxiv:1536", "title": "Sparse Approximation via Penalty Decomposition Methods", "text": "In this paper we consider sparse approximation problems, that is, general $l_0$ minimization problems with the $l_0$-\"norm\" of a vector being a part of constraints or objective function. In particular, we first study the first-order optimality conditions for these problems. We then propose penalty decomposition (PD) methods for solving them in which a sequence of penalty subproblems are solved by a block coordinate descent (BCD) method. Under some suitable assumptions, we establish that any accumulation point of the sequence generated by the PD methods satisfies the first-order optimality conditions of the problems. Furthermore, for the problems in which the $l_0$ part is the only nonconvex part, we show that such an accumulation point is a local minimizer of the problems. In addition, we show that any accumulation point of the sequence generated by the BCD method is a saddle point of the penalty subproblem. Moreover, for the problems in which the $l_0$ part is the only nonconvex part, we establish that such an accumulation point is a local minimizer of the penalty subproblem. Finally, we test the performance of our PD methods by applying them to sparse logistic regression, sparse inverse covariance selection, and compressed sensing problems. The computational results demonstrate that our methods generally outperform the existing methods in terms of solution quality and/or speed.", "source": "arxiv/ml"}
{"id": "arxiv:1537", "title": "Low Complexity Damped Gauss-Newton Algorithms for CANDECOMP/PARAFAC", "text": "The damped Gauss-Newton (dGN) algorithm for CANDECOMP/PARAFAC (CP) decomposition can handle the challenges of collinearity of factors and different magnitudes of factors; nevertheless, for factorization of an $N$-D tensor of size $I_1\\times I_N$ with rank $R$, the algorithm is computationally demanding due to construction of large approximate Hessian of size $(RT \\times RT)$ and its inversion where $T = \\sum_n I_n$. In this paper, we propose a fast implementation of the dGN algorithm which is based on novel expressions of the inverse approximate Hessian in block form. The new implementation has lower computational complexity, besides computation of the gradient (this part is common to both methods), requiring the inversion of a matrix of size $NR^2\\times NR^2$, which is much smaller than the whole approximate Hessian, if $T \\gg NR$. In addition, the implementation has lower memory requirements, because neither the Hessian nor its inverse never need to be stored in their entirety. A variant of the algorithm working with complex valued data is proposed as well. Complexity and performance of the proposed algorithm is compared with those of dGN and ALS with line search on examples of difficult benchmark tensors.", "source": "arxiv/ml"}
{"id": "arxiv:1538", "title": "On the Identifiability of the Post-Nonlinear Causal Model", "text": "By taking into account the nonlinear effect of the cause, the inner noise effect, and the measurement distortion effect in the observed variables, the post-nonlinear (PNL) causal model has demonstrated its excellent performance in distinguishing the cause from effect. However, its identifiability has not been properly addressed, and how to apply it in the case of more than two variables is also a problem. In this paper, we conduct a systematic investigation on its identifiability in the two-variable case. We show that this model is identifiable in most cases; by enumerating all possible situations in which the model is not identifiable, we provide sufficient conditions for its identifiability. Simulations are given to support the theoretical results. Moreover, in the case of more than two variables, we show that the whole causal structure can be found by applying the PNL causal model to each structure in the Markov equivalent class and testing if the disturbance is independent of the direct causes for each variable. In this way the exhaustive search over all possible causal structures is avoided.", "source": "arxiv/ml"}
{"id": "arxiv:1539", "title": "A Uniqueness Theorem for Clustering", "text": "Despite the widespread use of Clustering, there is distressingly little general theory of clustering available. Questions like \"What distinguishes a clustering of data from other data partitioning?\", \"Are there any principles governing all clustering paradigms?\", \"How should a user choose an appropriate clustering algorithm for a particular task?\", etc. are almost completely unanswered by the existing body of clustering literature. We consider an axiomatic approach to the theory of Clustering. We adopt the framework of Kleinberg, [Kle03]. By relaxing one of Kleinberg's clustering axioms, we sidestep his impossibility result and arrive at a consistent set of axioms. We suggest to extend these axioms, aiming to provide an axiomatic taxonomy of clustering paradigms. Such a taxonomy should provide users some guidance concerning the choice of the appropriate clustering paradigm for a given task. The main result of this paper is a set of abstract properties that characterize the Single-Linkage clustering function. This characterization result provides new insight into the properties of desired data groupings that make Single-Linkage the appropriate choice. We conclude by considering a taxonomy of clustering functions based on abstract properties that each satisfies.", "source": "arxiv/ml"}
{"id": "arxiv:1540", "title": "The Entire Quantile Path of a Risk-Agnostic SVM Classifier", "text": "A quantile binary classifier uses the rule: Classify x as +1 if P(Y = 1|X = x) >= t, and as -1 otherwise, for a fixed quantile parameter t {[0, 1]. It has been shown that Support Vector Machines (SVMs) in the limit are quantile classifiers with t = 1/2 . In this paper, we show that by using asymmetric cost of misclassification SVMs can be appropriately extended to recover, in the limit, the quantile binary classifier for any t. We then present a principled algorithm to solve the extended SVM classifier for all values of t simultaneously. This has two implications: First, one can recover the entire conditional distribution P(Y = 1|X = x) = t for t {[0, 1]. Second, we can build a risk-agnostic SVM classifier where the cost of misclassification need not be known apriori. Preliminary numerical experiments show the effectiveness of the proposed algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1541", "title": "The Infinite Latent Events Model", "text": "We present the Infinite Latent Events Model, a nonparametric hierarchical Bayesian distribution over infinite dimensional Dynamic Bayesian Networks with binary state representations and noisy-OR-like transitions. The distribution can be used to learn structure in discrete timeseries data by simultaneously inferring a set of latent events, which events fired at each timestep, and how those events are causally linked. We illustrate the model on a sound factorization task, a network topology identification task, and a video game task.", "source": "arxiv/ml"}
{"id": "arxiv:1542", "title": "Herding Dynamic Weights for Partially Observed Random Field Models", "text": "Learning the parameters of a (potentially partially observable) random field model is intractable in general. Instead of focussing on a single optimal parameter value we propose to treat parameters as dynamical quantities. We introduce an algorithm to generate complex dynamics for parameters and (both visible and hidden) state vectors. We show that under certain conditions averages computed over trajectories of the proposed dynamical system converge to averages computed over the data. Our \"herding dynamics\" does not require expensive operations such as exponentiation and is fully deterministic.", "source": "arxiv/ml"}
{"id": "arxiv:1543", "title": "Exploring compact reinforcement-learning representations with linear regression", "text": "This paper presents a new algorithm for online linear regression whose efficiency guarantees satisfy the requirements of the KWIK (Knows What It Knows) framework. The algorithm improves on the complexity bounds of the current state-of-the-art procedure in this setting. We explore several applications of this algorithm for learning compact reinforcement-learning representations. We show that KWIK linear regression can be used to learn the reward function of a factored MDP and the probabilities of action outcomes in Stochastic STRIPS and Object Oriented MDPs, none of which have been proven to be efficiently learnable in the RL setting before. We also combine KWIK linear regression with other KWIK learners to learn larger portions of these models, including experiments on learning factored MDP transition and reward functions together.", "source": "arxiv/ml"}
{"id": "arxiv:1544", "title": "Temporal-Difference Networks for Dynamical Systems with Continuous Observations and Actions", "text": "Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm for learning TD network representations of dynamical systems with continuous observations and actions. Our results show that the algorithm is capable of learning accurate and robust models of several noisy continuous dynamical systems. The algorithm presented here is the first fully incremental method for learning a predictive representation of a continuous dynamical system.", "source": "arxiv/ml"}
{"id": "arxiv:1545", "title": "Which Spatial Partition Trees are Adaptive to Intrinsic Dimension?", "text": "Recent theory work has found that a special type of spatial partition tree - called a random projection tree - is adaptive to the intrinsic dimension of the data from which it is built. Here we examine this same question, with a combination of theory and experiments, for a broader class of trees that includes k-d trees, dyadic trees, and PCA trees. Our motivation is to get a feel for (i) the kind of intrinsic low dimensional structure that can be empirically verified, (ii) the extent to which a spatial partition can exploit such structure, and (iii) the implications for standard statistical tasks such as regression, vector quantization, and nearest neighbor search.", "source": "arxiv/ml"}
{"id": "arxiv:1546", "title": "Probabilistic Structured Predictors", "text": "We consider MAP estimators for structured prediction with exponential family models. In particular, we concentrate on the case that efficient algorithms for uniform sampling from the output space exist. We show that under this assumption (i) exact computation of the partition function remains a hard problem, and (ii) the partition function and the gradient of the log partition function can be approximated efficiently. Our main result is an approximation scheme for the partition function based on Markov Chain Monte Carlo theory. We also show that the efficient uniform sampling assumption holds in several application settings that are of importance in machine learning.", "source": "arxiv/ml"}
{"id": "arxiv:1547", "title": "Ordinal Boltzmann Machines for Collaborative Filtering", "text": "Collaborative filtering is an effective recommendation technique wherein the preference of an individual can potentially be predicted based on preferences of other members. Early algorithms often relied on the strong locality in the preference data, that is, it is enough to predict preference of a user on a particular item based on a small subset of other users with similar tastes or of other items with similar properties. More recently, dimensionality reduction techniques have proved to be equally competitive, and these are based on the co-occurrence patterns rather than locality. This paper explores and extends a probabilistic model known as Boltzmann Machine for collaborative filtering tasks. It seamlessly integrates both the similarity and co-occurrence in a principled manner. In particular, we study parameterisation options to deal with the ordinal nature of the preferences, and propose a joint modelling of both the user-based and item-based processes. Experiments on moderate and large-scale movie recommendation show that our framework rivals existing well-known methods.", "source": "arxiv/ml"}
{"id": "arxiv:1548", "title": "Computing Posterior Probabilities of Structural Features in Bayesian Networks", "text": "We study the problem of learning Bayesian network structures from data. Koivisto and Sood (2004) and Koivisto (2006) presented algorithms that can compute the exact marginal posterior probability of a subnetwork, e.g., a single edge, in O(n2n) time and the posterior probabilities for all n(n-1) potential edges in O(n2n) total time, assuming that the number of parents per node or the indegree is bounded by a constant. One main drawback of their algorithms is the requirement of a special structure prior that is non uniform and does not respect Markov equivalence. In this paper, we develop an algorithm that can compute the exact posterior probability of a subnetwork in O(3n) time and the posterior probabilities for all n(n-1) potential edges in O(n3n) total time. Our algorithm also assumes a bounded indegree but allows general structure priors. We demonstrate the applicability of the algorithm on several data sets with up to 20 variables.", "source": "arxiv/ml"}
{"id": "arxiv:1549", "title": "Products of Hidden Markov Models: It Takes N>1 to Tango", "text": "Products of Hidden Markov Models(PoHMMs) are an interesting class of generative models which have received little attention since their introduction. This maybe in part due to their more computationally expensive gradient-based learning algorithm,and the intractability of computing the log likelihood of sequences under the model. In this paper, we demonstrate how the partition function can be estimated reliably via Annealed Importance Sampling. We perform experiments using contrastive divergence learning on rainfall data and data captured from pairs of people dancing. Our results suggest that advances in learning and evaluation for undirected graphical models and recent increases in available computing power make PoHMMs worth considering for complex time-series modeling tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1550", "title": "Modeling Discrete Interventional Data using Directed Cyclic Graphical Models", "text": "We outline a representation for discrete multivariate distributions in terms of interventional potential functions that are globally normalized. This representation can be used to model the effects of interventions, and the independence properties encoded in this model can be represented as a directed graph that allows cycles. In addition to discussing inference and sampling with this representation, we give an exponential family parametrization that allows parameter estimation to be stated as a convex optimization problem; we also give a convex relaxation of the task of simultaneous parameter and structure learning using group l1-regularization. The model is evaluated on simulated data and intracellular flow cytometry data.", "source": "arxiv/ml"}
{"id": "arxiv:1551", "title": "BPR: Bayesian Personalized Ranking from Implicit Feedback", "text": "Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorization (MF) or adaptive knearest-neighbor (kNN). Even though these methods are designed for the item prediction task of personalized ranking, none of them is directly optimized for ranking. In this paper we present a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem. We also provide a generic learning algorithm for optimizing models with respect to BPR-Opt. The learning method is based on stochastic gradient descent with bootstrap sampling. We show how to apply our method to two state-of-the-art recommender models: matrix factorization and adaptive kNN. Our experiments indicate that for the task of personalized ranking our optimization method outperforms the standard learning techniques for MF and kNN. The results show the importance of optimizing models for the right criterion.", "source": "arxiv/ml"}
{"id": "arxiv:1552", "title": "Using the Gene Ontology Hierarchy when Predicting Gene Function", "text": "The problem of multilabel classification when the labels are related through a hierarchical categorization scheme occurs in many application domains such as computational biology. For example, this problem arises naturally when trying to automatically assign gene function using a controlled vocabularies like Gene Ontology. However, most existing approaches for predicting gene functions solve independent classification problems to predict genes that are involved in a given function category, independently of the rest. Here, we propose two simple methods for incorporating information about the hierarchical nature of the categorization scheme. In the first method, we use information about a gene's previous annotation to set an initial prior on its label. In a second approach, we extend a graph-based semi-supervised learning algorithm for predicting gene function in a hierarchy. We show that we can efficiently solve this problem by solving a linear system of equations. We compare these approaches with a previous label reconciliation-based approach. Results show that using the hierarchy information directly, compared to using reconciliation methods, improves gene function prediction.", "source": "arxiv/ml"}
{"id": "arxiv:1553", "title": "Virtual Vector Machine for Bayesian Online Classification", "text": "In a typical online learning scenario, a learner is required to process a large data stream using a small memory buffer. Such a requirement is usually in conflict with a learner's primary pursuit of prediction accuracy. To address this dilemma, we introduce a novel Bayesian online classi cation algorithm, called the Virtual Vector Machine. The virtual vector machine allows you to smoothly trade-off prediction accuracy with memory size. The virtual vector machine summarizes the information contained in the preceding data stream by a Gaussian distribution over the classi cation weights plus a constant number of virtual data points. The virtual data points are designed to add extra non-Gaussian information about the classi cation weights. To maintain the constant number of virtual points, the virtual vector machine adds the current real data point into the virtual point set, merges two most similar virtual points into a new virtual point or deletes a virtual point that is far from the decision boundary. The information lost in this process is absorbed into the Gaussian distribution. The extra information provided by the virtual points leads to improved predictive accuracy over previous online classification algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1554", "title": "Convexifying the Bethe Free Energy", "text": "The introduction of loopy belief propagation (LBP) revitalized the application of graphical models in many domains. Many recent works present improvements on the basic LBP algorithm in an attempt to overcome convergence and local optima problems. Notable among these are convexified free energy approximations that lead to inference procedures with provable convergence and quality properties. However, empirically LBP still outperforms most of its convex variants in a variety of settings, as we also demonstrate here. Motivated by this fact we seek convexified free energies that directly approximate the Bethe free energy. We show that the proposed approximations compare favorably with state-of-the art convex free energy approximations.", "source": "arxiv/ml"}
{"id": "arxiv:1555", "title": "Convergent message passing algorithms - a unifying view", "text": "Message-passing algorithms have emerged as powerful techniques for approximate inference in graphical models. When these algorithms converge, they can be shown to find local (or sometimes even global) optima of variational formulations to the inference problem. But many of the most popular algorithms are not guaranteed to converge. This has lead to recent interest in convergent message-passing algorithms. In this paper, we present a unified view of convergent message-passing algorithms. We present a simple derivation of an abstract algorithm, tree-consistency bound optimization (TCBO) that is provably convergent in both its sum and max product forms. We then show that many of the existing convergent algorithms are instances of our TCBO algorithm, and obtain novel convergent algorithms \"for free\" by exchanging maximizations and summations in existing algorithms. In particular, we show that Wainwright's non-convergent sum-product algorithm for tree based variational bounds, is actually convergent with the right update order for the case where trees are monotonic chains.", "source": "arxiv/ml"}
{"id": "arxiv:1556", "title": "Group Sparse Priors for Covariance Estimation", "text": "Recently it has become popular to learn sparse Gaussian graphical models (GGMs) by imposing l1 or group l1,2 penalties on the elements of the precision matrix. Thispenalized likelihood approach results in a tractable convex optimization problem. In this paper, we reinterpret these results as performing MAP estimation under a novel prior which we call the group l1 and l1,2 positivedefinite matrix distributions. This enables us to build a hierarchical model in which the l1 regularization terms vary depending on which group the entries are assigned to, which in turn allows us to learn block structured sparse GGMs with unknown group assignments. Exact inference in this hierarchical model is intractable, due to the need to compute the normalization constant of these matrix distributions. However, we derive upper bounds on the partition functions, which lets us use fast variational inference (optimizing a lower bound on the joint posterior). We show that on two real world data sets (motion capture and financial data), our method which infers the block structure outperforms a method that uses a fixed block structure, which in turn outperforms baseline methods that ignore block structure.", "source": "arxiv/ml"}
{"id": "arxiv:1557", "title": "Domain Knowledge Uncertainty and Probabilistic Parameter Constraints", "text": "Incorporating domain knowledge into the modeling process is an effective way to improve learning accuracy. However, as it is provided by humans, domain knowledge can only be specified with some degree of uncertainty. We propose to explicitly model such uncertainty through probabilistic constraints over the parameter space. In contrast to hard parameter constraints, our approach is effective also when the domain knowledge is inaccurate and generally results in superior modeling accuracy. We focus on generative and conditional modeling where the parameters are assigned a Dirichlet or Gaussian prior and demonstrate the framework with experiments on both synthetic and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:1558", "title": "Multiple Source Adaptation and the Renyi Divergence", "text": "This paper presents a novel theoretical study of the general problem of multiple source adaptation using the notion of Renyi divergence. Our results build on our previous work [12], but significantly broaden the scope of that work in several directions. We extend previous multiple source loss guarantees based on distribution weighted combinations to arbitrary target distributions P, not necessarily mixtures of the source distributions, analyze both known and unknown target distribution cases, and prove a lower bound. We further extend our bounds to deal with the case where the learner receives an approximate distribution for each source instead of the exact one, and show that similar loss guarantees can be achieved depending on the divergence between the approximate and true distributions. We also analyze the case where the labeling functions of the source domains are somewhat different. Finally, we report the results of experiments with both an artificial data set and a sentiment analysis task, showing the performance benefits of the distribution weighted combinations and the quality of our bounds based on the Renyi divergence.", "source": "arxiv/ml"}
{"id": "arxiv:1559", "title": "Interpretation and Generalization of Score Matching", "text": "Score matching is a recently developed parameter learning method that is particularly effective to complicated high dimensional density models with intractable partition functions. In this paper, we study two issues that have not been completely resolved for score matching. First, we provide a formal link between maximum likelihood and score matching. Our analysis shows that score matching finds model parameters that are more robust with noisy training data. Second, we develop a generalization of score matching. Based on this generalization, we further demonstrate an extension of score matching to models of discrete data.", "source": "arxiv/ml"}
{"id": "arxiv:1560", "title": "Multi-Task Feature Learning Via Efficient l2,1-Norm Minimization", "text": "The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2,1-norm regularized regression model for joint feature selection from multiple tasks, which can be derived in the probabilistic framework by assuming a suitable prior from the exponential family. One appealing feature of the l2,1-norm regularization is that it encourages multiple predictors to share similar sparsity patterns. However, the resulting optimization problem is challenging to solve due to the non-smoothness of the l2,1-norm regularization. In this paper, we propose to accelerate the computation by reformulating it as two equivalent smooth convex optimization problems which are then solved via the Nesterov's method-an optimal first-order black-box method for smooth convex optimization. A key building block in solving the reformulations is the Euclidean projection. We show that the Euclidean projection for the first reformulation can be analytically computed, while the Euclidean projection for the second one can be computed in linear time. Empirical evaluations on several data sets verify the efficiency of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1561", "title": "Improving Compressed Counting", "text": "Compressed Counting (CC) [22] was recently proposed for estimating the ath frequency moments of data streams, where 0 < a <= 2. CC can be used for estimating Shannon entropy, which can be approximated by certain functions of the ath frequency moments as a -> 1. Monitoring Shannon entropy for anomaly detection (e.g., DDoS attacks) in large networks is an important task. This paper presents a new algorithm for improving CC. The improvement is most substantial when a -> 1--. For example, when a = 0:99, the new algorithm reduces the estimation variance roughly by 100-fold. This new algorithm would make CC considerably more practical for estimating Shannon entropy. Furthermore, the new algorithm is statistically optimal when a = 0.5.", "source": "arxiv/ml"}
{"id": "arxiv:1562", "title": "Identifying confounders using additive noise models", "text": "We propose a method for inferring the existence of a latent common cause ('confounder') of two observed random variables. The method assumes that the two effects of the confounder are (possibly nonlinear) functions of the confounder plus independent, additive noise. We discuss under which conditions the model is identifiable (up to an arbitrary reparameterization of the confounder) from the joint distribution of the effects. We state and prove a theoretical result that provides evidence for the conjecture that the model is generically identifiable under suitable technical conditions. In addition, we propose a practical method to estimate the confounder from a finite i.i.d. sample of the effects and illustrate that the method works well on both simulated and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:1563", "title": "Bayesian Discovery of Linear Acyclic Causal Models", "text": "Methods for automated discovery of causal relationships from non-interventional data have received much attention recently. A widely used and well understood model family is given by linear acyclic causal models (recursive structural equation models). For Gaussian data both constraint-based methods (Spirtes et al., 1993; Pearl, 2000) (which output a single equivalence class) and Bayesian score-based methods (Geiger and Heckerman, 1994) (which assign relative scores to the equivalence classes) are available. On the contrary, all current methods able to utilize non-Gaussianity in the data (Shimizu et al., 2006; Hoyer et al., 2008) always return only a single graph or a single equivalence class, and so are fundamentally unable to express the degree of certainty attached to that output. In this paper we develop a Bayesian score-based approach able to take advantage of non-Gaussianity when estimating linear acyclic causal models, and we empirically demonstrate that, at least on very modest size networks, its accuracy is as good as or better than existing methods. We provide a complete code package (in R) which implements all algorithms and performs all of the analysis provided in the paper, and hope that this will further the application of these methods to solving causal inference problems.", "source": "arxiv/ml"}
{"id": "arxiv:1564", "title": "New inference strategies for solving Markov Decision Processes using reversible jump MCMC", "text": "In this paper we build on previous work which uses inferences techniques, in particular Markov Chain Monte Carlo (MCMC) methods, to solve parameterized control problems. We propose a number of modifications in order to make this approach more practical in general, higher-dimensional spaces. We first introduce a new target distribution which is able to incorporate more reward information from sampled trajectories. We also show how to break strong correlations between the policy parameters and sampled trajectories in order to sample more freely. Finally, we show how to incorporate these techniques in a principled manner to obtain estimates of the optimal policy.", "source": "arxiv/ml"}
{"id": "arxiv:1565", "title": "Censored Exploration and the Dark Pool Problem", "text": "We introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove that our algorithm converges in polynomial time to a near-optimal allocation policy; prior results for similar problems in stochastic inventory control guaranteed only asymptotic convergence and examined variants in which each venue could be treated independently. Our analysis bears a strong resemblance to that of efficient exploration/ exploitation schemes in the reinforcement learning literature. We describe an extensive experimental evaluation of our algorithm on the Dark Pool Problem using real trading data.", "source": "arxiv/ml"}
{"id": "arxiv:1566", "title": "Learning Continuous-Time Social Network Dynamics", "text": "We demonstrate that a number of sociology models for social network dynamics can be viewed as continuous time Bayesian networks (CTBNs). A sampling-based approximate inference method for CTBNs can be used as the basis of an expectation-maximization procedure that achieves better accuracy in estimating the parameters of the model than the standard method of moments algorithmfromthe sociology literature. We extend the existing social network models to allow for indirect and asynchronous observations of the links. A Markov chain Monte Carlo sampling algorithm for this new model permits estimation and inference. We provide results on both a synthetic network (for verification) and real social network data.", "source": "arxiv/ml"}
{"id": "arxiv:1567", "title": "Correlated Non-Parametric Latent Feature Models", "text": "We are often interested in explaining data through a set of hidden factors or features. When the number of hidden features is unknown, the Indian Buffet Process (IBP) is a nonparametric latent feature model that does not bound the number of active features in dataset. However, the IBP assumes that all latent features are uncorrelated, making it inadequate for many realworld problems. We introduce a framework for correlated nonparametric feature models, generalising the IBP. We use this framework to generate several specific models and demonstrate applications on realworld datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1568", "title": "L2 Regularization for Learning Kernels", "text": "The choice of the kernel is critical to the success of many learning algorithms but it is typically left to the user. Instead, the training data can be used to learn the kernel by selecting it out of a given family, such as that of non-negative linear combinations of p base kernels, constrained by a trace or L1 regularization. This paper studies the problem of learning kernels with the same family of kernels but with an L2 regularization instead, and for regression problems. We analyze the problem of learning kernels with ridge regression. We derive the form of the solution of the optimization problem and give an efficient iterative algorithm for computing that solution. We present a novel theoretical analysis of the problem based on stability and give learning bounds for orthogonal kernels that contain only an additive term O(pp/m) when compared to the standard kernel ridge regression stability bound. We also report the results of experiments indicating that L1 regularization can lead to modest improvements for a small number of kernels, but to performance degradations in larger-scale cases. In contrast, L2 regularization never degrades performance and in fact achieves significant improvements with a large number of kernels.", "source": "arxiv/ml"}
{"id": "arxiv:1569", "title": "Convex Coding", "text": "Inspired by recent work on convex formulations of clustering (Lashkari & Golland, 2008; Nowozin & Bakir, 2008) we investigate a new formulation of the Sparse Coding Problem (Olshausen & Field, 1997). In sparse coding we attempt to simultaneously represent a sequence of data-vectors sparsely (i.e. sparse approximation (Tropp et al., 2006)) in terms of a 'code' defined by a set of basis elements, while also finding a code that enables such an approximation. As existing alternating optimization procedures for sparse coding are theoretically prone to severe local minima problems, we propose a convex relaxation of the sparse coding problem and derive a boosting-style algorithm, that (Nowozin & Bakir, 2008) serves as a convex 'master problem' which calls a (potentially non-convex) sub-problem to identify the next code element to add. Finally, we demonstrate the properties of our boosted coding algorithm on an image denoising task.", "source": "arxiv/ml"}
{"id": "arxiv:1570", "title": "Multilingual Topic Models for Unaligned Text", "text": "We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously discover both a matching between the languages and multilingual latent topics. We demonstrate that MuTo is able to find shared topics on real-world multilingual corpora, successfully pairing related documents across languages. MuTo provides a new framework for creating multilingual topic models without needing carefully curated parallel corpora and allows applications built using the topic model formalism to be applied to a much wider class of corpora.", "source": "arxiv/ml"}
{"id": "arxiv:1571", "title": "Optimization of Structured Mean Field Objectives", "text": "In intractable, undirected graphical models, an intuitive way of creating structured mean field approximations is to select an acyclic tractable subgraph. We show that the hardness of computing the objective function and gradient of the mean field objective qualitatively depends on a simple graph property. If the tractable subgraph has this property- we call such subgraphs v-acyclic-a very fast block coordinate ascent algorithm is possible. If not, optimization is harder, but we show a new algorithm based on the construction of an auxiliary exponential family that can be used to make inference possible in this case as well. We discuss the advantages and disadvantages of each regime and compare the algorithms empirically.", "source": "arxiv/ml"}
{"id": "arxiv:1572", "title": "Alternating Projections for Learning with Expectation Constraints", "text": "We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (Graca et al., 2008), maintains uncertainty during optimization unlike constraint-driven learning (Chang et al., 2007), and is more efficient than generalized expectation criteria (Mann & McCallum, 2008). Applications of this framework include minimally supervised learning, semisupervised learning, and learning with constraints that are more expressive than the underlying model. In experiments, we demonstrate comparable accuracy to generalized expectation criteria for minimally supervised learning, and use expressive structural constraints to guide semi-supervised learning, providing a 3%-6% improvement over stateof-the-art constraint-driven learning.", "source": "arxiv/ml"}
{"id": "arxiv:1573", "title": "REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs", "text": "We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the span of the optimal bias vector. For an MDP with S states and A actions whose optimal bias vector has span bounded by H, we show a regret bound of ~O(HSpAT). We also relate the span to various diameter-like quantities associated with the MDP, demonstrating how our results improve on previous regret bounds.", "source": "arxiv/ml"}
{"id": "arxiv:1574", "title": "On Smoothing and Inference for Topic Models", "text": "Latent Dirichlet analysis, or topic modeling, is a flexible latent variable framework for modeling high-dimensional sparse count data. Various learning algorithms have been developed in recent years, including collapsed Gibbs sampling, variational inference, and maximum a posteriori estimation, and this variety motivates the need for careful empirical comparisons. In this paper, we highlight the close connections between these approaches. We find that the main differences are attributable to the amount of smoothing applied to the counts. When the hyperparameters are optimized, the differences in performance among the algorithms diminish significantly. The ability of these algorithms to achieve solutions of comparable accuracy gives us the freedom to select computationally efficient approaches. Using the insights gained from this comparative study, we show how accurate topic models can be learned in several seconds on text corpora with thousands of documents.", "source": "arxiv/ml"}
{"id": "arxiv:1575", "title": "A Bayesian Sampling Approach to Exploration in Reinforcement Learning", "text": "We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and selecting actions optimistically. It extends previous work by providing a rule for deciding when to resample and how to combine the models. We show that our algorithm achieves nearoptimal reward with high probability with a sample complexity that is low relative to the speed at which the posterior distribution converges during learning. We demonstrate that BOSS performs quite favorably compared to state-of-the-art reinforcement-learning approaches and illustrate its flexibility by pairing it with a non-parametric model that generalizes across states.", "source": "arxiv/ml"}
{"id": "arxiv:1576", "title": "Decoupling Exploration and Exploitation in Multi-Armed Bandits", "text": "We consider a multi-armed bandit problem where the decision maker can explore and exploit different arms at every round. The exploited arm adds to the decision maker's cumulative reward (without necessarily observing the reward) while the explored arm reveals its value. We devise algorithms for this setup and show that the dependence on the number of arms, k, can be much better than the standard square root of k dependence, depending on the behavior of the arms' reward sequences. For the important case of piecewise stationary stochastic bandits, we show a significant improvement over existing algorithms. Our algorithms are based on a non-uniform sampling policy, which we show is essential to the success of any algorithm in the adversarial setup. Finally, we show some simulation results on an ultra-wide band channel selection inspired setting indicating the applicability of our algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1577", "title": "Density Sensitive Hashing", "text": "Nearest neighbors search is a fundamental problem in various research fields like machine learning, data mining and pattern recognition. Recently, hashing-based approaches, e.g., Locality Sensitive Hashing (LSH), are proved to be effective for scalable high dimensional nearest neighbors search. Many hashing algorithms found their theoretic root in random projection. Since these algorithms generate the hash tables (projections) randomly, a large number of hash tables (i.e., long codewords) are required in order to achieve both high precision and recall. To address this limitation, we propose a novel hashing algorithm called {\\em Density Sensitive Hashing} (DSH) in this paper. DSH can be regarded as an extension of LSH. By exploring the geometric structure of the data, DSH avoids the purely random projections selection and uses those projective functions which best agree with the distribution of the data. Extensive experimental results on real-world data sets have shown that the proposed method achieves better performance compared to the state-of-the-art hashing approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1578", "title": "b-Bit Minwise Hashing in Practice: Large-Scale Batch and Online Learning and Using GPUs for Fast Preprocessing with Simple Hash Functions", "text": "In this paper, we study several critical issues which must be tackled before one can apply b-bit minwise hashing to the volumes of data often used industrial applications, especially in the context of search. 1. (b-bit) Minwise hashing requires an expensive preprocessing step that computes k (e.g., 500) minimal values after applying the corresponding permutations for each data vector. We developed a parallelization scheme using GPUs and observed that the preprocessing time can be reduced by a factor of 20-80 and becomes substantially smaller than the data loading time. 2. One major advantage of b-bit minwise hashing is that it can substantially reduce the amount of memory required for batch learning. However, as online algorithms become increasingly popular for large-scale learning in the context of search, it is not clear if b-bit minwise yields significant improvements for them. This paper demonstrates that $b$-bit minwise hashing provides an effective data size/dimension reduction scheme and hence it can dramatically reduce the data loading time for each epoch of the online training process. This is significant because online learning often requires many (e.g., 10 to 100) epochs to reach a sufficient accuracy. 3. Another critical issue is that for very large data sets it becomes impossible to store a (fully) random permutation matrix, due to its space requirements. Our paper is the first study to demonstrate that $b$-bit minwise hashing implemented using simple hash functions, e.g., the 2-universal (2U) and 4-universal (4U) hash families, can produce very similar learning results as using fully random permutations. Experiments on datasets of up to 200GB are presented.", "source": "arxiv/ml"}
{"id": "arxiv:1579", "title": "Malware Detection Module using Machine Learning Algorithms to Assist in Centralized Security in Enterprise Networks", "text": "Malicious software is abundant in a world of innumerable computer users, who are constantly faced with these threats from various sources like the internet, local networks and portable drives. Malware is potentially low to high risk and can cause systems to function incorrectly, steal data and even crash. Malware may be executable or system library files in the form of viruses, worms, Trojans, all aimed at breaching the security of the system and compromising user privacy. Typically, anti-virus software is based on a signature definition system which keeps updating from the internet and thus keeping track of known viruses. While this may be sufficient for home-users, a security risk from a new virus could threaten an entire enterprise network. This paper proposes a new and more sophisticated antivirus engine that can not only scan files, but also build knowledge and detect files as potential viruses. This is done by extracting system API calls made by various normal and harmful executable, and using machine learning algorithms to classify and hence, rank files on a scale of security risk. While such a system is processor heavy, it is very effective when used centrally to protect an enterprise network which maybe more prone to such threats.", "source": "arxiv/ml"}
{"id": "arxiv:1580", "title": "Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search", "text": "Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal policies is notoriously taxing, since the search space becomes enormous. In this paper we introduce a tractable, sample-based method for approximate Bayes-optimal planning which exploits Monte-Carlo tree search. Our approach outperformed prior Bayesian model-based RL algorithms by a significant margin on several well-known benchmark problems -- because it avoids expensive applications of Bayes rule within the search tree by lazily sampling models from the current beliefs. We illustrate the advantages of our approach by showing it working in an infinite state space domain which is qualitatively out of reach of almost all previous work in Bayesian exploration.", "source": "arxiv/ml"}
{"id": "arxiv:1581", "title": "Unsupervised Discovery of Mid-Level Discriminative Patches", "text": "The goal of this paper is to discover a set of discriminative patches which can serve as a fully unsupervised mid-level visual representation. The desired patches need to satisfy two requirements: 1) to be representative, they need to occur frequently enough in the visual world; 2) to be discriminative, they need to be different enough from the rest of the visual world. The patches could correspond to parts, objects, \"visual phrases\", etc. but are not restricted to be any one of them. We pose this as an unsupervised discriminative clustering problem on a huge dataset of image patches. We use an iterative procedure which alternates between clustering and training discriminative classifiers, while applying careful cross-validation at each step to prevent overfitting. The paper experimentally demonstrates the effectiveness of discriminative patches as an unsupervised mid-level visual representation, suggesting that it could be used in place of visual words for many tasks. Furthermore, discriminative patches can also be used in a supervised regime, such as scene classification, where they demonstrate state-of-the-art performance on the MIT Indoor-67 dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1582", "title": "Multiple Identifications in Multi-Armed Bandits", "text": "We study the problem of identifying the top $m$ arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad arms, and successive accepts of the good ones. This algorithmic contribution allows to tackle other multiple identifications settings that were previously out of reach. In particular we show that this idea of successive accepts and rejects applies to the multi-bandit best arm identification problem.", "source": "arxiv/ml"}
{"id": "arxiv:1583", "title": "Genetic Programming for Multibiometrics", "text": "Biometric systems suffer from some drawbacks: a biometric system can provide in general good performances except with some individuals as its performance depends highly on the quality of the capture. One solution to solve some of these problems is to use multibiometrics where different biometric systems are combined together (multiple captures of the same biometric modality, multiple feature extraction algorithms, multiple biometric modalities...). In this paper, we are interested in score level fusion functions application (i.e., we use a multibiometric authentication scheme which accept or deny the claimant for using an application). In the state of the art, the weighted sum of scores (which is a linear classifier) and the use of an SVM (which is a non linear classifier) provided by different biometric systems provide one of the best performances. We present a new method based on the use of genetic programming giving similar or better performances (depending on the complexity of the database). We derive a score fusion function by assembling some classical primitives functions (+, *, -, ...). We have validated the proposed method on three significant biometric benchmark datasets from the state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:1584", "title": "Normalized Maximum Likelihood Coding for Exponential Family with Its Applications to Optimal Clustering", "text": "We are concerned with the issue of how to calculate the normalized maximum likelihood (NML) code-length. There is a problem that the normalization term of the NML code-length may diverge when it is continuous and unbounded and a straightforward computation of it is highly expensive when the data domain is finite . In previous works it has been investigated how to calculate the NML code-length for specific types of distributions. We first propose a general method for computing the NML code-length for the exponential family. Then we specifically focus on Gaussian mixture model (GMM), and propose a new efficient method for computing the NML to them. We develop it by generalizing Rissanen's re-normalizing technique. Then we apply this method to the clustering issue, in which a clustering structure is modeled using a GMM, and the main task is to estimate the optimal number of clusters on the basis of the NML code-length. We demonstrate using artificial data sets the superiority of the NML-based clustering over other criteria such as AIC, BIC in terms of the data size required for high accuracy rate to be achieved.", "source": "arxiv/ml"}
{"id": "arxiv:1585", "title": "Universal Algorithm for Online Trading Based on the Method of Calibration", "text": "We present a universal algorithm for online trading in Stock Market which performs asymptotically at least as good as any stationary trading strategy that computes the investment at each step using a fixed function of the side information that belongs to a given RKHS (Reproducing Kernel Hilbert Space). Using a universal kernel, we extend this result for any continuous stationary strategy. In this learning process, a trader rationally chooses his gambles using predictions made by a randomized well-calibrated algorithm. Our strategy is based on Dawid's notion of calibration with more general checking rules and on some modification of Kakade and Foster's randomized rounding algorithm for computing the well-calibrated forecasts. We combine the method of randomized calibration with Vovk's method of defensive forecasting in RKHS. Unlike the statistical theory, no stochastic assumptions are made about the stock prices. Our empirical results on historical markets provide strong evidence that this type of technical trading can \"beat the market\" if transaction costs are ignored.", "source": "arxiv/ml"}
{"id": "arxiv:1586", "title": "kLog: A Language for Logical and Relational Learning with Kernels", "text": "We introduce kLog, a novel approach to statistical relational learning. Unlike standard approaches, kLog does not represent a probability distribution directly. It is rather a language to perform kernel-based learning on expressive logical and relational representations. kLog allows users to specify learning problems declaratively. It builds on simple but powerful concepts: learning from interpretations, entity/relationship data modeling, logic programming, and deductive databases. Access by the kernel to the rich representation is mediated by a technique we call graphicalization: the relational representation is first transformed into a graph --- in particular, a grounded entity/relationship diagram. Subsequently, a choice of graph kernel defines the feature space. kLog supports mixed numerical and symbolic data, as well as background knowledge in the form of Prolog or Datalog programs as in inductive logic programming systems. The kLog framework can be applied to tackle the same range of tasks that has made statistical relational learning so popular, including classification, regression, multitask learning, and collective classification. We also report about empirical comparisons, showing that kLog can be either more accurate, or much faster at the same level of accuracy, than Tilde and Alchemy. kLog is GPLv3 licensed and is available at http://klog.dinfo.unifi.it along with tutorials.", "source": "arxiv/ml"}
{"id": "arxiv:1587", "title": "Constrained Overcomplete Analysis Operator Learning for Cosparse Signal Modelling", "text": "We consider the problem of learning a low-dimensional signal model from a collection of training samples. The mainstream approach would be to learn an overcomplete dictionary to provide good approximations of the training samples using sparse synthesis coefficients. This famous sparse model has a less well known counterpart, in analysis form, called the cosparse analysis model. In this new model, signals are characterised by their parsimony in a transformed domain using an overcomplete (linear) analysis operator. We propose to learn an analysis operator from a training corpus using a constrained optimisation framework based on L1 optimisation. The reason for introducing a constraint in the optimisation framework is to exclude trivial solutions. Although there is no final answer here for which constraint is the most relevant constraint, we investigate some conventional constraints in the model adaptation field and use the uniformly normalised tight frame (UNTF) for this purpose. We then derive a practical learning algorithm, based on projected subgradients and Douglas-Rachford splitting technique, and demonstrate its ability to robustly recover a ground truth analysis operator, when provided with a clean training set, of sufficient size. We also find an analysis operator for images, using some noisy cosparse signals, which is indeed a more realistic experiment. As the derived optimisation problem is not a convex program, we often find a local minimum using such variational methods. Some local optimality conditions are derived for two different settings, providing preliminary theoretical support for the well-posedness of the learning problem under appropriate conditions.", "source": "arxiv/ml"}
{"id": "arxiv:1588", "title": "Theory of Dependent Hierarchical Normalized Random Measures", "text": "This paper presents theory for Normalized Random Measures (NRMs), Normalized Generalized Gammas (NGGs), a particular kind of NRM, and Dependent Hierarchical NRMs which allow networks of dependent NRMs to be analysed. These have been used, for instance, for time-dependent topic modelling. In this paper, we first introduce some mathematical background of completely random measures (CRMs) and their construction from Poisson processes, and then introduce NRMs and NGGs. Slice sampling is also introduced for posterior inference. The dependency operators in Poisson processes and for the corresponding CRMs and NRMs is then introduced and Posterior inference for the NGG presented. Finally, we give dependency and composition results when applying these operators to NRMs so they can be used in a network with hierarchical and dependent relations.", "source": "arxiv/ml"}
{"id": "arxiv:1589", "title": "Online Structured Prediction via Coactive Learning", "text": "We propose Coactive Learning as a model of interaction between a learning system and a human user, where both have the common goal of providing results of maximum utility to the user. At each step, the system (e.g. search engine) receives a context (e.g. query) and predicts an object (e.g. ranking). The user responds by correcting the system if necessary, providing a slightly improved -- but not necessarily optimal -- object as feedback. We argue that such feedback can often be inferred from observable user behavior, for example, from clicks in web-search. Evaluating predictions by their cardinal utility to the user, we propose efficient learning algorithms that have ${\\cal O}(\\frac{1}{\\sqrt{T}})$ average regret, even though the learning algorithm never observes cardinal utility values as in conventional online learning. We demonstrate the applicability of our model and learning algorithms on a movie recommendation task, as well as ranking for web-search.", "source": "arxiv/ml"}
{"id": "arxiv:1590", "title": "Thompson Sampling: An Asymptotically Optimal Finite Time Analysis", "text": "The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case.", "source": "arxiv/ml"}
{"id": "arxiv:1591", "title": "Diffusion Adaptation over Networks", "text": "Adaptive networks are well-suited to perform decentralized information processing and optimization tasks and to model various types of self-organized and complex behavior encountered in nature. Adaptive networks consist of a collection of agents with processing and learning abilities. The agents are linked together through a connection topology, and they cooperate with each other through local interactions to solve distributed optimization, estimation, and inference problems in real-time. The continuous diffusion of information across the network enables agents to adapt their performance in relation to streaming data and network conditions; it also results in improved adaptation and learning performance relative to non-cooperative agents. This article provides an overview of diffusion strategies for adaptation and learning over networks. The article is divided into several sections: 1. Motivation; 2. Mean-Square-Error Estimation; 3. Distributed Optimization via Diffusion Strategies; 4. Adaptive Diffusion Strategies; 5. Performance of Steepest-Descent Diffusion Strategies; 6. Performance of Adaptive Diffusion Strategies; 7. Comparing the Performance of Cooperative Strategies; 8. Selecting the Combination Weights; 9. Diffusion with Noisy Information Exchanges; 10. Extensions and Further Considerations; Appendix A: Properties of Kronecker Products; Appendix B: Graph Laplacian and Network Connectivity; Appendix C: Stochastic Matrices; Appendix D: Block Maximum Norm; Appendix E: Comparison with Consensus Strategies; References.", "source": "arxiv/ml"}
{"id": "arxiv:1592", "title": "Visualization of features of a series of measurements with one-dimensional cellular structure", "text": "This paper describes the method of visualization of periodic constituents and instability areas in series of measurements, being based on the algorithm of smoothing out and concept of one-dimensional cellular automata. A method can be used at the analysis of temporal series, related to the volumes of thematic publications in web-space.", "source": "arxiv/ml"}
{"id": "arxiv:1593", "title": "Efficient Methods for Unsupervised Learning of Probabilistic Models", "text": "In this thesis I develop a variety of techniques to train, evaluate, and sample from intractable and high dimensional probabilistic models. Abstract exceeds arXiv space limitations -- see PDF.", "source": "arxiv/ml"}
{"id": "arxiv:1594", "title": "New Analysis and Algorithm for Learning with Drifting Distributions", "text": "We present a new analysis of the problem of learning with drifting distributions in the batch setting using the notion of discrepancy. We prove learning bounds based on the Rademacher complexity of the hypothesis set and the discrepancy of distributions both for a drifting PAC scenario and a tracking scenario. Our bounds are always tighter and in some cases substantially improve upon previous ones based on the $L_1$ distance. We also present a generalization of the standard on-line to batch conversion to the drifting scenario in terms of the discrepancy and arbitrary convex combinations of hypotheses. We introduce a new algorithm exploiting these learning guarantees, which we show can be formulated as a simple QP. Finally, we report the results of preliminary experiments demonstrating the benefits of this algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1595", "title": "From Exact Learning to Computing Boolean Functions and Back Again", "text": "The goal of the paper is to relate complexity measures associated with the evaluation of Boolean functions (certificate complexity, decision tree complexity) and learning dimensions used to characterize exact learning (teaching dimension, extended teaching dimension). The high level motivation is to discover non-trivial relations between exact learning of an unknown concept and testing whether an unknown concept is part of a concept class or not. Concretely, the goal is to provide lower and upper bounds of complexity measures for one problem type in terms of the other.", "source": "arxiv/ml"}
{"id": "arxiv:1596", "title": "Sparse Signal Recovery in the Presence of Intra-Vector and Inter-Vector Correlation", "text": "This work discusses the problem of sparse signal recovery when there is correlation among the values of non-zero entries. We examine intra-vector correlation in the context of the block sparse model and inter-vector correlation in the context of the multiple measurement vector model, as well as their combination. Algorithms based on the sparse Bayesian learning are presented and the benefits of incorporating correlation at the algorithm level are discussed. The impact of correlation on the limits of support recovery is also discussed highlighting the different impact intra-vector and inter-vector correlations have on such limits.", "source": "arxiv/ml"}
{"id": "arxiv:1597", "title": "Soft Rule Ensembles for Statistical Learning", "text": "In this article supervised learning problems are solved using soft rule ensembles. We first review the importance sampling learning ensembles (ISLE) approach that is useful for generating hard rules. The soft rules are then obtained with logistic regression from the corresponding hard rules. In order to deal with the perfect separation problem related to the logistic regression, Firth's bias corrected likelihood is used. Various examples and simulation results show that soft rule ensembles can improve predictive performance over hard rule ensembles.", "source": "arxiv/ml"}
{"id": "arxiv:1598", "title": "Streaming Algorithms for Pattern Discovery over Dynamically Changing Event Sequences", "text": "Discovering frequent episodes over event sequences is an important data mining task. In many applications, events constituting the data sequence arrive as a stream, at furious rates, and recent trends (or frequent episodes) can change and drift due to the dynamical nature of the underlying event generation process. The ability to detect and track such the changing sets of frequent episodes can be valuable in many application scenarios. Current methods for frequent episode discovery are typically multipass algorithms, making them unsuitable in the streaming context. In this paper, we propose a new streaming algorithm for discovering frequent episodes over a window of recent events in the stream. Our algorithm processes events as they arrive, one batch at a time, while discovering the top frequent episodes over a window consisting of several batches in the immediate past. We derive approximation guarantees for our algorithm under the condition that frequent episodes are approximately well-separated from infrequent ones in every batch of the window. We present extensive experimental evaluations of our algorithm on both real and synthetic data. We also present comparisons with baselines and adaptations of streaming algorithms from itemset mining literature.", "source": "arxiv/ml"}
{"id": "arxiv:1599", "title": "Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure", "text": "In this work we consider the stochastic minimization of nonsmooth convex loss functions, a central problem in machine learning. We propose a novel algorithm called Accelerated Nonsmooth Stochastic Gradient Descent (ANSGD), which exploits the structure of common nonsmooth loss functions to achieve optimal convergence rates for a class of problems including SVMs. It is the first stochastic algorithm that can achieve the optimal O(1/t) rate for minimizing nonsmooth loss functions (with strong convexity). The fast rates are confirmed by empirical comparisons, in which ANSGD significantly outperforms previous subgradient descent algorithms including SGD.", "source": "arxiv/ml"}
{"id": "arxiv:1600", "title": "Conditional mean embeddings as regressors - supplementary", "text": "We demonstrate an equivalence between reproducing kernel Hilbert space (RKHS) embeddings of conditional distributions and vector-valued regressors. This connection introduces a natural regularized loss function which the RKHS embeddings minimise, providing an intuitive understanding of the embeddings and a justification for their use. Furthermore, the equivalence allows the application of vector-valued regression methods and results to the problem of learning conditional distributions. Using this link we derive a sparse version of the embedding by considering alternative formulations. Further, by applying convergence results for vector-valued regression to the embedding problem we derive minimax convergence rates which are O(\\log(n)/n) -- compared to current state of the art rates of O(n^{-1/4}) -- and are valid under milder and more intuitive assumptions. These minimax upper rates coincide with lower rates up to a logarithmic factor, showing that the embedding method achieves nearly optimal rates. We study our sparse embedding algorithm in a reinforcement learning task where the algorithm shows significant improvement in sparsity over an incomplete Cholesky decomposition.", "source": "arxiv/ml"}
{"id": "arxiv:1601", "title": "The Role of Weight Shrinking in Large Margin Perceptron Learning", "text": "We introduce into the classical perceptron algorithm with margin a mechanism that shrinks the current weight vector as a first step of the update. If the shrinking factor is constant the resulting algorithm may be regarded as a margin-error-driven version of NORMA with constant learning rate. In this case we show that the allowed strength of shrinking depends on the value of the maximum margin. We also consider variable shrinking factors for which there is no such dependence. In both cases we obtain new generalizations of the perceptron with margin able to provably attain in a finite number of steps any desirable approximation of the maximal margin hyperplane. The new approximate maximum margin classifiers appear experimentally to be very competitive in 2-norm soft margin tasks involving linear kernels.", "source": "arxiv/ml"}
{"id": "arxiv:1602", "title": "Visual and semantic interpretability of projections of high dimensional data for classification tasks", "text": "A number of visual quality measures have been introduced in visual analytics literature in order to automatically select the best views of high dimensional data from a large number of candidate data projections. These methods generally concentrate on the interpretability of the visualization and pay little attention to the interpretability of the projection axes. In this paper, we argue that interpretability of the visualizations and the feature transformation functions are both crucial for visual exploration of high dimensional labeled data. We present a two-part user study to examine these two related but orthogonal aspects of interpretability. We first study how humans judge the quality of 2D scatterplots of various datasets with varying number of classes and provide comparisons with ten automated measures, including a number of visual quality measures and related measures from various machine learning fields. We then investigate how the user perception on interpretability of mathematical expressions relate to various automated measures of complexity that can be used to characterize data projection functions. We conclude with a discussion of how automated measures of visual and semantic interpretability of data projections can be used together for exploratory analysis in classification tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1603", "title": "Safe Exploration in Markov Decision Processes", "text": "In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodicity is that any state is eventually reachable from any other state by following a suitable policy. This assumption allows for exploration algorithms that operate by simply favoring states that have rarely been visited before. For most physical systems this assumption is impractical as the systems would break before any reasonable exploration has taken place, i.e., most physical systems don't satisfy the ergodicity assumption. In this paper we address the need for safe exploration methods in Markov decision processes. We first propose a general formulation of safety through ergodicity. We show that imposing safety by restricting attention to the resulting set of guaranteed safe policies is NP-hard. We then present an efficient algorithm for guaranteed safe, but potentially suboptimal, exploration. At the core is an optimization formulation in which the constraints restrict attention to a subset of the guaranteed safe policies and the objective favors exploration policies. Our framework is compatible with the majority of previously proposed exploration methods, which rely on an exploration bonus. Our experiments, which include a Martian terrain exploration problem, show that our method is able to explore better than classical exploration methods.", "source": "arxiv/ml"}
{"id": "arxiv:1604", "title": "Off-Policy Actor-Critic", "text": "This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on actor-critic algorithms is limited to the on-policy setting and does not take advantage of the recent advances in off-policy gradient temporal-difference learning. Off-policy techniques, such as Greedy-GQ, enable a target policy to be learned while following and obtaining data from another (behavior) policy. For many problems, however, actor-critic methods are more practical than action value methods (like Greedy-GQ) because they explicitly represent the policy; consequently, the policy can be stochastic and utilize a large action space. In this paper, we illustrate how to practically combine the generality and learning potential of off-policy learning with the flexibility in action selection given by actor-critic methods. We derive an incremental, linear time and space complexity algorithm that includes eligibility traces, prove convergence under assumptions similar to previous off-policy algorithms, and empirically show better or comparable performance to existing algorithms on standard reinforcement-learning benchmark problems.", "source": "arxiv/ml"}
{"id": "arxiv:1605", "title": "Clustering is difficult only when it does not matter", "text": "Numerous papers ask how difficult it is to cluster data. We suggest that the more relevant and interesting question is how difficult it is to cluster data sets {\\em that can be clustered well}. More generally, despite the ubiquity and the great importance of clustering, we still do not have a satisfactory mathematical theory of clustering. In order to properly understand clustering, it is clearly necessary to develop a solid theoretical basis for the area. For example, from the perspective of computational complexity theory the clustering problem seems very hard. Numerous papers introduce various criteria and numerical measures to quantify the quality of a given clustering. The resulting conclusions are pessimistic, since it is computationally difficult to find an optimal clustering of a given data set, if we go by any of these popular criteria. In contrast, the practitioners' perspective is much more optimistic. Our explanation for this disparity of opinions is that complexity theory concentrates on the worst case, whereas in reality we only care for data sets that can be clustered well. We introduce a theoretical framework of clustering in metric spaces that revolves around a notion of \"good clustering\". We show that if a good clustering exists, then in many cases it can be efficiently found. Our conclusion is that contrary to popular belief, clustering should not be considered a hard task.", "source": "arxiv/ml"}
{"id": "arxiv:1606", "title": "On the practically interesting instances of MAXCUT", "text": "The complexity of a computational problem is traditionally quantified based on the hardness of its worst case. This approach has many advantages and has led to a deep and beautiful theory. However, from the practical perspective, this leaves much to be desired. In application areas, practically interesting instances very often occupy just a tiny part of an algorithm's space of instances, and the vast majority of instances are simply irrelevant. Addressing these issues is a major challenge for theoretical computer science which may make theory more relevant to the practice of computer science. Following Bilu and Linial, we apply this perspective to MAXCUT, viewed as a clustering problem. Using a variety of techniques, we investigate practically interesting instances of this problem. Specifically, we show how to solve in polynomial time distinguished, metric, expanding and dense instances of MAXCUT under mild stability assumptions. In particular, $(1+\\epsilon)$-stability (which is optimal) suffices for metric and dense MAXCUT. We also show how to solve in polynomial time $\\Omega(\\sqrt{n})$-stable instances of MAXCUT, substantially improving the best previously known result.", "source": "arxiv/ml"}
{"id": "arxiv:1607", "title": "Learning Mixed Graphical Models", "text": "We consider the problem of learning the structure of a pairwise graphical model over continuous and discrete variables. We present a new pairwise model for graphical models with both continuous and discrete variables that is amenable to structure learning. In previous work, authors have considered structure learning of Gaussian graphical models and structure learning of discrete models. Our approach is a natural generalization of these two lines of work to the mixed case. The penalization scheme involves a novel symmetric use of the group-lasso norm and follows naturally from a particular parametrization of the model.", "source": "arxiv/ml"}
{"id": "arxiv:1608", "title": "Efficient Sparse Group Feature Selection via Nonconvex Optimization", "text": "Sparse feature selection has been demonstrated to be effective in handling high-dimensional data. While promising, most of the existing works use convex methods, which may be suboptimal in terms of the accuracy of feature selection and parameter estimation. In this paper, we expand a nonconvex paradigm to sparse group feature selection, which is motivated by applications that require identifying the underlying group structure and performing feature selection simultaneously. The main contributions of this article are twofold: (1) statistically, we introduce a nonconvex sparse group feature selection model which can reconstruct the oracle estimator. Therefore, consistent feature selection and parameter estimation can be achieved; (2) computationally, we propose an efficient algorithm that is applicable to large-scale problems. Numerical results suggest that the proposed nonconvex method compares favorably against its competitors on synthetic data and real-world applications, thus achieving desired goal of delivering high performance.", "source": "arxiv/ml"}
{"id": "arxiv:1609", "title": "A hybrid clustering algorithm for data mining", "text": "Data clustering is a process of arranging similar data into groups. A clustering algorithm partitions a data set into several groups such that the similarity within a group is better than among groups. In this paper a hybrid clustering algorithm based on K-mean and K-harmonic mean (KHM) is described. The proposed algorithm is tested on five different datasets. The research is focused on fast and accurate clustering. Its performance is compared with the traditional K-means & KHM algorithm. The result obtained from proposed hybrid algorithm is much better than the traditional K-mean & KHM algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1610", "title": "Language-Constraint Reachability Learning in Probabilistic Graphs", "text": "The probabilistic graphs framework models the uncertainty inherent in real-world domains by means of probabilistic edges whose value quantifies the likelihood of the edge existence or the strength of the link it represents. The goal of this paper is to provide a learning method to compute the most likely relationship between two nodes in a framework based on probabilistic graphs. In particular, given a probabilistic graph we adopted the language-constraint reachability method to compute the probability of possible interconnections that may exists between two nodes. Each of these connections may be viewed as feature, or a factor, between the two nodes and the corresponding probability as its weight. Each observed link is considered as a positive instance for its corresponding link label. Given the training set of observed links a L2-regularized Logistic Regression has been adopted to learn a model able to predict unobserved link labels. The experiments on a real world collaborative filtering problem proved that the proposed approach achieves better results than that obtained adopting classical methods.", "source": "arxiv/ml"}
{"id": "arxiv:1611", "title": "Measurability Aspects of the Compactness Theorem for Sample Compression Schemes", "text": "It was proved in 1998 by Ben-David and Litman that a concept space has a sample compression scheme of size d if and only if every finite subspace has a sample compression scheme of size d. In the compactness theorem, measurability of the hypotheses of the created sample compression scheme is not guaranteed; at the same time measurability of the hypotheses is a necessary condition for learnability. In this thesis we discuss when a sample compression scheme, created from com- pression schemes on finite subspaces via the compactness theorem, have measurable hypotheses. We show that if X is a standard Borel space with a d-maximum and universally separable concept class C, then (X,C) has a sample compression scheme of size d with universally Borel measurable hypotheses. Additionally we introduce a new variant of compression scheme called a copy sample compression scheme.", "source": "arxiv/ml"}
{"id": "arxiv:1612", "title": "Towards a Mathematical Foundation of Immunology and Amino Acid Chains", "text": "We attempt to set a mathematical foundation of immunology and amino acid chains. To measure the similarities of these chains, a kernel on strings is defined using only the sequence of the chains and a good amino acid substitution matrix (e.g. BLOSUM62). The kernel is used in learning machines to predict binding affinities of peptides to human leukocyte antigens DR (HLA-DR) molecules. On both fixed allele (Nielsen and Lund 2009) and pan-allele (Nielsen et.al. 2010) benchmark databases, our algorithm achieves the state-of-the-art performance. The kernel is also used to define a distance on an HLA-DR allele set based on which a clustering analysis precisely recovers the serotype classifications assigned by WHO (Nielsen and Lund 2009, and Marsh et.al. 2010). These results suggest that our kernel relates well the chain structure of both peptides and HLA-DR molecules to their biological functions, and that it offers a simple, powerful and promising methodology to immunology and amino acid chain studies.", "source": "arxiv/ml"}
{"id": "arxiv:1613", "title": "Learning Dictionaries with Bounded Self-Coherence", "text": "Sparse coding in learned dictionaries has been established as a successful approach for signal denoising, source separation and solving inverse problems in general. A dictionary learning method adapts an initial dictionary to a particular signal class by iteratively computing an approximate factorization of a training data matrix into a dictionary and a sparse coding matrix. The learned dictionary is characterized by two properties: the coherence of the dictionary to observations of the signal class, and the self-coherence of the dictionary atoms. A high coherence to the signal class enables the sparse coding of signal observations with a small approximation error, while a low self-coherence of the atoms guarantees atom recovery and a more rapid residual error decay rate for the sparse coding algorithm. The two goals of high signal coherence and low self-coherence are typically in conflict, therefore one seeks a trade-off between them, depending on the application. We present a dictionary learning method with an effective control over the self-coherence of the trained dictionary, enabling a trade-off between maximizing the sparsity of codings and approximating an equiangular tight frame.", "source": "arxiv/ml"}
{"id": "arxiv:1614", "title": "A Framework for Evaluating Approximation Methods for Gaussian Process Regression", "text": "Gaussian process (GP) predictors are an important component of many Bayesian approaches to machine learning. However, even a straightforward implementation of Gaussian process regression (GPR) requires O(n^2) space and O(n^3) time for a dataset of n examples. Several approximation methods have been proposed, but there is a lack of understanding of the relative merits of the different approximations, and in what situations they are most useful. We recommend assessing the quality of the predictions obtained as a function of the compute time taken, and comparing to standard baselines (e.g., Subset of Data and FITC). We empirically investigate four different approximation algorithms on four different prediction problems, and make our code available to encourage future comparisons.", "source": "arxiv/ml"}
{"id": "arxiv:1615", "title": "Multiclass Learning Approaches: A Theoretical Comparison with Implications", "text": "We theoretically analyze and compare the following five popular multiclass classification methods: One vs. All, All Pairs, Tree-based classifiers, Error Correcting Output Codes (ECOC) with randomly generated code matrices, and Multiclass SVM. In the first four methods, the classification is based on a reduction to binary classification. We consider the case where the binary classifier comes from a class of VC dimension $d$, and in particular from the class of halfspaces over $\\reals^d$. We analyze both the estimation error and the approximation error of these methods. Our analysis reveals interesting conclusions of practical relevance, regarding the success of the different approaches under various conditions. Our proof technique employs tools from VC theory to analyze the \\emph{approximation error} of hypothesis classes. This is in sharp contrast to most, if not all, previous uses of VC theory, which only deal with estimation error.", "source": "arxiv/ml"}
{"id": "arxiv:1616", "title": "Finding Important Genes from High-Dimensional Data: An Appraisal of Statistical Tests and Machine-Learning Approaches", "text": "Over the past decades, statisticians and machine-learning researchers have developed literally thousands of new tools for the reduction of high-dimensional data in order to identify the variables most responsible for a particular trait. These tools have applications in a plethora of settings, including data analysis in the fields of business, education, forensics, and biology (such as microarray, proteomics, brain imaging), to name a few. In the present work, we focus our investigation on the limitations and potential misuses of certain tools in the analysis of the benchmark colon cancer data (2,000 variables; Alon et al., 1999) and the prostate cancer data (6,033 variables; Efron, 2010, 2008). Our analysis demonstrates that models that produce 100% accuracy measures often select different sets of genes and cannot stand the scrutiny of parameter estimates and model stability. Furthermore, we created a host of simulation datasets and \"artificial diseases\" to evaluate the reliability of commonly used statistical and data mining tools. We found that certain widely used models can classify the data with 100% accuracy without using any of the variables responsible for the disease. With moderate sample size and suitable pre-screening, stochastic gradient boosting will be shown to be a superior model for gene selection and variable screening from high-dimensional datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1617", "title": "A Brief Summary of Dictionary Learning Based Approach for Classification (revised)", "text": "This note presents some representative methods which are based on dictionary learning (DL) for classification. We do not review the sophisticated methods or frameworks that involve DL for classification, such as online DL and spatial pyramid matching (SPM), but rather, we concentrate on the direct DL-based classification methods. Here, the \"so-called direct DL-based method\" is the approach directly deals with DL framework by adding some meaningful penalty terms. By listing some representative methods, we can roughly divide them into two categories, i.e. (1) directly making the dictionary discriminative and (2) forcing the sparse coefficients discriminative to push the discrimination power of the dictionary. From this taxonomy, we can expect some extensions of them as future researches.", "source": "arxiv/ml"}
{"id": "arxiv:1618", "title": "Beyond $\\ell_1$-norm minimization for sparse signal recovery", "text": "Sparse signal recovery has been dominated by the basis pursuit denoise (BPDN) problem formulation for over a decade. In this paper, we propose an algorithm that outperforms BPDN in finding sparse solutions to underdetermined linear systems of equations at no additional computational cost. Our algorithm, called WSPGL1, is a modification of the spectral projected gradient for $\\ell_1$ minimization (SPGL1) algorithm in which the sequence of LASSO subproblems are replaced by a sequence of weighted LASSO subproblems with constant weights applied to a support estimate. The support estimate is derived from the data and is updated at every iteration. The algorithm also modifies the Pareto curve at every iteration to reflect the new weighted $\\ell_1$ minimization problem that is being solved. We demonstrate through extensive simulations that the sparse recovery performance of our algorithm is superior to that of $\\ell_1$ minimization and approaches the recovery performance of iterative re-weighted $\\ell_1$ (IRWL1) minimization of Cand{\\`e}s, Wakin, and Boyd, although it does not match it in general. Moreover, our algorithm has the computational cost of a single BPDN problem.", "source": "arxiv/ml"}
{"id": "arxiv:1619", "title": "Posterior contraction of the population polytope in finite admixture models", "text": "We study the posterior contraction behavior of the latent population structure that arises in admixture models as the amount of data increases. We adopt the geometric view of admixture models - alternatively known as topic models - as a data generating mechanism for points randomly sampled from the interior of a (convex) population polytope, whose extreme points correspond to the population structure variables of interest. Rates of posterior contraction are established with respect to Hausdorff metric and a minimum matching Euclidean metric defined on polytopes. Tools developed include posterior asymptotics of hierarchical models and arguments from convex geometry.", "source": "arxiv/ml"}
{"id": "arxiv:1620", "title": "Sparse Trace Norm Regularization", "text": "We study the problem of estimating multiple predictive functions from a dictionary of basis functions in the nonparametric regression setting. Our estimation scheme assumes that each predictive function can be estimated in the form of a linear combination of the basis functions. By assuming that the coefficient matrix admits a sparse low-rank structure, we formulate the function estimation problem as a convex program regularized by the trace norm and the $\\ell_1$-norm simultaneously. We propose to solve the convex program using the accelerated gradient (AG) method and the alternating direction method of multipliers (ADMM) respectively; we also develop efficient algorithms to solve the key components in both AG and ADMM. In addition, we conduct theoretical analysis on the proposed function estimation scheme: we derive a key property of the optimal solution to the convex program; based on an assumption on the basis functions, we establish a performance bound of the proposed function estimation scheme (via the composite regularization). Simulation studies demonstrate the effectiveness and efficiency of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1621", "title": "A Route Confidence Evaluation Method for Reliable Hierarchical Text Categorization", "text": "Hierarchical Text Categorization (HTC) is becoming increasingly important with the rapidly growing amount of text data available in the World Wide Web. Among the different strategies proposed to cope with HTC, the Local Classifier per Node (LCN) approach attains good performance by mirroring the underlying class hierarchy while enforcing a top-down strategy in the testing step. However, the problem of embedding hierarchical information (parent-child relationship) to improve the performance of HTC systems still remains open. A confidence evaluation method for a selected route in the hierarchy is proposed to evaluate the reliability of the final candidate labels in an HTC system. In order to take into account the information embedded in the hierarchy, weight factors are used to take into account the importance of each level. An acceptance/rejection strategy in the top-down decision making process is proposed, which improves the overall categorization accuracy by rejecting a few percentage of samples, i.e., those with low reliability score. Experimental results on the Reuters benchmark dataset (RCV1- v2) confirm the effectiveness of the proposed method, compared to other state-of-the art HTC methods.", "source": "arxiv/ml"}
{"id": "arxiv:1622", "title": "Poisson noise reduction with non-local PCA", "text": "Photon-limited imaging arises when the number of photons collected by a sensor array is small relative to the number of detector elements. Photon limitations are an important concern for many applications such as spectral imaging, night vision, nuclear medicine, and astronomy. Typically a Poisson distribution is used to model these observations, and the inherent heteroscedasticity of the data combined with standard noise removal methods yields significant artifacts. This paper introduces a novel denoising algorithm for photon-limited images which combines elements of dictionary learning and sparse patch-based representations of images. The method employs both an adaptation of Principal Component Analysis (PCA) for Poisson noise and recently developed sparsity-regularized convex optimization algorithms for photon-limited images. A comprehensive empirical evaluation of the proposed method helps characterize the performance of this approach relative to other state-of-the-art denoising methods. The results reveal that, despite its conceptual simplicity, Poisson PCA-based denoising appears to be highly competitive in very low light regimes.", "source": "arxiv/ml"}
{"id": "arxiv:1623", "title": "Learning in Hierarchical Social Networks", "text": "We study a social network consisting of agents organized as a hierarchical M-ary rooted tree, common in enterprise and military organizational structures. The goal is to aggregate information to solve a binary hypothesis testing problem. Each agent at a leaf of the tree, and only such an agent, makes a direct measurement of the underlying true hypothesis. The leaf agent then makes a decision and sends it to its supervising agent, at the next level of the tree. Each supervising agent aggregates the decisions from the M members of its group, produces a summary message, and sends it to its supervisor at the next level, and so on. Ultimately, the agent at the root of the tree makes an overall decision. We derive upper and lower bounds for the Type I and II error probabilities associated with this decision with respect to the number of leaf agents, which in turn characterize the converge rates of the Type I, Type II, and total error probabilities. We also provide a message-passing scheme involving non-binary message alphabets and characterize the exponent of the error probability with respect to the message alphabet size.", "source": "arxiv/ml"}
{"id": "arxiv:1624", "title": "Topological graph clustering with thin position", "text": "A clustering algorithm partitions a set of data points into smaller sets (clusters) such that each subset is more tightly packed than the whole. Many approaches to clustering translate the vector data into a graph with edges reflecting a distance or similarity metric on the points, then look for highly connected subgraphs. We introduce such an algorithm based on ideas borrowed from the topological notion of thin position for knots and 3-dimensional manifolds.", "source": "arxiv/ml"}
{"id": "arxiv:1625", "title": "A Mixed Observability Markov Decision Process Model for Musical Pitch", "text": "Partially observable Markov decision processes have been widely used to provide models for real-world decision making problems. In this paper, we will provide a method in which a slightly different version of them called Mixed observability Markov decision process, MOMDP, is going to join with our problem. Basically, we aim at offering a behavioural model for interaction of intelligent agents with musical pitch environment and we will show that how MOMDP can shed some light on building up a decision making model for musical pitch conveniently.", "source": "arxiv/ml"}
{"id": "arxiv:1626", "title": "Nearly optimal solutions for the Chow Parameters Problem and low-weight approximation of halfspaces", "text": "The \\emph{Chow parameters} of a Boolean function $f: \\{-1,1\\}^n \\to \\{-1,1\\}$ are its $n+1$ degree-0 and degree-1 Fourier coefficients. It has been known since 1961 (Chow, Tannenbaum) that the (exact values of the) Chow parameters of any linear threshold function $f$ uniquely specify $f$ within the space of all Boolean functions, but until recently (O'Donnell and Servedio) nothing was known about efficient algorithms for \\emph{reconstructing} $f$ (exactly or approximately) from exact or approximate values of its Chow parameters. We refer to this reconstruction problem as the \\emph{Chow Parameters Problem.} Our main result is a new algorithm for the Chow Parameters Problem which, given (sufficiently accurate approximations to) the Chow parameters of any linear threshold function $f$, runs in time $\\tilde{O}(n^2)\\cdot (1/\\eps)^{O(\\log^2(1/\\eps))}$ and with high probability outputs a representation of an LTF $f'$ that is $\\eps$-close to $f$. The only previous algorithm (O'Donnell and Servedio) had running time $\\poly(n) \\cdot 2^{2^{\\tilde{O}(1/\\eps^2)}}.$ As a byproduct of our approach, we show that for any linear threshold function $f$ over $\\{-1,1\\}^n$, there is a linear threshold function $f'$ which is $\\eps$-close to $f$ and has all weights that are integers at most $\\sqrt{n} \\cdot (1/\\eps)^{O(\\log^2(1/\\eps))}$. This significantly improves the best previous result of Diakonikolas and Servedio which gave a $\\poly(n) \\cdot 2^{\\tilde{O}(1/\\eps^{2/3})}$ weight bound, and is close to the known lower bound of $\\max\\{\\sqrt{n},$ $(1/\\eps)^{\\Omega(\\log \\log (1/\\eps))}\\}$ (Goldberg, Servedio). Our techniques also yield improved algorithms for related problems in learning theory.", "source": "arxiv/ml"}
{"id": "arxiv:1627", "title": "An Optimization Framework for Semi-Supervised and Transfer Learning using Multiple Classifiers and Clusterers", "text": "Unsupervised models can provide supplementary soft constraints to help classify new, \"target\" data since similar instances in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in applications where concept drift may take place, as in transfer learning settings. This paper describes a general optimization framework that takes as input class membership estimates from existing classifiers learnt on previously encountered \"source\" data, as well as a similarity matrix from a cluster ensemble operating solely on the target data to be classified, and yields a consensus labeling of the target data. This framework admits a wide range of loss functions and classification/clustering methods. It exploits properties of Bregman divergences in conjunction with Legendre duality to yield a principled and scalable approach. A variety of experiments show that the proposed framework can yield results substantially superior to those provided by popular transductive learning techniques or by naively applying classifiers learnt on the original task to the target data.", "source": "arxiv/ml"}
{"id": "arxiv:1628", "title": "A Machine Learning Approach For Opinion Holder Extraction In Arabic Language", "text": "Opinion mining aims at extracting useful subjective information from reliable amounts of text. Opinion mining holder recognition is a task that has not been considered yet in Arabic Language. This task essentially requires deep understanding of clauses structures. Unfortunately, the lack of a robust, publicly available, Arabic parser further complicates the research. This paper presents a leading research for the opinion holder extraction in Arabic news independent from any lexical parsers. We investigate constructing a comprehensive feature set to compensate the lack of parsing structural outcomes. The proposed feature set is tuned from English previous works coupled with our proposed semantic field and named entities features. Our feature analysis is based on Conditional Random Fields (CRF) and semi-supervised pattern recognition techniques. Different research models are evaluated via cross-validation experiments achieving 54.03 F-measure. We publicly release our own research outcome corpus and lexicon for opinion mining community to encourage further research.", "source": "arxiv/ml"}
{"id": "arxiv:1629", "title": "Bayesian Structure Learning for Markov Random Fields with a Spike and Slab Prior", "text": "In recent years a number of methods have been developed for automatically learning the (sparse) connectivity structure of Markov Random Fields. These methods are mostly based on L1-regularized optimization which has a number of disadvantages such as the inability to assess model uncertainty and expensive cross-validation to find the optimal regularization parameter. Moreover, the model's predictive performance may degrade dramatically with a suboptimal value of the regularization parameter (which is sometimes desirable to induce sparseness). We propose a fully Bayesian approach based on a \"spike and slab\" prior (similar to L0 regularization) that does not suffer from these shortcomings. We develop an approximate MCMC method combining Langevin dynamics and reversible jump MCMC to conduct inference in this model. Experiments show that the proposed model learns a good combination of the structure and parameter values without the need for separate hyper-parameter tuning. Moreover, the model's predictive performance is much more robust than L1-based methods with hyper-parameter settings that induce highly sparse model structures.", "source": "arxiv/ml"}
{"id": "arxiv:1630", "title": "No More Pesky Learning Rates", "text": "The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any one time. The method relies on local gradient variations across samples. In our approach, learning rates can increase as well as decrease, making it suitable for non-stationary problems. Using a number of convex and non-convex learning tasks, we show that the resulting algorithm matches the performance of SGD or other adaptive approaches with their best settings obtained through systematic search, and effectively removes the need for learning rate tuning.", "source": "arxiv/ml"}
{"id": "arxiv:1631", "title": "Comparison of the C4.5 and a Naive Bayes Classifier for the Prediction of Lung Cancer Survivability", "text": "Numerous data mining techniques have been developed to extract information and identify patterns and predict trends from large data sets. In this study, two classification techniques, the J48 implementation of the C4.5 algorithm and a Naive Bayes classifier are applied to predict lung cancer survivability from an extensive data set with fifteen years of patient records. The purpose of the project is to verify the predictive effectiveness of the two techniques on real, historical data. Besides the performance outcome that renders J48 marginally better than the Naive Bayes technique, there is a detailed description of the data and the required pre-processing activities. The performance results confirm expectations while some of the issues that appeared during experimentation, underscore the value of having domain-specific understanding to leverage any domain-specific characteristics inherent in the data.", "source": "arxiv/ml"}
{"id": "arxiv:1632", "title": "Memory-Efficient Topic Modeling", "text": "As one of the simplest probabilistic topic modeling techniques, latent Dirichlet allocation (LDA) has found many important applications in text mining, computer vision and computational biology. Recent training algorithms for LDA can be interpreted within a unified message passing framework. However, message passing requires storing previous messages with a large amount of memory space, increasing linearly with the number of documents or the number of topics. Therefore, the high memory usage is often a major problem for topic modeling of massive corpora containing a large number of topics. To reduce the space complexity, we propose a novel algorithm without storing previous messages for training LDA: tiny belief propagation (TBP). The basic idea of TBP relates the message passing algorithms with the non-negative matrix factorization (NMF) algorithms, which absorb the message updating into the message passing process, and thus avoid storing previous messages. Experimental results on four large data sets confirm that TBP performs comparably well or even better than current state-of-the-art training algorithms for LDA but with a much less memory consumption. TBP can do topic modeling when massive corpora cannot fit in the computer memory, for example, extracting thematic topics from 7 GB PUBMED corpora on a common desktop computer with 2GB memory.", "source": "arxiv/ml"}
{"id": "arxiv:1633", "title": "Cumulative Step-size Adaptation on Linear Functions: Technical Report", "text": "The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies the CSA-ES on composites of strictly increasing with affine linear functions through the investigation of its underlying Markov chains. Rigorous results on the change and the variation of the step size are derived with and without cumulation. The step-size diverges geometrically fast in most cases. Furthermore, the influence of the cumulation parameter is studied.", "source": "arxiv/ml"}
{"id": "arxiv:1634", "title": "Factoring nonnegative matrices with linear programs", "text": "This paper describes a new approach, based on linear programming, for computing nonnegative matrix factorizations (NMFs). The key idea is a data-driven model for the factorization where the most salient features in the data are used to express the remaining features. More precisely, given a data matrix X, the algorithm identifies a matrix C such that X approximately equals CX and some linear constraints. The constraints are chosen to ensure that the matrix C selects features; these features can then be used to find a low-rank NMF of X. A theoretical analysis demonstrates that this approach has guarantees similar to those of the recent NMF algorithm of Arora et al. (2012). In contrast with this earlier work, the proposed method extends to more general noise models and leads to efficient, scalable algorithms. Experiments with synthetic and real datasets provide evidence that the new approach is also superior in practice. An optimized C++ implementation can factor a multigigabyte matrix in a matter of minutes.", "source": "arxiv/ml"}
{"id": "arxiv:1635", "title": "A New Greedy Algorithm for Multiple Sparse Regression", "text": "This paper proposes a new algorithm for multiple sparse regression in high dimensions, where the task is to estimate the support and values of several (typically related) sparse vectors from a few noisy linear measurements. Our algorithm is a \"forward-backward\" greedy procedure that -- uniquely -- operates on two distinct classes of objects. In particular, we organize our target sparse vectors as a matrix; our algorithm involves iterative addition and removal of both (a) individual elements, and (b) entire rows (corresponding to shared features), of the matrix. Analytically, we establish that our algorithm manages to recover the supports (exactly) and values (approximately) of the sparse vectors, under assumptions similar to existing approaches based on convex optimization. However, our algorithm has a much smaller computational complexity. Perhaps most interestingly, it is seen empirically to require visibly fewer samples. Ours represents the first attempt to extend greedy algorithms to the class of models that can only/best be represented by a combination of component structural assumptions (sparse and group-sparse, in our case).", "source": "arxiv/ml"}
{"id": "arxiv:1636", "title": "Sparse projections onto the simplex", "text": "Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the $\\ell_1$-norm. However, several important learning applications cannot benefit from this approach as they feature these convex norms as constraints in addition to the non-convex rank and sparsity constraints. In this setting, we derive efficient sparse projections onto the simplex and its extension, and illustrate how to use them to solve high-dimensional learning problems in quantum tomography, sparse density estimation and portfolio selection with non-convex constraints.", "source": "arxiv/ml"}
{"id": "arxiv:1637", "title": "Proximal Newton-type methods for minimizing composite functions", "text": "We generalize Newton-type methods for minimizing smooth functions to handle a sum of two convex functions: a smooth function and a nonsmooth function with a simple proximal mapping. We show that the resulting proximal Newton-type methods inherit the desirable convergence behavior of Newton-type methods for minimizing smooth functions, even when search directions are computed inexactly. Many popular methods tailored to problems arising in bioinformatics, signal processing, and statistical learning are special cases of proximal Newton-type methods, and our analysis yields new convergence results for some of these methods.", "source": "arxiv/ml"}
{"id": "arxiv:1638", "title": "Dimension Reduction by Mutual Information Discriminant Analysis", "text": "In the past few decades, researchers have proposed many discriminant analysis (DA) algorithms for the study of high-dimensional data in a variety of problems. Most DA algorithms for feature extraction are based on transformations that simultaneously maximize the between-class scatter and minimize the withinclass scatter matrices. This paper presents a novel DA algorithm for feature extraction using mutual information (MI). However, it is not always easy to obtain an accurate estimation for high-dimensional MI. In this paper, we propose an efficient method for feature extraction that is based on one-dimensional MI estimations. We will refer to this algorithm as mutual information discriminant analysis (MIDA). The performance of this proposed method was evaluated using UCI databases. The results indicate that MIDA provides robust performance over different data sets with different characteristics and that MIDA always performs better than, or at least comparable to, the best performing algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1639", "title": "Communication-Efficient Parallel Belief Propagation for Latent Dirichlet Allocation", "text": "This paper presents a novel communication-efficient parallel belief propagation (CE-PBP) algorithm for training latent Dirichlet allocation (LDA). Based on the synchronous belief propagation (BP) algorithm, we first develop a parallel belief propagation (PBP) algorithm on the parallel architecture. Because the extensive communication delay often causes a low efficiency of parallel topic modeling, we further use Zipf's law to reduce the total communication cost in PBP. Extensive experiments on different data sets demonstrate that CE-PBP achieves a higher topic modeling accuracy and reduces more than 80% communication cost than the state-of-the-art parallel Gibbs sampling (PGS) algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1640", "title": "Fast Cross-Validation via Sequential Testing", "text": "With the increasing size of today's data sets, finding the right parameter configuration in model selection via cross-validation can be an extremely time-consuming task. In this paper we propose an improved cross-validation procedure which uses nonparametric testing coupled with sequential analysis to determine the best parameter set on linearly increasing subsets of the data. By eliminating underperforming candidates quickly and keeping promising candidates as long as possible, the method speeds up the computation while preserving the capability of the full cross-validation. Theoretical considerations underline the statistical power of our procedure. The experimental evaluation shows that our method reduces the computation time by a factor of up to 120 compared to a full cross-validation with a negligible impact on the accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:1641", "title": "PRISMA: PRoximal Iterative SMoothing Algorithm", "text": "Motivated by learning problems including max-norm regularized matrix completion and clustering, robust PCA and sparse inverse covariance selection, we propose a novel optimization algorithm for minimizing a convex objective which decomposes into three parts: a smooth part, a simple non-smooth Lipschitz part, and a simple non-smooth non-Lipschitz part. We use a time variant smoothing strategy that allows us to obtain a guarantee that does not depend on knowing in advance the total number of iterations nor a bound on the domain.", "source": "arxiv/ml"}
{"id": "arxiv:1642", "title": "IDS: An Incremental Learning Algorithm for Finite Automata", "text": "We present a new algorithm IDS for incremental learning of deterministic finite automata (DFA). This algorithm is based on the concept of distinguishing sequences introduced in (Angluin81). We give a rigorous proof that two versions of this learning algorithm correctly learn in the limit. Finally we present an empirical performance analysis that compares these two algorithms, focussing on learning times and different types of learning queries. We conclude that IDS is an efficient algorithm for software engineering applications of automata learning, such as testing and model inference.", "source": "arxiv/ml"}
{"id": "arxiv:1643", "title": "Practical Bayesian Optimization of Machine Learning Algorithms", "text": "Machine learning algorithms frequently require careful tuning of model hyperparameters, regularization terms, and optimization parameters. Unfortunately, this tuning is often a \"black art\" that requires expert experience, unwritten rules of thumb, or sometimes brute-force search. Much more appealing is the idea of developing automatic approaches which can optimize the performance of a given learning algorithm to the task at hand. In this work, we consider the automatic tuning problem within the framework of Bayesian optimization, in which a learning algorithm's generalization performance is modeled as a sample from a Gaussian process (GP). The tractable posterior distribution induced by the GP leads to efficient use of the information gathered by previous experiments, enabling optimal choices about what parameters to try next. Here we show how the effects of the Gaussian process prior and the associated inference procedure can have a large impact on the success or failure of Bayesian optimization. We show that thoughtful choices can lead to results that exceed expert-level performance in tuning machine learning algorithms. We also describe new algorithms that take into account the variable cost (duration) of learning experiments and that can leverage the presence of multiple cores for parallel experimentation. We show that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization on a diverse set of contemporary algorithms including latent Dirichlet allocation, structured SVMs and convolutional neural networks.", "source": "arxiv/ml"}
{"id": "arxiv:1644", "title": "Statistical Consistency of Finite-dimensional Unregularized Linear Classification", "text": "This manuscript studies statistical properties of linear classifiers obtained through minimization of an unregularized convex risk over a finite sample. Although the results are explicitly finite-dimensional, inputs may be passed through feature maps; in this way, in addition to treating the consistency of logistic regression, this analysis also handles boosting over a finite weak learning class with, for instance, the exponential, logistic, and hinge losses. In this finite-dimensional setting, it is still possible to fit arbitrary decision boundaries: scaling the complexity of the weak learning class with the sample size leads to the optimal classification risk almost surely.", "source": "arxiv/ml"}
{"id": "arxiv:1645", "title": "Sparse Distributed Learning Based on Diffusion Adaptation", "text": "This article proposes diffusion LMS strategies for distributed estimation over adaptive networks that are able to exploit sparsity in the underlying system model. The approach relies on convex regularization, common in compressive sensing, to enhance the detection of sparsity via a diffusive process over the network. The resulting algorithms endow networks with learning abilities and allow them to learn the sparse structure from the incoming data in real-time, and also to track variations in the sparsity of the model. We provide convergence and mean-square performance analysis of the proposed method and show under what conditions it outperforms the unregularized diffusion version. We also show how to adaptively select the regularization parameter. Simulation results illustrate the advantage of the proposed filters for sparse data recovery.", "source": "arxiv/ml"}
{"id": "arxiv:1646", "title": "Identifiability and Unmixing of Latent Parse Trees", "text": "This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing models. Second, for identifiable models, how do we estimate the parameters efficiently? EM suffers from local optima, while recent work using spectral methods cannot be directly applied since the topology of the parse tree varies across sentences. We develop a strategy, unmixing, which deals with this additional complexity for restricted classes of parsing models.", "source": "arxiv/ml"}
{"id": "arxiv:1647", "title": "Improved Spectral-Norm Bounds for Clustering", "text": "Aiming to unify known results about clustering mixtures of distributions under separation conditions, Kumar and Kannan[2010] introduced a deterministic condition for clustering datasets. They showed that this single deterministic condition encompasses many previously studied clustering assumptions. More specifically, their proximity condition requires that in the target $k$-clustering, the projection of a point $x$ onto the line joining its cluster center $\\mu$ and some other center $\\mu'$, is a large additive factor closer to $\\mu$ than to $\\mu'$. This additive factor can be roughly described as $k$ times the spectral norm of the matrix representing the differences between the given (known) dataset and the means of the (unknown) target clustering. Clearly, the proximity condition implies center separation -- the distance between any two centers must be as large as the above mentioned bound. In this paper we improve upon the work of Kumar and Kannan along several axes. First, we weaken the center separation bound by a factor of $\\sqrt{k}$, and secondly we weaken the proximity condition by a factor of $k$. Using these weaker bounds we still achieve the same guarantees when all points satisfy the proximity condition. We also achieve better guarantees when only $(1-\\epsilon)$-fraction of the points satisfy the weaker proximity condition. The bulk of our analysis relies only on center separation under which one can produce a clustering which (i) has low error, (ii) has low $k$-means cost, and (iii) has centers very close to the target centers. Our improved separation condition allows us to match the results of the Planted Partition Model of McSherry[2001], improve upon the results of Ostrovsky et al[2006], and improve separation results for mixture of Gaussian models in a particular setting.", "source": "arxiv/ml"}
{"id": "arxiv:1648", "title": "CORL: A Continuous-state Offset-dynamics Reinforcement Learner", "text": "Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in our bounds. Finally, we report an experiment using a robotic car driving over varying terrain to demonstrate that these dynamics representations adequately capture real-world dynamics and that our algorithm can be used to efficiently solve such problems.", "source": "arxiv/ml"}
{"id": "arxiv:1649", "title": "Learning Inclusion-Optimal Chordal Graphs", "text": "Chordal graphs can be used to encode dependency models that are representable by both directed acyclic and undirected graphs. This paper discusses a very simple and efficient algorithm to learn the chordal structure of a probabilistic model from data. The algorithm is a greedy hill-climbing search algorithm that uses the inclusion boundary neighborhood over chordal graphs. In the limit of a large sample size and under appropriate hypotheses on the scoring criterion, we prove that the algorithm will find a structure that is inclusion-optimal when the dependency model of the data-generating distribution can be represented exactly by an undirected graph. The algorithm is evaluated on simulated datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1650", "title": "Clique Matrices for Statistical Graph Decomposition and Parameterising Restricted Positive Definite Matrices", "text": "We introduce Clique Matrices as an alternative representation of undirected graphs, being a generalisation of the incidence matrix representation. Here we use clique matrices to decompose a graph into a set of possibly overlapping clusters, de ned as well-connected subsets of vertices. The decomposition is based on a statistical description which encourages clusters to be well connected and few in number. Inference is carried out using a variational approximation. Clique matrices also play a natural role in parameterising positive de nite matrices under zero constraints on elements of the matrix. We show that clique matrices can parameterise all positive de nite matrices restricted according to a decomposable graph and form a structured Factor Analysis approximation in the non-decomposable case.", "source": "arxiv/ml"}
{"id": "arxiv:1651", "title": "Greedy Block Coordinate Descent for Large Scale Gaussian Process Regression", "text": "We propose a variable decomposition algorithm -greedy block coordinate descent (GBCD)- in order to make dense Gaussian process regression practical for large scale problems. GBCD breaks a large scale optimization into a series of small sub-problems. The challenge in variable decomposition algorithms is the identification of a subproblem (the active set of variables) that yields the largest improvement. We analyze the limitations of existing methods and cast the active set selection into a zero-norm constrained optimization problem that we solve using greedy methods. By directly estimating the decrease in the objective function, we obtain not only efficient approximate solutions for GBCD, but we are also able to demonstrate that the method is globally convergent. Empirical comparisons against competing dense methods like Conjugate Gradient or SMO show that GBCD is an order of magnitude faster. Comparisons against sparse GP methods show that GBCD is both accurate and capable of handling datasets of 100,000 samples or more.", "source": "arxiv/ml"}
{"id": "arxiv:1652", "title": "Approximating the Partition Function by Deleting and then Correcting for Model Edges", "text": "We propose an approach for approximating the partition function which is based on two steps: (1) computing the partition function of a simplified model which is obtained by deleting model edges, and (2) rectifying the result by applying an edge-by-edge correction. The approach leads to an intuitive framework in which one can trade-off the quality of an approximation with the complexity of computing it. It also includes the Bethe free energy approximation as a degenerate case. We develop the approach theoretically in this paper and provide a number of empirical results that reveal its practical utility.", "source": "arxiv/ml"}
{"id": "arxiv:1653", "title": "Multi-View Learning in the Presence of View Disagreement", "text": "Traditional multi-view learning approaches suffer in the presence of view disagreement,i.e., when samples in each view do not belong to the same class due to view corruption, occlusion or other noise processes. In this paper we present a multi-view learning approach that uses a conditional entropy criterion to detect view disagreement. Once detected, samples with view disagreement are filtered and standard multi-view learning methods can be successfully applied to the remaining samples. Experimental evaluation on synthetic and audio-visual databases demonstrates that the detection and filtering of view disagreement considerably increases the performance of traditional multi-view learning approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1654", "title": "Bounds on the Bethe Free Energy for Gaussian Networks", "text": "We address the problem of computing approximate marginals in Gaussian probabilistic models by using mean field and fractional Bethe approximations. As an extension of Welling and Teh (2001), we define the Gaussian fractional Bethe free energy in terms of the moment parameters of the approximate marginals and derive an upper and lower bound for it. We give necessary conditions for the Gaussian fractional Bethe free energies to be bounded from below. It turns out that the bounding condition is the same as the pairwise normalizability condition derived by Malioutov et al. (2006) as a sufficient condition for the convergence of the message passing algorithm. By giving a counterexample, we disprove the conjecture in Welling and Teh (2001): even when the Bethe free energy is not bounded from below, it can possess a local minimum to which the minimization algorithms can converge.", "source": "arxiv/ml"}
{"id": "arxiv:1655", "title": "Learning Convex Inference of Marginals", "text": "Graphical models trained using maximum likelihood are a common tool for probabilistic inference of marginal distributions. However, this approach suffers difficulties when either the inference process or the model is approximate. In this paper, the inference process is first defined to be the minimization of a convex function, inspired by free energy approximations. Learning is then done directly in terms of the performance of the inference process at univariate marginal prediction. The main novelty is that this is a direct minimization of emperical risk, where the risk measures the accuracy of predicted marginals.", "source": "arxiv/ml"}
{"id": "arxiv:1656", "title": "Projected Subgradient Methods for Learning Sparse Gaussians", "text": "Gaussian Markov random fields (GMRFs) are useful in a broad range of applications. In this paper we tackle the problem of learning a sparse GMRF in a high-dimensional space. Our approach uses the l1-norm as a regularization on the inverse covariance matrix. We utilize a novel projected gradient method, which is faster than previous methods in practice and equal to the best performing of these in asymptotic complexity. We also extend the l1-regularized objective to the problem of sparsifying entire blocks within the inverse covariance matrix. Our methods generalize fairly easily to this case, while other methods do not. We demonstrate that our extensions give better generalization performance on two real domains--biological network analysis and a 2D-shape modeling image task.", "source": "arxiv/ml"}
{"id": "arxiv:1657", "title": "Convex Point Estimation using Undirected Bayesian Transfer Hierarchies", "text": "When related learning tasks are naturally arranged in a hierarchy, an appealing approach for coping with scarcity of instances is that of transfer learning using a hierarchical Bayes framework. As fully Bayesian computations can be difficult and computationally demanding, it is often desirable to use posterior point estimates that facilitate (relatively) efficient prediction. However, the hierarchical Bayes framework does not always lend itself naturally to this maximum aposteriori goal. In this work we propose an undirected reformulation of hierarchical Bayes that relies on priors in the form of similarity measures. We introduce the notion of \"degree of transfer\" weights on components of these similarity measures, and show how they can be automatically learned within a joint probabilistic framework. Importantly, our reformulation results in a convex objective for many learning problems, thus facilitating optimal posterior point estimation using standard optimization techniques. In addition, we no longer require proper priors, allowing for flexible and straightforward specification of joint distributions over transfer hierarchies. We show that our framework is effective for learning models that are part of transfer hierarchies for two real-life tasks: object shape modeling using Gaussian density estimation and document classification.", "source": "arxiv/ml"}
{"id": "arxiv:1658", "title": "Latent Topic Models for Hypertext", "text": "Latent topic models have been successfully applied as an unsupervised topic discovery technique in large document collections. With the proliferation of hypertext document collection such as the Internet, there has also been great interest in extending these approaches to hypertext [6, 9]. These approaches typically model links in an analogous fashion to how they model words - the document-link co-occurrence matrix is modeled in the same way that the document-word co-occurrence matrix is modeled in standard topic models. In this paper we present a probabilistic generative model for hypertext document collections that explicitly models the generation of links. Specifically, links from a word w to a document d depend directly on how frequent the topic of w is in d, in addition to the in-degree of d. We show how to perform EM learning on this model efficiently. By not modeling links as analogous to words, we end up using far fewer free parameters and obtain better link prediction results.", "source": "arxiv/ml"}
{"id": "arxiv:1659", "title": "Multi-View Learning over Structured and Non-Identical Outputs", "text": "In many machine learning problems, labeled training data is limited but unlabeled data is ample. Some of these problems have instances that can be factored into multiple views, each of which is nearly sufficent in determining the correct labels. In this paper we present a new algorithm for probabilistic multi-view learning which uses the idea of stochastic agreement between views as regularization. Our algorithm works on structured and unstructured problems and easily generalizes to partial agreement scenarios. For the full agreement case, our algorithm minimizes the Bhattacharyya distance between the models of each view, and performs better than CoBoosting and two-view Perceptron on several flat and structured classification problems.", "source": "arxiv/ml"}
{"id": "arxiv:1660", "title": "Constrained Approximate Maximum Entropy Learning of Markov Random Fields", "text": "Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with approximate methods such as loopy belief propagation (LBP) can suffer from poor convergence. In this paper, we provide a different approach for combining MRF learning and Bethe approximation. We consider the dual of maximum likelihood Markov network learning - maximizing entropy with moment matching constraints - and then approximate both the objective and the constraints in the resulting optimization problem. Unlike previous work along these lines (Teh & Welling, 2003), our formulation allows parameter sharing between features in a general log-linear model, parameter regularization and conditional training. We show that piecewise training (Sutton & McCallum, 2005) is a very restricted special case of this formulation. We study two optimization strategies: one based on a single convex approximation and one that uses repeated convex approximations. We show results on several real-world networks that demonstrate that these algorithms can significantly outperform learning with loopy and piecewise. Our results also provide a framework for analyzing the trade-offs of different relaxations of the entropy objective and of the constraints.", "source": "arxiv/ml"}
{"id": "arxiv:1661", "title": "Cumulative distribution networks and the derivative-sum-product algorithm", "text": "We introduce a new type of graphical model called a \"cumulative distribution network\" (CDN), which expresses a joint cumulative distribution as a product of local functions. Each local function can be viewed as providing evidence about possible orderings, or rankings, of variables. Interestingly, we find that the conditional independence properties of CDNs are quite different from other graphical models. We also describe a messagepassing algorithm that efficiently computes conditional cumulative distributions. Due to the unique independence properties of the CDN, these messages do not in general have a one-to-one correspondence with messages exchanged in standard algorithms, such as belief propagation. We demonstrate the application of CDNs for structured ranking learning using a previously-studied multi-player gaming dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1662", "title": "Causal discovery of linear acyclic models with arbitrary distributions", "text": "An important task in data analysis is the discovery of causal relationships between observed variables. For continuous-valued data, linear acyclic causal models are commonly used to model the data-generating process, and the inference of such models is a well-studied problem. However, existing methods have significant limitations. Methods based on conditional independencies (Spirtes et al. 1993; Pearl 2000) cannot distinguish between independence-equivalent models, whereas approaches purely based on Independent Component Analysis (Shimizu et al. 2006) are inapplicable to data which is partially Gaussian. In this paper, we generalize and combine the two approaches, to yield a method able to learn the model structure in many cases for which the previous methods provide answers that are either incorrect or are not as informative as possible. We give exact graphical conditions for when two distinct models represent the same family of distributions, and empirically demonstrate the power of our method through thorough simulations.", "source": "arxiv/ml"}
{"id": "arxiv:1663", "title": "Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies", "text": "Inference problems in graphical models can be represented as a constrained optimization of a free energy function. It is known that when the Bethe free energy is used, the fixedpoints of the belief propagation (BP) algorithm correspond to the local minima of the free energy. However BP fails to converge in many cases of interest. Moreover, the Bethe free energy is non-convex for graphical models with cycles thus introducing great difficulty in deriving efficient algorithms for finding local minima of the free energy for general graphs. In this paper we introduce two efficient BP-like algorithms, one sequential and the other parallel, that are guaranteed to converge to the global minimum, for any graph, over the class of energies known as \"convex free energies\". In addition, we propose an efficient heuristic for setting the parameters of the convex free energy based on the structure of the graph.", "source": "arxiv/ml"}
{"id": "arxiv:1664", "title": "Bayesian Out-Trees", "text": "A Bayesian treatment of latent directed graph structure for non-iid data is provided where each child datum is sampled with a directed conditional dependence on a single unknown parent datum. The latent graph structure is assumed to lie in the family of directed out-tree graphs which leads to efficient Bayesian inference. The latent likelihood of the data and its gradients are computable in closed form via Tutte's directed matrix tree theorem using determinants and inverses of the out-Laplacian. This novel likelihood subsumes iid likelihood, is exchangeable and yields efficient unsupervised and semi-supervised learning algorithms. In addition to handling taxonomy and phylogenetic datasets the out-tree assumption performs surprisingly well as a semi-parametric density estimator on standard iid datasets. Experiments with unsupervised and semisupervised learning are shown on various UCI and taxonomy datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1665", "title": "Estimation and Clustering with Infinite Rankings", "text": "This paper presents a natural extension of stagewise ranking to the the case of infinitely many items. We introduce the infinite generalized Mallows model (IGM), describe its properties and give procedures to estimate it from data. For estimation of multimodal distributions we introduce the Exponential-Blurring-Mean-Shift nonparametric clustering algorithm. The experiments highlight the properties of the new model and demonstrate that infinite models can be simple, elegant and practical.", "source": "arxiv/ml"}
{"id": "arxiv:1666", "title": "Small Sample Inference for Generalization Error in Classification Using the CUD Bound", "text": "Confidence measures for the generalization error are crucial when small training samples are used to construct classifiers. A common approach is to estimate the generalization error by resampling and then assume the resampled estimator follows a known distribution to form a confidence set [Kohavi 1995, Martin 1996,Yang 2006]. Alternatively, one might bootstrap the resampled estimator of the generalization error to form a confidence set. Unfortunately, these methods do not reliably provide sets of the desired confidence. The poor performance appears to be due to the lack of smoothness of the generalization error as a function of the learned classifier. This results in a non-normal distribution of the estimated generalization error. We construct a confidence set for the generalization error by use of a smooth upper bound on the deviation between the resampled estimate and generalization error. The confidence set is formed by bootstrapping this upper bound. In cases in which the approximation class for the classifier can be represented as a parametric additive model, we provide a computationally efficient algorithm. This method exhibits superior performance across a series of test and simulated data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1667", "title": "Learning Hidden Markov Models for Regression using Path Aggregation", "text": "We consider the task of learning mappings from sequential data to real-valued responses. We present and evaluate an approach to learning a type of hidden Markov model (HMM) for regression. The learning process involves inferring the structure and parameters of a conventional HMM, while simultaneously learning a regression model that maps features that characterize paths through the model to continuous responses. Our results, in both synthetic and biological domains, demonstrate the value of jointly learning the two components of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:1668", "title": "The Phylogenetic Indian Buffet Process: A Non-Exchangeable Nonparametric Prior for Latent Features", "text": "Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-of-words models for documents), exchangeability is sometimes assumed simply for computational reasons; non-exchangeable models might be a better choice for applications based on subject matter. Drawing on ideas from graphical models and phylogenetics, we describe a non-exchangeable prior for a class of nonparametric latent feature models that is nearly as efficient computationally as its exchangeable counterpart. Our model is applicable to the general setting in which the dependencies between objects can be expressed using a tree, where edge lengths indicate the strength of relationships. We demonstrate an application to modeling probabilistic choice.", "source": "arxiv/ml"}
{"id": "arxiv:1669", "title": "Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping", "text": "We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available after each interaction with the world. This paper develops an explicitly model-based approach extending the Dyna architecture to linear function approximation. Dynastyle planning proceeds by generating imaginary experience from the world model and then applying model-free reinforcement learning algorithms to the imagined state transitions. Our main results are to prove that linear Dyna-style planning converges to a unique solution independent of the generating distribution, under natural conditions. In the policy evaluation setting, we prove that the limit point is the least-squares (LSTD) solution. An implication of our results is that prioritized-sweeping can be soundly extended to the linear approximation case, backing up to preceding features rather than to preceding states. We introduce two versions of prioritized sweeping with linear Dyna and briefly illustrate their performance empirically on the Mountain Car and Boyan Chain problems.", "source": "arxiv/ml"}
{"id": "arxiv:1670", "title": "Learning the Bayesian Network Structure: Dirichlet Prior versus Data", "text": "In the Bayesian approach to structure learning of graphical models, the equivalent sample size (ESS) in the Dirichlet prior over the model parameters was recently shown to have an important effect on the maximum-a-posteriori estimate of the Bayesian network structure. In our first contribution, we theoretically analyze the case of large ESS-values, which complements previous work: among other results, we find that the presence of an edge in a Bayesian network is favoured over its absence even if both the Dirichlet prior and the data imply independence, as long as the conditional empirical distribution is notably different from uniform. In our second contribution, we focus on realistic ESS-values, and provide an analytical approximation to the \"optimal\" ESS-value in a predictive sense (its accuracy is also validated experimentally): this approximation provides an understanding as to which properties of the data have the main effect determining the \"optimal\" ESS-value.", "source": "arxiv/ml"}
{"id": "arxiv:1671", "title": "Modelling local and global phenomena with sparse Gaussian processes", "text": "Much recent work has concerned sparse approximations to speed up the Gaussian process regression from the unfavorable O(n3) scaling in computational time to O(nm2). Thus far, work has concentrated on models with one covariance function. However, in many practical situations additive models with multiple covariance functions may perform better, since the data may contain both long and short length-scale phenomena. The long length-scales can be captured with global sparse approximations, such as fully independent conditional (FIC), and the short length-scales can be modeled naturally by covariance functions with compact support (CS). CS covariance functions lead to naturally sparse covariance matrices, which are computationally cheaper to handle than full covariance matrices. In this paper, we propose a new sparse Gaussian process model with two additive components: FIC for the long length-scales and CS covariance function for the short length-scales. We give theoretical and experimental results and show that under certain conditions the proposed model has the same computational complexity as FIC. We also compare the model performance of the proposed model to additive models approximated by fully and partially independent conditional (PIC). We use real data sets and show that our model outperforms FIC and PIC approximations for data sets with two additive phenomena.", "source": "arxiv/ml"}
{"id": "arxiv:1672", "title": "Flexible Priors for Exemplar-based Clustering", "text": "Exemplar-based clustering methods have been shown to produce state-of-the-art results on a number of synthetic and real-world clustering problems. They are appealing because they offer computational benefits over latent-mean models and can handle arbitrary pairwise similarity measures between data points. However, when trying to recover underlying structure in clustering problems, tailored similarity measures are often not enough; we also desire control over the distribution of cluster sizes. Priors such as Dirichlet process priors allow the number of clusters to be unspecified while expressing priors over data partitions. To our knowledge, they have not been applied to exemplar-based models. We show how to incorporate priors, including Dirichlet process priors, into the recently introduced affinity propagation algorithm. We develop an efficient maxproduct belief propagation algorithm for our new model and demonstrate experimentally how the expanded range of clustering priors allows us to better recover true clusterings in situations where we have some information about the generating process.", "source": "arxiv/ml"}
{"id": "arxiv:1673", "title": "Hybrid Variational/Gibbs Collapsed Inference in Topic Models", "text": "Variational Bayesian inference and (collapsed) Gibbs sampling are the two important classes of inference algorithms for Bayesian networks. Both have their advantages and disadvantages: collapsed Gibbs sampling is unbiased but is also inefficient for large count values and requires averaging over many samples to reduce variance. On the other hand, variational Bayesian inference is efficient and accurate for large count values but suffers from bias for small counts. We propose a hybrid algorithm that combines the best of both worlds: it samples very small counts and applies variational updates to large counts. This hybridization is shown to significantly improve testset perplexity relative to variational inference at no computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:1674", "title": "Continuous Time Dynamic Topic Models", "text": "In this paper, we develop the continuous time dynamic topic model (cDTM). The cDTM is a dynamic topic model that uses Brownian motion to model the latent topics through a sequential collection of documents, where a \"topic\" is a pattern of word use that we expect to evolve over the course of the collection. We derive an efficient variational approximate inference algorithm that takes advantage of the sparsity of observations in text, a property that lets us easily handle many time points. In contrast to the cDTM, the original discrete-time dynamic topic model (dDTM) requires that time be discretized. Moreover, the complexity of variational inference for the dDTM grows quickly as time granularity increases, a drawback which limits fine-grained discretization. We demonstrate the cDTM on two news corpora, reporting both predictive perplexity and the novel task of time stamp prediction.", "source": "arxiv/ml"}
{"id": "arxiv:1675", "title": "Simple Regret Optimization in Online Planning for Markov Decision Processes", "text": "We consider online planning in Markov decision processes (MDPs). In online planning, the agent focuses on its current state only, deliberates about the set of possible policies from that state onwards and, when interrupted, uses the outcome of that exploratory deliberation to choose what action to perform next. The performance of algorithms for online planning is assessed in terms of simple regret, which is the agent's expected performance loss when the chosen action, rather than an optimal one, is followed. To date, state-of-the-art algorithms for online planning in general MDPs are either best effort, or guarantee only polynomial-rate reduction of simple regret over time. Here we introduce a new Monte-Carlo tree search algorithm, BRUE, that guarantees exponential-rate reduction of simple regret and error probability. This algorithm is based on a simple yet non-standard state-space sampling scheme, MCTS2e, in which different parts of each sample are dedicated to different exploratory objectives. Our empirical evaluation shows that BRUE not only provides superior performance guarantees, but is also very effective in practice and favorably compares to state-of-the-art. We then extend BRUE with a variant of \"learning by forgetting.\" The resulting set of algorithms, BRUE(alpha), generalizes BRUE, improves the exponential factor in the upper bound on its reduction rate, and exhibits even more attractive empirical performance.", "source": "arxiv/ml"}
{"id": "arxiv:1676", "title": "A Novel Approach for Protein Structure Prediction", "text": "The idea of this project is to study the protein structure and sequence relationship using the hidden markov model and artificial neural network. In this context we have assumed two hidden markov models. In first model we have taken protein secondary structures as hidden and protein sequences as observed. In second model we have taken protein sequences as hidden and protein structures as observed. The efficiencies for both the hidden markov models have been calculated. The results show that the efficiencies of first model is greater that the second one .These efficiencies are cross validated using artificial neural network. This signifies the importance of protein secondary structures as the main hidden controlling factors due to which we observe a particular amino acid sequence. This also signifies that protein secondary structure is more conserved in comparison to amino acid sequence.", "source": "arxiv/ml"}
{"id": "arxiv:1677", "title": "Decentralized Learning for Multi-player Multi-armed Bandits", "text": "We consider the problem of distributed online learning with multiple players in multi-armed bandits (MAB) models. Each player can pick among multiple arms. When a player picks an arm, it gets a reward. We consider both i.i.d. reward model and Markovian reward model. In the i.i.d. model each arm is modelled as an i.i.d. process with an unknown distribution with an unknown mean. In the Markovian model, each arm is modelled as a finite, irreducible, aperiodic and reversible Markov chain with an unknown probability transition matrix and stationary distribution. The arms give different rewards to different players. If two players pick the same arm, there is a \"collision\", and neither of them get any reward. There is no dedicated control channel for coordination or communication among the players. Any other communication between the users is costly and will add to the regret. We propose an online index-based distributed learning policy called ${\\tt dUCB_4}$ algorithm that trades off \\textit{exploration v. exploitation} in the right way, and achieves expected regret that grows at most as near-$O(\\log^2 T)$. The motivation comes from opportunistic spectrum access by multiple secondary users in cognitive radio networks wherein they must pick among various wireless channels that look different to different users. This is the first distributed learning algorithm for multi-player MABs to the best of our knowledge.", "source": "arxiv/ml"}
{"id": "arxiv:1678", "title": "Unsupervised adaptation of brain machine interface decoders", "text": "The performance of neural decoders can degrade over time due to nonstationarities in the relationship between neuronal activity and behavior. In this case, brain-machine interfaces (BMI) require adaptation of their decoders to maintain high performance across time. One way to achieve this is by use of periodical calibration phases, during which the BMI system (or an external human demonstrator) instructs the user to perform certain movements or behaviors. This approach has two disadvantages: (i) calibration phases interrupt the autonomous operation of the BMI and (ii) between two calibration phases the BMI performance might not be stable but continuously decrease. A better alternative would be that the BMI decoder is able to continuously adapt in an unsupervised manner during autonomous BMI operation, i.e. without knowing the movement intentions of the user. In the present article, we present an efficient method for such unsupervised training of BMI systems for continuous movement control. The proposed method utilizes a cost function derived from neuronal recordings, which guides a learning algorithm to evaluate the decoding parameters. We verify the performance of our adaptive method by simulating a BMI user with an optimal feedback control model and its interaction with our adaptive BMI decoder. The simulation results show that the cost function and the algorithm yield fast and precise trajectories towards targets at random orientations on a 2-dimensional computer screen. For initially unknown and non-stationary tuning parameters, our unsupervised method is still able to generate precise trajectories and to keep its performance stable in the long term. The algorithm can optionally work also with neuronal error signals instead or in conjunction with the proposed unsupervised adaptation.", "source": "arxiv/ml"}
{"id": "arxiv:1679", "title": "Learning the Structure and Parameters of Large-Population Graphical Games from Behavioral Data", "text": "We consider learning, from strictly behavioral data, the structure and parameters of linear influence games (LIGs), a class of parametric graphical games introduced by Irfan and Ortiz (2014). LIGs facilitate causal strategic inference (CSI): Making inferences from causal interventions on stable behavior in strategic settings. Applications include the identification of the most influential individuals in large (social) networks. Such tasks can also support policy-making analysis. Motivated by the computational work on LIGs, we cast the learning problem as maximum-likelihood estimation (MLE) of a generative model defined by pure-strategy Nash equilibria (PSNE). Our simple formulation uncovers the fundamental interplay between goodness-of-fit and model complexity: good models capture equilibrium behavior within the data while controlling the true number of equilibria, including those unobserved. We provide a generalization bound establishing the sample complexity for MLE in our framework. We propose several algorithms including convex loss minimization (CLM) and sigmoidal approximations. We prove that the number of exact PSNE in LIGs is small, with high probability; thus, CLM is sound. We illustrate our approach on synthetic data and real-world U.S. congressional voting records. We briefly discuss our learning framework's generality and potential applicability to general graphical games.", "source": "arxiv/ml"}
{"id": "arxiv:1680", "title": "How important are Deformable Parts in the Deformable Parts Model?", "text": "The main stated contribution of the Deformable Parts Model (DPM) detector of Felzenszwalb et al. (over the Histogram-of-Oriented-Gradients approach of Dalal and Triggs) is the use of deformable parts. A secondary contribution is the latent discriminative learning. Tertiary is the use of multiple components. A common belief in the vision community (including ours, before this study) is that their ordering of contributions reflects the performance of detector in practice. However, what we have experimentally found is that the ordering of importance might actually be the reverse. First, we show that by increasing the number of components, and switching the initialization step from their aspect-ratio, left-right flipping heuristics to appearance-based clustering, considerable improvement in performance is obtained. But more intriguingly, we show that with these new components, the part deformations can now be completely switched off, yet obtaining results that are almost on par with the original DPM detector. Finally, we also show initial results for using multiple components on a different problem -- scene classification, suggesting that this idea might have wider applications in addition to object detection.", "source": "arxiv/ml"}
{"id": "arxiv:1681", "title": "Constraint-free Graphical Model with Fast Learning Algorithm", "text": "In this paper, we propose a simple, versatile model for learning the structure and parameters of multivariate distributions from a data set. Learning a Markov network from a given data set is not a simple problem, because Markov networks rigorously represent Markov properties, and this rigor imposes complex constraints on the design of the networks. Our proposed model removes these constraints, acquiring important aspects from the information geometry. The proposed parameter- and structure-learning algorithms are simple to execute as they are based solely on local computation at each node. Experiments demonstrate that our algorithms work appropriately.", "source": "arxiv/ml"}
{"id": "arxiv:1682", "title": "DANCo: Dimensionality from Angle and Norm Concentration", "text": "In the last decades the estimation of the intrinsic dimensionality of a dataset has gained considerable importance. Despite the great deal of research work devoted to this task, most of the proposed solutions prove to be unreliable when the intrinsic dimensionality of the input dataset is high and the manifold where the points lie is nonlinearly embedded in a higher dimensional space. In this paper we propose a novel robust intrinsic dimensionality estimator that exploits the twofold complementary information conveyed both by the normalized nearest neighbor distances and by the angles computed on couples of neighboring points, providing also closed-forms for the Kullback-Leibler divergences of the respective distributions. Experiments performed on both synthetic and real datasets highlight the robustness and the effectiveness of the proposed algorithm when compared to state of the art methodologies.", "source": "arxiv/ml"}
{"id": "arxiv:1683", "title": "A Linear Approximation to the chi^2 Kernel with Geometric Convergence", "text": "We propose a new analytical approximation to the $\\chi^2$ kernel that converges geometrically. The analytical approximation is derived with elementary methods and adapts to the input distribution for optimal convergence rate. Experiments show the new approximation leads to improved performance in image classification and semantic segmentation tasks using a random Fourier feature approximation of the $\\exp-\\chi^2$ kernel. Besides, out-of-core principal component analysis (PCA) methods are introduced to reduce the dimensionality of the approximation and achieve better performance at the expense of only an additional constant factor to the time complexity. Moreover, when PCA is performed jointly on the training and unlabeled testing data, further performance improvements can be obtained. Experiments conducted on the PASCAL VOC 2010 segmentation and the ImageNet ILSVRC 2010 datasets show statistically significant improvements over alternative approximation methods.", "source": "arxiv/ml"}
{"id": "arxiv:1684", "title": "ConeRANK: Ranking as Learning Generalized Inequalities", "text": "We propose a new data mining approach in ranking documents based on the concept of cone-based generalized inequalities between vectors. A partial ordering between two vectors is made with respect to a proper cone and thus learning the preferences is formulated as learning proper cones. A pairwise learning-to-rank algorithm (ConeRank) is proposed to learn a non-negative subspace, formulated as a polyhedral cone, over document-pair differences. The algorithm is regularized by controlling the `volume' of the cone. The experimental studies on the latest and largest ranking dataset LETOR 4.0 shows that ConeRank is competitive against other recent ranking approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1685", "title": "Clustered Bandits", "text": "We consider a multi-armed bandit setting that is inspired by real-world applications in e-commerce. In our setting, there are a few types of users, each with a specific response to the different arms. When a user enters the system, his type is unknown to the decision maker. The decision maker can either treat each user separately ignoring the previously observed users, or can attempt to take advantage of knowing that only few types exist and cluster the users according to their response to the arms. We devise algorithms that combine the usual exploration-exploitation tradeoff with clustering of users and demonstrate the value of clustering. In the process of developing algorithms for the clustered setting, we propose and analyze simple algorithms for the setup where a decision maker knows that a user belongs to one of few types, but does not know which one.", "source": "arxiv/ml"}
{"id": "arxiv:1686", "title": "Parsimonious Mahalanobis Kernel for the Classification of High Dimensional Data", "text": "The classification of high dimensional data with kernel methods is considered in this article. Exploit- ing the emptiness property of high dimensional spaces, a kernel based on the Mahalanobis distance is proposed. The computation of the Mahalanobis distance requires the inversion of a covariance matrix. In high dimensional spaces, the estimated covariance matrix is ill-conditioned and its inversion is unstable or impossible. Using a parsimonious statistical model, namely the High Dimensional Discriminant Analysis model, the specific signal and noise subspaces are estimated for each considered class making the inverse of the class specific covariance matrix explicit and stable, leading to the definition of a parsimonious Mahalanobis kernel. A SVM based framework is used for selecting the hyperparameters of the parsimonious Mahalanobis kernel by optimizing the so-called radius-margin bound. Experimental results on three high dimensional data sets show that the proposed kernel is suitable for classifying high dimensional data, providing better classification accuracies than the conventional Gaussian kernel.", "source": "arxiv/ml"}
{"id": "arxiv:1687", "title": "Residual Component Analysis: Generalising PCA for more flexible inference in linear-Gaussian models", "text": "Probabilistic principal component analysis (PPCA) seeks a low dimensional representation of a data set in the presence of independent spherical Gaussian noise. The maximum likelihood solution for the model is an eigenvalue problem on the sample covariance matrix. In this paper we consider the situation where the data variance is already partially explained by other actors, for example sparse conditional dependencies between the covariates, or temporal correlations leaving some residual variance. We decompose the residual variance into its components through a generalised eigenvalue problem, which we call residual component analysis (RCA). We explore a range of new algorithms that arise from the framework, including one that factorises the covariance of a Gaussian density into a low-rank and a sparse-inverse component. We illustrate the ideas on the recovery of a protein-signaling network, a gene expression time-series data set and the recovery of the human skeleton from motion capture 3-D cloud data.", "source": "arxiv/ml"}
{"id": "arxiv:1688", "title": "A Unified Robust Classification Model", "text": "A wide variety of machine learning algorithms such as support vector machine (SVM), minimax probability machine (MPM), and Fisher discriminant analysis (FDA), exist for binary classification. The purpose of this paper is to provide a unified classification model that includes the above models through a robust optimization approach. This unified model has several benefits. One is that the extensions and improvements intended for SVM become applicable to MPM and FDA, and vice versa. Another benefit is to provide theoretical results to above learning methods at once by dealing with the unified model. We give a statistical interpretation of the unified classification model and propose a non-convex optimization algorithm that can be applied to non-convex variants of existing learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:1689", "title": "Bayesian Nonexhaustive Learning for Online Discovery and Modeling of Emerging Classes", "text": "We present a framework for online inference in the presence of a nonexhaustively defined set of classes that incorporates supervised classification with class discovery and modeling. A Dirichlet process prior (DPP) model defined over class distributions ensures that both known and unknown class distributions originate according to a common base distribution. In an attempt to automatically discover potentially interesting class formations, the prior model is coupled with a suitably chosen data model, and sequential Monte Carlo sampling is used to perform online inference. Our research is driven by a biodetection application, where a new class of pathogen may suddenly appear, and the rapid increase in the number of samples originating from this class indicates the onset of an outbreak.", "source": "arxiv/ml"}
{"id": "arxiv:1690", "title": "Convex Multitask Learning with Flexible Task Clusters", "text": "Traditionally, multitask learning (MTL) assumes that all the tasks are related. This can lead to negative transfer when tasks are indeed incoherent. Recently, a number of approaches have been proposed that alleviate this problem by discovering the underlying task clusters or relationships. However, they are limited to modeling these relationships at the task level, which may be restrictive in some applications. In this paper, we propose a novel MTL formulation that captures task relationships at the feature-level. Depending on the interactions among tasks and features, the proposed method construct different task clusters for different features, without even the need of pre-specifying the number of clusters. Computationally, the proposed formulation is strongly convex, and can be efficiently solved by accelerated proximal methods. Experiments are performed on a number of synthetic and real-world data sets. Under various degrees of task relationships, the accuracy of the proposed method is consistently among the best. Moreover, the feature-specific task clusters obtained agree with the known/plausible task structures of the data.", "source": "arxiv/ml"}
{"id": "arxiv:1691", "title": "Quasi-Newton Methods: A New Direction", "text": "Four decades after their invention, quasi-Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.", "source": "arxiv/ml"}
{"id": "arxiv:1692", "title": "Learning the Experts for Online Sequence Prediction", "text": "Online sequence prediction is the problem of predicting the next element of a sequence given previous elements. This problem has been extensively studied in the context of individual sequence prediction, where no prior assumptions are made on the origin of the sequence. Individual sequence prediction algorithms work quite well for long sequences, where the algorithm has enough time to learn the temporal structure of the sequence. However, they might give poor predictions for short sequences. A possible remedy is to rely on the general model of prediction with expert advice, where the learner has access to a set of $r$ experts, each of which makes its own predictions on the sequence. It is well known that it is possible to predict almost as well as the best expert if the sequence length is order of $\\log(r)$. But, without firm prior knowledge on the problem, it is not clear how to choose a small set of {\\em good} experts. In this paper we describe and analyze a new algorithm that learns a good set of experts using a training set of previously observed sequences. We demonstrate the merits of our approach by applying it on the task of click prediction on the web.", "source": "arxiv/ml"}
{"id": "arxiv:1693", "title": "TrueLabel + Confusions: A Spectrum of Probabilistic Models in Analyzing Multiple Ratings", "text": "This paper revisits the problem of analyzing multiple ratings given by different judges. Different from previous work that focuses on distilling the true labels from noisy crowdsourcing ratings, we emphasize gaining diagnostic insights into our in-house well-trained judges. We generalize the well-known DawidSkene model (Dawid & Skene, 1979) to a spectrum of probabilistic models under the same \"TrueLabel + Confusion\" paradigm, and show that our proposed hierarchical Bayesian model, called HybridConfusion, consistently outperforms DawidSkene on both synthetic and real-world data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1694", "title": "Distributed Tree Kernels", "text": "In this paper, we propose the distributed tree kernels (DTK) as a novel method to reduce time and space complexity of tree kernels. Using a linear complexity algorithm to compute vectors for trees, we embed feature spaces of tree fragments in low-dimensional spaces where the kernel computation is directly done with dot product. We show that DTKs are faster, correlate with tree kernels, and obtain a statistically similar performance in two natural language processing tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1695", "title": "A Hybrid Algorithm for Convex Semidefinite Optimization", "text": "We present a hybrid algorithm for optimizing a convex, smooth function over the cone of positive semidefinite matrices. Our algorithm converges to the global optimal solution and can be used to solve general large-scale semidefinite programs and hence can be readily applied to a variety of machine learning problems. We show experimental results on three machine learning problems (matrix completion, metric learning, and sparse PCA) . Our approach outperforms state-of-the-art algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1696", "title": "On multi-view feature learning", "text": "Sparse coding is a common approach to learning local features for object recognition. Recently, there has been an increasing interest in learning features from spatio-temporal, binocular, or other multi-observation data, where the goal is to encode the relationship between images rather than the content of a single image. We provide an analysis of multi-view feature learning, which shows that hidden variables encode transformations by detecting rotation angles in the eigenspaces shared among multiple image warps. Our analysis helps explain recent experimental results showing that transformation-specific features emerge when training complex cell models on videos. Our analysis also shows that transformation-invariant features can emerge as a by-product of learning representations of transformations.", "source": "arxiv/ml"}
{"id": "arxiv:1697", "title": "Manifold Relevance Determination", "text": "In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private information from multiple views of the data. In contrast to previous approaches, we introduce a relaxation to the discrete segmentation and allow for a \"softly\" shared latent space. Further, Bayesian techniques allow us to automatically estimate the dimensionality of the latent spaces. The model is capable of capturing structure underlying extremely high dimensional spaces. This is illustrated by modelling unprocessed images with tenths of thousands of pixels. This also allows us to directly generate novel images from the trained model by sampling from the discovered latent spaces. We also demonstrate the model by prediction of human pose in an ambiguous setting. Our Bayesian framework allows us to perform disambiguation in a principled manner by including latent space priors which incorporate the dynamic nature of the data.", "source": "arxiv/ml"}
{"id": "arxiv:1698", "title": "A Convex Feature Learning Formulation for Latent Task Structure Discovery", "text": "This paper considers the multi-task learning problem and in the setting where some relevant features could be shared across few related tasks. Most of the existing methods assume the extent to which the given tasks are related or share a common feature space to be known apriori. In real-world applications however, it is desirable to automatically discover the groups of related tasks that share a feature space. In this paper we aim at searching the exponentially large space of all possible groups of tasks that may share a feature space. The main contribution is a convex formulation that employs a graph-based regularizer and simultaneously discovers few groups of related tasks, having close-by task parameters, as well as the feature space shared within each group. The regularizer encodes an important structure among the groups of tasks leading to an efficient algorithm for solving it: if there is no feature space under which a group of tasks has close-by task parameters, then there does not exist such a feature space for any of its supersets. An efficient active set algorithm that exploits this simplification and performs a clever search in the exponentially large space is presented. The algorithm is guaranteed to solve the proposed formulation (within some precision) in a time polynomial in the number of groups of related tasks discovered. Empirical results on benchmark datasets show that the proposed formulation achieves good generalization and outperforms state-of-the-art multi-task learning algorithms in some cases.", "source": "arxiv/ml"}
{"id": "arxiv:1699", "title": "Exact Soft Confidence-Weighted Learning", "text": "In this paper, we propose a new Soft Confidence-Weighted (SCW) online learning scheme, which enables the conventional confidence-weighted learning method to handle non-separable cases. Unlike the previous confidence-weighted learning algorithms, the proposed soft confidence-weighted learning method enjoys all the four salient properties: (i) large margin training, (ii) confidence weighting, (iii) capability to handle non-separable data, and (iv) adaptive margin. Our experimental results show that the proposed SCW algorithms significantly outperform the original CW algorithm. When comparing with a variety of state-of-the-art algorithms (including AROW, NAROW and NHERD), we found that SCW generally achieves better or at least comparable predictive accuracy, but enjoys significant advantage of computational efficiency (i.e., smaller number of updates and lower time cost).", "source": "arxiv/ml"}
{"id": "arxiv:1700", "title": "Near-Optimal BRL using Optimistic Local Transitions", "text": "Model-based Bayesian Reinforcement Learning (BRL) allows a found formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work relies on heuristic algorithms. This paper introduces BOLT, a simple and (almost) deterministic heuristic algorithm for BRL which is optimistic about the transition function. We analyze BOLT's sample complexity, and show that under certain parameters, the algorithm is near-optimal in the Bayesian sense with high probability. Then, experimental results highlight the key differences of this method compared to previous work.", "source": "arxiv/ml"}
{"id": "arxiv:1701", "title": "Information-theoretic Semi-supervised Metric Learning via Entropy Regularization", "text": "We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize the entropy of that probability on labeled data and minimize it on unlabeled data following entropy regularization, which allows the supervised and unsupervised parts to be integrated in a natural and meaningful way. Furthermore, Seraph is regularized by encouraging a low-rank projection induced from the metric. The optimization of Seraph is solved efficiently and stably by an EM-like scheme with the analytical E-Step and convex M-Step. Experiments demonstrate that Seraph compares favorably with many well-known global and local metric learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:1702", "title": "Levy Measure Decompositions for the Beta and Gamma Processes", "text": "We develop new representations for the Levy measures of the beta and gamma processes. These representations are manifested in terms of an infinite sum of well-behaved (proper) beta and gamma distributions. Further, we demonstrate how these infinite sums may be truncated in practice, and explicitly characterize truncation errors. We also perform an analysis of the characteristics of posterior distributions, based on the proposed decompositions. The decompositions provide new insights into the beta and gamma processes (and their generalizations), and we demonstrate how the proposed representation unifies some properties of the two. This paper is meant to provide a rigorous foundation for and new perspectives on Levy processes, as these are of increasing importance in machine learning.", "source": "arxiv/ml"}
{"id": "arxiv:1703", "title": "A Hierarchical Dirichlet Process Model with Multiple Levels of Clustering for Human EEG Seizure Modeling", "text": "Driven by the multi-level structure of human intracranial electroencephalogram (iEEG) recordings of epileptic seizures, we introduce a new variant of a hierarchical Dirichlet Process---the multi-level clustering hierarchical Dirichlet Process (MLC-HDP)---that simultaneously clusters datasets on multiple levels. Our seizure dataset contains brain activity recorded in typically more than a hundred individual channels for each seizure of each patient. The MLC-HDP model clusters over channels-types, seizure-types, and patient-types simultaneously. We describe this model and its implementation in detail. We also present the results of a simulation study comparing the MLC-HDP to a similar model, the Nested Dirichlet Process and finally demonstrate the MLC-HDP's use in modeling seizures across multiple patients. We find the MLC-HDP's clustering to be comparable to independent human physician clusterings. To our knowledge, the MLC-HDP model is the first in the epilepsy literature capable of clustering seizures within and between patients.", "source": "arxiv/ml"}
{"id": "arxiv:1704", "title": "Continuous Inverse Optimal Control with Locally Optimal Examples", "text": "Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, and is suitable for large, continuous domains where even computing a full policy is impractical. By using a local approximation of the reward function, our method can also drop the assumption that the demonstrations are globally optimal, requiring only local optimality. This allows it to learn from examples that are unsuitable for prior methods.", "source": "arxiv/ml"}
{"id": "arxiv:1705", "title": "Compact Hyperplane Hashing with Bilinear Functions", "text": "Hyperplane hashing aims at rapidly searching nearest points to a hyperplane, and has shown practical impact in scaling up active learning with SVMs. Unfortunately, the existing randomized methods need long hash codes to achieve reasonable search accuracy and thus suffer from reduced search speed and large memory overhead. To this end, this paper proposes a novel hyperplane hashing technique which yields compact hash codes. The key idea is the bilinear form of the proposed hash functions, which leads to higher collision probability than the existing hyperplane hash functions when using random projections. To further increase the performance, we propose a learning based framework in which the bilinear functions are directly learned from the data. This results in short yet discriminative codes, and also boosts the search performance over the random projection based solutions. Large-scale active learning experiments carried out on two datasets with up to one million samples demonstrate the overall superiority of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:1706", "title": "Inductive Kernel Low-rank Decomposition with Priors: A Generalized Nystrom Method", "text": "Low-rank matrix decomposition has gained great popularity recently in scaling up kernel methods to large amounts of data. However, some limitations could prevent them from working effectively in certain domains. For example, many existing approaches are intrinsically unsupervised, which does not incorporate side information (e.g., class labels) to produce task specific decompositions; also, they typically work \"transductively\", i.e., the factorization does not generalize to new samples, so the complete factorization needs to be recomputed when new samples become available. To solve these problems, in this paper we propose an\"inductive\"-flavored method for low-rank kernel decomposition with priors. We achieve this by generalizing the Nystr\\\"om method in a novel way. On the one hand, our approach employs a highly flexible, nonparametric structure that allows us to generalize the low-rank factors to arbitrarily new samples; on the other hand, it has linear time and space complexities, which can be orders of magnitudes faster than existing approaches and renders great efficiency in learning a low-rank kernel decomposition. Empirical results demonstrate the efficacy and efficiency of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1707", "title": "Improved Information Gain Estimates for Decision Tree Induction", "text": "Ensembles of classification and regression trees remain popular machine learning methods because they define flexible non-parametric models that predict well and are computationally efficient both during training and testing. During induction of decision trees one aims to find predicates that are maximally informative about the prediction target. To select good predicates most approaches estimate an information-theoretic scoring function, the information gain, both for classification and regression problems. We point out that the common estimation procedures are biased and show that by replacing them with improved estimators of the discrete and the differential entropy we can obtain better decision trees. In effect our modifications yield improved predictive performance and are simple to implement in any decision tree code.", "source": "arxiv/ml"}
{"id": "arxiv:1708", "title": "Path Integral Policy Improvement with Covariance Matrix Adaptation", "text": "There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI2 as a member of the wider family of methods which share the concept of probability-weighted averaging to iteratively update parameters to optimize a cost function. We compare PI2 to other members of the same family - Cross-Entropy Methods and CMAES - at the conceptual level and in terms of performance. The comparison suggests the derivation of a novel algorithm which we call PI2-CMA for \"Path Integral Policy Improvement with Covariance Matrix Adaptation\". PI2-CMA's main advantage is that it determines the magnitude of the exploration noise automatically.", "source": "arxiv/ml"}
{"id": "arxiv:1709", "title": "A Graphical Model Formulation of Collaborative Filtering Neighbourhood Methods with Fast Maximum Entropy Training", "text": "Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of a user's rating on an item is then given by that rating of neighbouring items, weighted by their similarity. This paper presents a new neighbourhood approach which we call item fields, whereby an undirected graphical model is formed over the item graph. The resulting prediction rule is a simple generalization of the classical approaches, which takes into account non-local information in the graph, allowing its best results to be obtained when using drastically fewer edges than other neighbourhood approaches. A fast approximate maximum entropy training method based on the Bethe approximation is presented, which uses a simple gradient ascent procedure. When using precomputed sufficient statistics on the Movielens datasets, our method is faster than maximum likelihood approaches by two orders of magnitude.", "source": "arxiv/ml"}
{"id": "arxiv:1710", "title": "On the Size of the Online Kernel Sparsification Dictionary", "text": "We analyze the size of the dictionary constructed from online kernel sparsification, using a novel formula that expresses the expected determinant of the kernel Gram matrix in terms of the eigenvalues of the covariance operator. Using this formula, we are able to connect the cardinality of the dictionary with the eigen-decay of the covariance operator. In particular, we show that under certain technical conditions, the size of the dictionary will always grow sub-linearly in the number of data points, and, as a consequence, the kernel linear regressor constructed from the resulting dictionary is consistent.", "source": "arxiv/ml"}
{"id": "arxiv:1711", "title": "Robust Multiple Manifolds Structure Learning", "text": "We present a robust multiple manifolds structure learning (RMMSL) scheme to robustly estimate data structures under the multiple low intrinsic dimensional manifolds assumption. In the local learning stage, RMMSL efficiently estimates local tangent space by weighted low-rank matrix factorization. In the global learning stage, we propose a robust manifold clustering method based on local structure learning results. The proposed clustering method is designed to get the flattest manifolds clusters by introducing a novel curved-level similarity function. Our approach is evaluated and compared to state-of-the-art methods on synthetic data, handwritten digit images, human motion capture data and motorbike videos. We demonstrate the effectiveness of the proposed approach, which yields higher clustering accuracy, and produces promising results for challenging tasks of human motion segmentation and motion flow learning from videos.", "source": "arxiv/ml"}
{"id": "arxiv:1712", "title": "Optimizing F-measure: A Tale of Two Approaches", "text": "F-measures are popular performance metrics, particularly for tasks with imbalanced data sets. Algorithms for learning to maximize F-measures follow two approaches: the empirical utility maximization (EUM) approach learns a classifier having optimal performance on training data, while the decision-theoretic approach learns a probabilistic model and then predicts labels with maximum expected F-measure. In this paper, we investigate the theoretical justifications and connections for these two approaches, and we study the conditions under which one approach is preferable to the other using synthetic and real datasets. Given accurate models, our results suggest that the two approaches are asymptotically equivalent given large training and test sets. Nevertheless, empirically, the EUM approach appears to be more robust against model misspecification, and given a good model, the decision-theoretic approach appears to be better for handling rare classes and a common domain adaptation scenario.", "source": "arxiv/ml"}
{"id": "arxiv:1713", "title": "On-Line Portfolio Selection with Moving Average Reversion", "text": "On-line portfolio selection has attracted increasing interests in machine learning and AI communities recently. Empirical evidences show that stock's high and low prices are temporary and stock price relatives are likely to follow the mean reversion phenomenon. While the existing mean reversion strategies are shown to achieve good empirical performance on many real datasets, they often make the single-period mean reversion assumption, which is not always satisfied in some real datasets, leading to poor performance when the assumption does not hold. To overcome the limitation, this article proposes a multiple-period mean reversion, or so-called Moving Average Reversion (MAR), and a new on-line portfolio selection strategy named \"On-Line Moving Average Reversion\" (OLMAR), which exploits MAR by applying powerful online learning techniques. From our empirical results, we found that OLMAR can overcome the drawback of existing mean reversion algorithms and achieve significantly better results, especially on the datasets where the existing mean reversion algorithms failed. In addition to superior trading performance, OLMAR also runs extremely fast, further supporting its practical applicability to a wide range of applications.", "source": "arxiv/ml"}
{"id": "arxiv:1714", "title": "Convergence Rates of Biased Stochastic Optimization for Learning Sparse Ising Models", "text": "We study the convergence rate of stochastic optimization of exact (NP-hard) objectives, for which only biased estimates of the gradient are available. We motivate this problem in the context of learning the structure and parameters of Ising models. We first provide a convergence-rate analysis of deterministic errors for forward-backward splitting (FBS). We then extend our analysis to biased stochastic errors, by first characterizing a family of samplers and providing a high probability bound that allows understanding not only FBS, but also proximal gradient (PG) methods. We derive some interesting conclusions: FBS requires only a logarithmically increasing number of random samples in order to converge (although at a very low rate); the required number of random samples is the same for the deterministic and the biased stochastic setting for FBS and basic PG; accelerated PG is not guaranteed to converge in the biased stochastic setting.", "source": "arxiv/ml"}
{"id": "arxiv:1715", "title": "Robust PCA in High-dimension: A Deterministic Approach", "text": "We consider principal component analysis for contaminated data-set in the high dimensional regime, where the dimensionality of each observation is comparable or even more than the number of observations. We propose a deterministic high-dimensional robust PCA algorithm which inherits all theoretical properties of its randomized counterpart, i.e., it is tractable, robust to contaminated points, easily kernelizable, asymptotic consistent and achieves maximal robustness -- a breakdown point of 50%. More importantly, the proposed method exhibits significantly better computational efficiency, which makes it suitable for large-scale real applications.", "source": "arxiv/ml"}
{"id": "arxiv:1716", "title": "Multiple Kernel Learning from Noisy Labels by Stochastic Programming", "text": "We study the problem of multiple kernel learning from noisy labels. This is in contrast to most of the previous studies on multiple kernel learning that mainly focus on developing efficient algorithms and assume perfectly labeled training examples. Directly applying the existing multiple kernel learning algorithms to noisily labeled examples often leads to suboptimal performance due to the incorrect class assignments. We address this challenge by casting multiple kernel learning from noisy labels into a stochastic programming problem, and presenting a minimax formulation. We develop an efficient algorithm for solving the related convex-concave optimization problem with a fast convergence rate of $O(1/T)$ where $T$ is the number of iterations. Empirical studies on UCI data sets verify both the effectiveness of the proposed framework and the efficiency of the proposed optimization algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:1717", "title": "Efficient Decomposed Learning for Structured Prediction", "text": "Structured prediction is the cornerstone of several machine learning applications. Unfortunately, in structured prediction settings with expressive inter-variable interactions, exact inference-based learning algorithms, e.g. Structural SVM, are often intractable. We present a new way, Decomposed Learning (DecL), which performs efficient learning by restricting the inference step to a limited part of the structured spaces. We provide characterizations based on the structure, target parameters, and gold labels, under which DecL is equivalent to exact learning. We then show that in real world settings, where our theoretical assumptions may not completely hold, DecL-based algorithms are significantly more efficient and as accurate as exact learning.", "source": "arxiv/ml"}
{"id": "arxiv:1718", "title": "A Poisson convolution model for characterizing topical content with word frequency and exclusivity", "text": "An ongoing challenge in the analysis of document collections is how to summarize content in terms of a set of inferred themes that can be interpreted substantively in terms of topics. The current practice of parametrizing the themes in terms of most frequent words limits interpretability by ignoring the differential use of words across topics. We argue that words that are both common and exclusive to a theme are more effective at characterizing topical content. We consider a setting where professional editors have annotated documents to a collection of topic categories, organized into a tree, in which leaf-nodes correspond to the most specific topics. Each document is annotated to multiple categories, at different levels of the tree. We introduce a hierarchical Poisson convolution model to analyze annotated documents in this setting. The model leverages the structure among categories defined by professional editors to infer a clear semantic description for each topic in terms of words that are both frequent and exclusive. We carry out a large randomized experiment on Amazon Turk to demonstrate that topic summaries based on the FREX score are more interpretable than currently established frequency based summaries, and that the proposed model produces more efficient estimates of exclusivity than with currently models. We also develop a parallelized Hamiltonian Monte Carlo sampler that allows the inference to scale to millions of documents.", "source": "arxiv/ml"}
{"id": "arxiv:1719", "title": "A Complete Analysis of the l_1,p Group-Lasso", "text": "The Group-Lasso is a well-known tool for joint regularization in machine learning methods. While the l_{1,2} and the l_{1,\\infty} version have been studied in detail and efficient algorithms exist, there are still open questions regarding other l_{1,p} variants. We characterize conditions for solutions of the l_{1,p} Group-Lasso for all p-norms with 1 <= p <= \\infty, and we present a unified active set algorithm. For all p-norms, a highly efficient projected gradient algorithm is presented. This new algorithm enables us to compare the prediction performance of many variants of the Group-Lasso in a multi-task learning setting, where the aim is to solve many learning problems in parallel which are coupled via the Group-Lasso constraint. We conduct large-scale experiments on synthetic data and on two real-world data sets. In accordance with theoretical characterizations of the different norms we observe that the weak-coupling norms with p between 1.5 and 2 consistently outperform the strong-coupling norms with p >> 2.", "source": "arxiv/ml"}
{"id": "arxiv:1720", "title": "Fast Bounded Online Gradient Descent Algorithms for Scalable Kernel-Based Online Learning", "text": "Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable for applications with large-scale datasets. In this work, we study the problem of bounded kernel-based online learning that aims to constrain the number of support vectors by a predefined budget. Although several algorithms have been proposed in literature, they are neither computationally efficient due to their intensive budget maintenance strategy nor effective due to the use of simple Perceptron algorithm. To overcome these limitations, we propose a framework for bounded kernel-based online learning based on an online gradient descent approach. We propose two efficient algorithms of bounded online gradient descent (BOGD) for scalable kernel-based online learning: (i) BOGD by maintaining support vectors using uniform sampling, and (ii) BOGD++ by maintaining support vectors using non-uniform sampling. We present theoretical analysis of regret bound for both algorithms, and found promising empirical performance in terms of both efficacy and efficiency by comparing them to several well-known algorithms for bounded kernel-based online learning on large-scale datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1721", "title": "Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting", "text": "Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. Major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement learning agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of actions, states, and rewards tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1722", "title": "Deep Mixtures of Factor Analysers", "text": "An efficient way to learn deep density models that have many layers of latent variables is to learn one layer at a time using a model that has only one layer of latent variables. After learning each layer, samples from the posterior distributions for that layer are used as training data for learning the next layer. This approach is commonly used with Restricted Boltzmann Machines, which are undirected graphical models with a single hidden layer, but it can also be used with Mixtures of Factor Analysers (MFAs) which are directed graphical models. In this paper, we present a greedy layer-wise learning algorithm for Deep Mixtures of Factor Analysers (DMFAs). Even though a DMFA can be converted to an equivalent shallow MFA by multiplying together the factor loading matrices at different levels, learning and inference are much more efficient in a DMFA and the sharing of each lower-level factor loading matrix by many different higher level MFAs prevents overfitting. We demonstrate empirically that DMFAs learn better density models than both MFAs and two types of Restricted Boltzmann Machine on a wide variety of datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1723", "title": "Modeling Latent Variable Uncertainty for Loss-based Learning", "text": "We consider the problem of parameter estimation using weakly supervised datasets, where a training sample consists of the input and a partially specified annotation, which we refer to as the output. The missing information in the annotation is modeled using latent variables. Previous methods overburden a single distribution with two separate tasks: (i) modeling the uncertainty in the latent variables during training; and (ii) making accurate predictions for the output and the latent variables during testing. We propose a novel framework that separates the demands of the two tasks using two distributions: (i) a conditional distribution to model the uncertainty of the latent variables for a given input-output pair; and (ii) a delta distribution to predict the output and the latent variables for a given input. During learning, we encourage agreement between the two distributions by minimizing a loss-based dissimilarity coefficient. Our approach generalizes latent SVM in two important ways: (i) it models the uncertainty over latent variables instead of relying on a pointwise estimate; and (ii) it allows the use of loss functions that depend on latent variables, which greatly increases its applicability. We demonstrate the efficacy of our approach on two challenging problems---object detection and action detection---using publicly available datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1724", "title": "Learning to Identify Regular Expressions that Describe Email Campaigns", "text": "This paper addresses the problem of inferring a regular expression from a given set of strings that resembles, as closely as possible, the regular expression that a human expert would have written to identify the language. This is motivated by our goal of automating the task of postmasters of an email service who use regular expressions to describe and blacklist email spam campaigns. Training data contains batches of messages and corresponding regular expressions that an expert postmaster feels confident to blacklist. We model this task as a learning problem with structured output spaces and an appropriate loss function, derive a decoder and the resulting optimization problem, and a report on a case study conducted with an email service.", "source": "arxiv/ml"}
{"id": "arxiv:1725", "title": "Efficient Euclidean Projections onto the Intersection of Norm Balls", "text": "Using sparse-inducing norms to learn robust models has received increasing attention from many fields for its attractive properties. Projection-based methods have been widely applied to learning tasks constrained by such norms. As a key building block of these methods, an efficient operator for Euclidean projection onto the intersection of $\\ell_1$ and $\\ell_{1,q}$ norm balls $(q=2\\text{or}\\infty)$ is proposed in this paper. We prove that the projection can be reduced to finding the root of an auxiliary function which is piecewise smooth and monotonic. Hence, a bisection algorithm is sufficient to solve the problem. We show that the time complexity of our solution is $O(n+g\\log g)$ for $q=2$ and $O(n\\log n)$ for $q=\\infty$, where $n$ is the dimensionality of the vector to be projected and $g$ is the number of disjoint groups; we confirm this complexity by experimentation. Empirical study reveals that our method achieves significantly better performance than classical methods in terms of running time and memory usage. We further show that embedded with our efficient projection operator, projection-based algorithms can solve regression problems with composite norm constraints more efficiently than other methods and give superior accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:1726", "title": "Adaptive Regularization for Weight Matrices", "text": "Algorithms for learning distributions over weight-vectors, such as AROW were recently shown empirically to achieve state-of-the-art performance at various problems, with strong theoretical guaranties. Extending these algorithms to matrix models pose challenges since the number of free parameters in the covariance of the distribution scales as $n^4$ with the dimension $n$ of the matrix, and $n$ tends to be large in real applications. We describe, analyze and experiment with two new algorithms for learning distribution of matrix models. Our first algorithm maintains a diagonal covariance over the parameters and can handle large covariance matrices. The second algorithm factors the covariance to capture inter-features correlation while keeping the number of parameters linear in the size of the original matrix. We analyze both algorithms in the mistake bound model and show a superior precision performance of our approach over other algorithms in two tasks: retrieving similar images, and ranking similar documents. The factored algorithm is shown to attain faster convergence rate.", "source": "arxiv/ml"}
{"id": "arxiv:1727", "title": "Stability of matrix factorization for collaborative filtering", "text": "We study the stability vis a vis adversarial noise of matrix factorization algorithm for matrix completion. In particular, our results include: (I) we bound the gap between the solution matrix of the factorization method and the ground truth in terms of root mean square error; (II) we treat the matrix factorization as a subspace fitting problem and analyze the difference between the solution subspace and the ground truth; (III) we analyze the prediction error of individual users based on the subspace stability. We apply these results to the problem of collaborative filtering under manipulator attack, which leads to useful insights and guidelines for collaborative filtering system design.", "source": "arxiv/ml"}
{"id": "arxiv:1728", "title": "Total Variation and Euler's Elastica for Supervised Learning", "text": "In recent years, total variation (TV) and Euler's elastica (EE) have been successfully applied to image processing tasks such as denoising and inpainting. This paper investigates how to extend TV and EE to the supervised learning settings on high dimensional data. The supervised learning problem can be formulated as an energy functional minimization under Tikhonov regularization scheme, where the energy is composed of a squared loss and a total variation smoothing (or Euler's elastica smoothing). Its solution via variational principles leads to an Euler-Lagrange PDE. However, the PDE is always high-dimensional and cannot be directly solved by common methods. Instead, radial basis functions are utilized to approximate the target function, reducing the problem to finding the linear coefficients of basis functions. We apply the proposed methods to supervised learning tasks (including binary classification, multi-class classification, and regression) on benchmark data sets. Extensive experiments have demonstrated promising results of the proposed methods.", "source": "arxiv/ml"}
{"id": "arxiv:1729", "title": "Fast Computation of Subpath Kernel for Trees", "text": "The kernel method is a potential approach to analyzing structured data such as sequences, trees, and graphs; however, unordered trees have not been investigated extensively. Kimura et al. (2011) proposed a kernel function for unordered trees on the basis of their subpaths, which are vertical substructures of trees responsible for hierarchical information in them. Their kernel exhibits practically good performance in terms of accuracy and speed; however, linear-time computation is not guaranteed theoretically, unlike the case of the other unordered tree kernel proposed by Vishwanathan and Smola (2003). In this paper, we propose a theoretically guaranteed linear-time kernel computation algorithm that is practically fast, and we present an efficient prediction algorithm whose running time depends only on the size of the input tree. Experimental results show that the proposed algorithms are quite efficient in practice.", "source": "arxiv/ml"}
{"id": "arxiv:1730", "title": "Lightning Does Not Strike Twice: Robust MDPs with Coupled Uncertainty", "text": "We consider Markov decision processes under parameter uncertainty. Previous studies all restrict to the case that uncertainties among different states are uncoupled, which leads to conservative solutions. In contrast, we introduce an intuitive concept, termed \"Lightning Does not Strike Twice,\" to model coupled uncertain parameters. Specifically, we require that the system can deviate from its nominal parameters only a bounded number of times. We give probabilistic guarantees indicating that this model represents real life situations and devise tractable algorithms for computing optimal control policies using this concept.", "source": "arxiv/ml"}
{"id": "arxiv:1731", "title": "Groupwise Constrained Reconstruction for Subspace Clustering", "text": "Reconstruction based subspace clustering methods compute a self reconstruction matrix over the samples and use it for spectral clustering to obtain the final clustering result. Their success largely relies on the assumption that the underlying subspaces are independent, which, however, does not always hold in the applications with increasing number of subspaces. In this paper, we propose a novel reconstruction based subspace clustering model without making the subspace independence assumption. In our model, certain properties of the reconstruction matrix are explicitly characterized using the latent cluster indicators, and the affinity matrix used for spectral clustering can be directly built from the posterior of the latent cluster indicators instead of the reconstruction matrix. Experimental results on both synthetic and real-world datasets show that the proposed model can outperform the state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:1732", "title": "Ensemble Methods for Convex Regression with Applications to Geometric Programming Based Circuit Design", "text": "Convex regression is a promising area for bridging statistical estimation and deterministic convex optimization. New piecewise linear convex regression methods are fast and scalable, but can have instability when used to approximate constraints or objective functions for optimization. Ensemble methods, like bagging, smearing and random partitioning, can alleviate this problem and maintain the theoretical properties of the underlying estimator. We empirically examine the performance of ensemble methods for prediction and optimization, and then apply them to device modeling and constraint approximation for geometric programming based circuit design.", "source": "arxiv/ml"}
{"id": "arxiv:1733", "title": "Partial-Hessian Strategies for Fast Learning of Nonlinear Embeddings", "text": "Stochastic neighbor embedding (SNE) and related nonlinear manifold learning algorithms achieve high-quality low-dimensional representations of similarity data, but are notoriously slow to train. We propose a generic formulation of embedding algorithms that includes SNE and other existing algorithms, and study their relation with spectral methods and graph Laplacians. This allows us to define several partial-Hessian optimization strategies, characterize their global and local convergence, and evaluate them empirically. We achieve up to two orders of magnitude speedup over existing training methods with a strategy (which we call the spectral direction) that adds nearly no overhead to the gradient and yet is simple, scalable and applicable to several existing and future embedding algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1734", "title": "Active Learning for Matching Problems", "text": "Effective learning of user preferences is critical to easing user burden in various types of matching problems. Equally important is active query selection to further reduce the amount of preference information users must provide. We address the problem of active learning of user preferences for matching problems, introducing a novel method for determining probabilistic matchings, and developing several new active learning strategies that are sensitive to the specific matching objective. Experiments with real-world data sets spanning diverse domains demonstrate that matching-sensitive active learning", "source": "arxiv/ml"}
{"id": "arxiv:1735", "title": "Two-Manifold Problems with Applications to Nonlinear System Identification", "text": "Recently, there has been much interest in spectral approaches to learning manifolds---so-called kernel eigenmap methods. These methods have had some successes, but their applicability is limited because they are not robust to noise. To address this limitation, we look at two-manifold problems, in which we simultaneously reconstruct two related manifolds, each representing a different view of the same data. By solving these interconnected learning problems together, two-manifold algorithms are able to succeed where a non-integrated approach would fail: each view allows us to suppress noise in the other, reducing bias. We propose a class of algorithms for two-manifold problems, based on spectral decomposition of cross-covariance operators in Hilbert space, and discuss when two-manifold problems are useful. Finally, we demonstrate that solving a two-manifold problem can aid in learning a nonlinear dynamical system from limited data.", "source": "arxiv/ml"}
{"id": "arxiv:1736", "title": "Learning Efficient Structured Sparse Models", "text": "We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal splitting method for the iterative solution of hierarchical sparse coding problems, and show an efficient feed forward architecture derived from its iteration. This architecture faithfully approximates the exact structured sparse codes with a fraction of the complexity of the standard optimization methods. We also show that by using different training objective functions, learnable sparse encoders are no longer restricted to be mere approximants of the exact sparse code for a pre-given dictionary, as in earlier formulations, but can be rather used as full-featured sparse encoders or even modelers. A simple implementation shows several orders of magnitude speedup compared to the state-of-the-art at minimal performance degradation, making the proposed framework suitable for real time and large-scale applications.", "source": "arxiv/ml"}
{"id": "arxiv:1737", "title": "Analysis of Kernel Mean Matching under Covariate Shift", "text": "In real supervised learning scenarios, it is not uncommon that the training and test sample follow different probability distributions, thus rendering the necessity to correct the sampling bias. Focusing on a particular covariate shift problem, we derive high probability confidence bounds for the kernel mean matching (KMM) estimator, whose convergence rate turns out to depend on some regularity measure of the regression function and also on some capacity measure of the kernel. By comparing KMM with the natural plug-in estimator, we establish the superiority of the former hence provide concrete evidence/understanding to the effectiveness of KMM under covariate shift.", "source": "arxiv/ml"}
{"id": "arxiv:1738", "title": "Is margin preserved after random projection?", "text": "Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problems. We also extend our analysis to margin for multiclass problems, and provide theoretical bounds on multiclass margin on the projected data.", "source": "arxiv/ml"}
{"id": "arxiv:1739", "title": "The Most Persistent Soft-Clique in a Set of Sampled Graphs", "text": "When searching for characteristic subpatterns in potentially noisy graph data, it appears self-evident that having multiple observations would be better than having just one. However, it turns out that the inconsistencies introduced when different graph instances have different edge sets pose a serious challenge. In this work we address this challenge for the problem of finding maximum weighted cliques. We introduce the concept of most persistent soft-clique. This is subset of vertices, that 1) is almost fully or at least densely connected, 2) occurs in all or almost all graph instances, and 3) has the maximum weight. We present a measure of clique-ness, that essentially counts the number of edge missing to make a subset of vertices into a clique. With this measure, we show that the problem of finding the most persistent soft-clique problem can be cast either as: a) a max-min two person game optimization problem, or b) a min-min soft margin optimization problem. Both formulations lead to the same solution when using a partial Lagrangian method to solve the optimization problems. By experiments on synthetic data and on real social network data, we show that the proposed method is able to reliably find soft cliques in graph data, even if that is distorted by random noise or unreliable observations.", "source": "arxiv/ml"}
{"id": "arxiv:1740", "title": "Dimensionality Reduction by Local Discriminative Gaussians", "text": "We present local discriminative Gaussian (LDG) dimensionality reduction, a supervised dimensionality reduction technique for classification. The LDG objective function is an approximation to the leave-one-out training error of a local quadratic discriminant analysis classifier, and thus acts locally to each training point in order to find a mapping where similar data can be discriminated from dissimilar data. While other state-of-the-art linear dimensionality reduction methods require gradient descent or iterative solution approaches, LDG is solved with a single eigen-decomposition. Thus, it scales better for datasets with a large number of feature dimensions or training examples. We also adapt LDG to the transfer learning setting, and show that it achieves good performance when the test data distribution differs from that of the training data.", "source": "arxiv/ml"}
{"id": "arxiv:1741", "title": "A Generalized Loop Correction Method for Approximate Inference in Graphical Models", "text": "Belief Propagation (BP) is one of the most popular methods for inference in probabilistic graphical models. BP is guaranteed to return the correct answer for tree structures, but can be incorrect or non-convergent for loopy graphical models. Recently, several new approximate inference algorithms based on cavity distribution have been proposed. These methods can account for the effect of loops by incorporating the dependency between BP messages. Alternatively, region-based approximations (that lead to methods such as Generalized Belief Propagation) improve upon BP by considering interactions within small clusters of variables, thus taking small loops within these clusters into account. This paper introduces an approach, Generalized Loop Correction (GLC), that benefits from both of these types of loop correction. We show how GLC relates to these two families of inference methods, then provide empirical evidence that GLC works effectively in general, and can be significantly more accurate than both correction schemes.", "source": "arxiv/ml"}
{"id": "arxiv:1742", "title": "Modelling transition dynamics in MDPs with RKHS embeddings", "text": "We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This approach makes use of a recently developed representation of conditional distributions as \\emph{embeddings} in a reproducing kernel Hilbert space (RKHS). Such representations bypass the need for estimating transition probabilities or densities, and apply to any domain on which kernels can be defined. This avoids the need to calculate intractable integrals, since expectations are represented as RKHS inner products whose computation has linear complexity in the number of points used to represent the embedding. We provide guarantees for the proposed applications in MDPs: in the context of a value iteration algorithm, we prove convergence to either the optimal policy, or to the closest projection of the optimal policy in our model class (an RKHS), under reasonable assumptions. In experiments, we investigate a learning task in a typical classical control setting (the under-actuated pendulum), and on a navigation problem where only images from a sensor are observed. For policy optimisation we compare with least-squares policy iteration where a Gaussian process is used for value function estimation. For value estimation we also compare to the NPDP method. Our approach achieves better performance in all experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1743", "title": "Machine Learning that Matters", "text": "Much of current machine learning (ML) research has lost its connection to problems of import to the larger world of science and society. From this perspective, there exist glaring limitations in the data sets we investigate, the metrics we employ for evaluation, and the degree to which results are communicated back to their originating domains. What changes are needed to how we conduct research to increase the impact that ML has? We present six Impact Challenges to explicitly focus the field?s energy and attention, and we discuss existing obstacles that must be addressed. We aim to inspire ongoing discussion and focus on ML that matters.", "source": "arxiv/ml"}
{"id": "arxiv:1744", "title": "Projection-free Online Learning", "text": "The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the Frank-Wolfe technique. We obtain a range of regret bounds for online convex optimization, with better bounds for specific cases such as stochastic online smooth convex optimization. Besides the computational advantage, other desirable features of our algorithms are that they are parameter-free in the stochastic case and produce sparse decisions. We apply our algorithms to computationally intensive applications of collaborative filtering, and show the theoretical improvements to be clearly visible on standard datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1745", "title": "Dirichlet Process with Mixed Random Measures: A Nonparametric Topic Model for Labeled Data", "text": "We describe a nonparametric topic model for labeled data. The model uses a mixture of random measures (MRM) as a base distribution of the Dirichlet process (DP) of the HDP framework, so we call it the DP-MRM. To model labeled data, we define a DP distributed random measure for each label, and the resulting model generates an unbounded number of topics for each label. We apply DP-MRM on single-labeled and multi-labeled corpora of documents and compare the performance on label prediction with MedLDA, LDA-SVM, and Labeled-LDA. We further enhance the model by incorporating ddCRP and modeling multi-labeled images for image segmentation and object labeling, comparing the performance with nCuts and rddCRP.", "source": "arxiv/ml"}
{"id": "arxiv:1746", "title": "Max-Margin Nonparametric Latent Feature Models for Link Prediction", "text": "We present a max-margin nonparametric latent feature model, which unites the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction and automatically infer the unknown latent social dimension. By minimizing a hinge-loss using the linear expectation operator, we can perform posterior inference efficiently without dealing with a highly nonlinear link likelihood function; by using a fully-Bayesian formulation, we can avoid tuning regularization constants. Experimental results on real datasets appear to demonstrate the benefits inherited from max-margin learning and fully-Bayesian nonparametric inference.", "source": "arxiv/ml"}
{"id": "arxiv:1747", "title": "Learning with Augmented Features for Heterogeneous Domain Adaptation", "text": "We propose a new learning method for heterogeneous domain adaptation (HDA), in which the data from the source domain and the target domain are represented by heterogeneous features with different dimensions. Using two different projection matrices, we first transform the data from two domains into a common subspace in order to measure the similarity between the data from two domains. We then propose two new feature mapping functions to augment the transformed data with their original features and zeros. The existing learning methods (e.g., SVM and SVR) can be readily incorporated with our newly proposed augmented feature representations to effectively utilize the data from both domains for HDA. Using the hinge loss function in SVM as an example, we introduce the detailed objective function in our method called Heterogeneous Feature Augmentation (HFA) for a linear case and also describe its kernelization in order to efficiently cope with the data with very high dimensions. Moreover, we also develop an alternating optimization algorithm to effectively solve the nontrivial optimization problem in our HFA method. Comprehensive experiments on two benchmark datasets clearly demonstrate that HFA outperforms the existing HDA methods.", "source": "arxiv/ml"}
{"id": "arxiv:1748", "title": "Predicting accurate probabilities with a ranking loss", "text": "In many real-world applications of machine learning classifiers, it is essential to predict the probability of an example belonging to a particular class. This paper proposes a simple technique for predicting probabilities based on optimizing a ranking loss, followed by isotonic regression. This semi-parametric technique offers both good ranking and regression performance, and models a richer set of probability distributions than statistical workhorses such as logistic regression. We provide experimental results that show the effectiveness of this technique on real-world applications of probability prediction.", "source": "arxiv/ml"}
{"id": "arxiv:1749", "title": "Bayesian Watermark Attacks", "text": "This paper presents an application of statistical machine learning to the field of watermarking. We propose a new attack model on additive spread-spectrum watermarking systems. The proposed attack is based on Bayesian statistics. We consider the scenario in which a watermark signal is repeatedly embedded in specific, possibly chosen based on a secret message bitstream, segments (signals) of the host data. The host signal can represent a patch of pixels from an image or a video frame. We propose a probabilistic model that infers the embedded message bitstream and watermark signal, directly from the watermarked data, without access to the decoder. We develop an efficient Markov chain Monte Carlo sampler for updating the model parameters from their conjugate full conditional posteriors. We also provide a variational Bayesian solution, which further increases the convergence speed of the algorithm. Experiments with synthetic and real image signals demonstrate that the attack model is able to correctly infer a large part of the message bitstream and obtain a very accurate estimate of the watermark signal.", "source": "arxiv/ml"}
{"id": "arxiv:1750", "title": "The Convexity and Design of Composite Multiclass Losses", "text": "We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using this composite representation allows for the design of families of losses with the same Bayes risk.", "source": "arxiv/ml"}
{"id": "arxiv:1751", "title": "Tighter Variational Representations of f-Divergences via Restriction to Probability Measures", "text": "We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on two i.i.d. samples and derive the dual program for this estimator that performs well empirically. We also point out a connection between our estimator and MMD.", "source": "arxiv/ml"}
{"id": "arxiv:1752", "title": "Nonparametric variational inference", "text": "Variational methods are widely used for approximate posterior inference. However, their use is typically limited to families of distributions that enjoy particular conjugacy properties. To circumvent this limitation, we propose a family of variational approximations inspired by nonparametric kernel density estimation. The locations of these kernels and their bandwidth are treated as variational parameters and optimized to improve an approximate lower bound on the marginal likelihood of the data. Using multiple kernels allows the approximation to capture multiple modes of the posterior, unlike most other variational approximations. We demonstrate the efficacy of the nonparametric approximation with a hierarchical logistic regression model and a nonlinear matrix factorization model. We obtain predictive performance as good as or better than more specialized variational methods and sample-based approximations. The method is easy to apply to more general graphical models for which standard variational methods are difficult to derive.", "source": "arxiv/ml"}
{"id": "arxiv:1753", "title": "A Bayesian Approach to Approximate Joint Diagonalization of Square Matrices", "text": "We present a Bayesian scheme for the approximate diagonalisation of several square matrices which are not necessarily symmetric. A Gibbs sampler is derived to simulate samples of the common eigenvectors and the eigenvalues for these matrices. Several synthetic examples are used to illustrate the performance of the proposed Gibbs sampler and we then provide comparisons to several other joint diagonalization algorithms, which shows that the Gibbs sampler achieves the state-of-the-art performance on the examples considered. As a byproduct, the output of the Gibbs sampler could be used to estimate the log marginal likelihood, however we employ the approximation based on the Bayesian information criterion (BIC) which in the synthetic examples considered correctly located the number of common eigenvectors. We then succesfully applied the sampler to the source separation problem as well as the common principal component analysis and the common spatial pattern analysis problems.", "source": "arxiv/ml"}
{"id": "arxiv:1754", "title": "Unachievable Region in Precision-Recall Space and Its Effect on Empirical Evaluation", "text": "Precision-recall (PR) curves and the areas under them are widely used to summarize machine learning results, especially for data sets exhibiting class skew. They are often used analogously to ROC curves and the area under ROC curves. It is known that PR curves vary as class skew changes. What was not recognized before this paper is that there is a region of PR space that is completely unachievable, and the size of this region depends only on the skew. This paper precisely characterizes the size of that region and discusses its implications for empirical evaluation methodology in machine learning.", "source": "arxiv/ml"}
{"id": "arxiv:1755", "title": "Approximate Principal Direction Trees", "text": "We introduce a new spatial data structure for high dimensional data called the \\emph{approximate principal direction tree} (APD tree) that adapts to the intrinsic dimension of the data. Our algorithm ensures vector-quantization accuracy similar to that of computationally-expensive PCA trees with similar time-complexity to that of lower-accuracy RP trees. APD trees use a small number of power-method iterations to find splitting planes for recursively partitioning the data. As such they provide a natural trade-off between the running-time and accuracy achieved by RP and PCA trees. Our theoretical results establish a) strong performance guarantees regardless of the convergence rate of the power-method and b) that $O(\\log d)$ iterations suffice to establish the guarantee of PCA trees when the intrinsic dimension is $d$. We demonstrate this trade-off and the efficacy of our data structure on both the CPU and GPU.", "source": "arxiv/ml"}
{"id": "arxiv:1756", "title": "Sparse Additive Functional and Kernel CCA", "text": "Canonical Correlation Analysis (CCA) is a classical tool for finding correlations among the components of two random vectors. In recent years, CCA has been widely applied to the analysis of genomic data, where it is common for researchers to perform multiple assays on a single set of patient samples. Recent work has proposed sparse variants of CCA to address the high dimensionality of such data. However, classical and sparse CCA are based on linear models, and are thus limited in their ability to find general correlations. In this paper, we present two approaches to high-dimensional nonparametric CCA, building on recent developments in high-dimensional nonparametric regression. We present estimation procedures for both approaches, and analyze their theoretical properties in the high-dimensional setting. We demonstrate the effectiveness of these procedures in discovering nonlinear correlations via extensive simulations, as well as through experiments with genomic data.", "source": "arxiv/ml"}
{"id": "arxiv:1757", "title": "State-Space Inference for Non-Linear Latent Force Models with Application to Satellite Orbit Prediction", "text": "Latent force models (LFMs) are flexible models that combine mechanistic modelling principles (i.e., physical models) with non-parametric data-driven components. Several key applications of LFMs need non-linearities, which results in analytically intractable inference. In this work we show how non-linear LFMs can be represented as non-linear white noise driven state-space models and present an efficient non-linear Kalman filtering and smoothing based method for approximate state and parameter inference. We illustrate the performance of the proposed methodology via two simulated examples, and apply it to a real-world problem of long-term prediction of GPS satellite orbits.", "source": "arxiv/ml"}
{"id": "arxiv:1758", "title": "Dependent Hierarchical Normalized Random Measures for Dynamic Topic Modeling", "text": "We develop dependent hierarchical normalized random measures and apply them to dynamic topic modeling. The dependency arises via superposition, subsampling and point transition on the underlying Poisson processes of these measures. The measures used include normalised generalised Gamma processes that demonstrate power law properties, unlike Dirichlet processes used previously in dynamic topic modeling. Inference for the model includes adapting a recently developed slice sampler to directly manipulate the underlying Poisson process. Experiments performed on news, blogs, academic and Twitter collections demonstrate the technique gives superior perplexity over a number of previous models.", "source": "arxiv/ml"}
{"id": "arxiv:1759", "title": "Efficient Active Algorithms for Hierarchical Clustering", "text": "Advances in sensing technologies and the growth of the internet have resulted in an explosion in the size of modern datasets, while storage and processing power continue to lag behind. This motivates the need for algorithms that are efficient, both in terms of the number of measurements needed and running time. To combat the challenges associated with large datasets, we propose a general framework for active hierarchical clustering that repeatedly runs an off-the-shelf clustering algorithm on small subsets of the data and comes with guarantees on performance, measurement complexity and runtime complexity. We instantiate this framework with a simple spectral clustering algorithm and provide concrete results on its performance, showing that, under some assumptions, this algorithm recovers all clusters of size ?(log n) using O(n log^2 n) similarities and runs in O(n log^3 n) time for a dataset of n objects. Through extensive experimentation we also demonstrate that this framework is practically alluring.", "source": "arxiv/ml"}
{"id": "arxiv:1760", "title": "Group Sparse Additive Models", "text": "We consider the problem of sparse variable selection in nonparametric additive models, with the prior knowledge of the structure among the covariates to encourage those variables within a group to be selected jointly. Previous works either study the group sparsity in the parametric setting (e.g., group lasso), or address the problem in the non-parametric setting without exploiting the structural information (e.g., sparse additive models). In this paper, we present a new method, called group sparse additive models (GroupSpAM), which can handle group sparsity in additive models. We generalize the l1/l2 norm to Hilbert spaces as the sparsity-inducing penalty in GroupSpAM. Moreover, we derive a novel thresholding condition for identifying the functional sparsity at the group level, and propose an efficient block coordinate descent algorithm for constructing the estimate. We demonstrate by simulation that GroupSpAM substantially outperforms the competing methods in terms of support recovery and prediction accuracy in additive models, and also conduct a comparative experiment on a real breast cancer dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1761", "title": "Comparison-Based Learning with Rank Nets", "text": "We consider the problem of search through comparisons, where a user is presented with two candidate objects and reveals which is closer to her intended target. We study adaptive strategies for finding the target, that require knowledge of rank relationships but not actual distances between objects. We propose a new strategy based on rank nets, and show that for target distributions with a bounded doubling constant, it finds the target in a number of comparisons close to the entropy of the target distribution and, hence, of the optimum. We extend these results to the case of noisy oracles, and compare this strategy to prior art over multiple datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1762", "title": "Finding Botnets Using Minimal Graph Clusterings", "text": "We study the problem of identifying botnets and the IP addresses which they comprise, based on the observation of a fraction of the global email spam traffic. Observed mailing campaigns constitute evidence for joint botnet membership, they are represented by cliques in the graph of all messages. No evidence against an association of nodes is ever available. We reduce the problem of identifying botnets to a problem of finding a minimal clustering of the graph of messages. We directly model the distribution of clusterings given the input graph; this avoids potential errors caused by distributional assumptions of a generative model. We report on a case study in which we evaluate the model by its ability to predict the spam campaign that a given IP address is going to participate in.", "source": "arxiv/ml"}
{"id": "arxiv:1763", "title": "Clustering by Low-Rank Doubly Stochastic Matrix Decomposition", "text": "Clustering analysis by nonnegative low-rank approximations has achieved remarkable progress in the past decade. However, most approximation approaches in this direction are still restricted to matrix factorization. We propose a new low-rank learning method to improve the clustering performance, which is beyond matrix factorization. The approximation is based on a two-step bipartite random walk through virtual cluster nodes, where the approximation is formed by only cluster assigning probabilities. Minimizing the approximation error measured by Kullback-Leibler divergence is equivalent to maximizing the likelihood of a discriminative model, which endows our method with a solid probabilistic interpretation. The optimization is implemented by a relaxed Majorization-Minimization algorithm that is advantageous in finding good local minima. Furthermore, we point out that the regularized algorithm with Dirichlet prior only serves as initialization. Experimental results show that the new method has strong performance in clustering purity for various datasets, especially for large-scale manifold data.", "source": "arxiv/ml"}
{"id": "arxiv:1764", "title": "Semi-Supervised Learning of Class Balance under Class-Prior Change by Distribution Matching", "text": "In real-world classification problems, the class balance in the training dataset does not necessarily reflect that of the test dataset, which can cause significant estimation bias. If the class ratio of the test dataset is known, instance re-weighting or resampling allows systematical bias correction. However, learning the class ratio of the test dataset is challenging when no labeled data is available from the test domain. In this paper, we propose to estimate the class ratio in the test dataset by matching probability distributions of training and test input data. We demonstrate the utility of the proposed approach through experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1765", "title": "Linear Regression with Limited Observation", "text": "We consider the most common variants of linear regression, including Ridge, Lasso and Support-vector regression, in a setting where the learner is allowed to observe only a fixed number of attributes of each example at training time. We present simple and efficient algorithms for these problems: for Lasso and Ridge regression they need the same total number of attributes (up to constants) as do full-information algorithms, for reaching a certain accuracy. For Support-vector regression, we require exponentially less attributes compared to the state of the art. By that, we resolve an open problem recently posed by Cesa-Bianchi et al. (2010). Experiments show the theoretical bounds to be justified by superior performance compared to the state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:1766", "title": "Factorized Asymptotic Bayesian Hidden Markov Models", "text": "This paper addresses the issue of model selection for hidden Markov models (HMMs). We generalize factorized asymptotic Bayesian inference (FAB), which has been recently developed for model selection on independent hidden variables (i.e., mixture models), for time-dependent hidden variables. As with FAB in mixture models, FAB for HMMs is derived as an iterative lower bound maximization algorithm of a factorized information criterion (FIC). It inherits, from FAB for mixture models, several desirable properties for learning HMMs, such as asymptotic consistency of FIC with marginal log-likelihood, a shrinkage effect for hidden state selection, monotonic increase of the lower FIC bound through the iterative optimization. Further, it does not have a tunable hyper-parameter, and thus its model selection process can be fully automated. Experimental results shows that FAB outperforms states-of-the-art variational Bayesian HMM and non-parametric Bayesian HMM in terms of model selection accuracy and computational efficiency.", "source": "arxiv/ml"}
{"id": "arxiv:1767", "title": "Fast Prediction of New Feature Utility", "text": "We study the new feature utility prediction problem: statistically testing whether adding a new feature to the data representation can improve predictive accuracy on a supervised learning task. In many applications, identifying new informative features is the primary pathway for improving performance. However, evaluating every potential feature by re-training the predictor with it can be costly. The paper describes an efficient, learner-independent technique for estimating new feature utility without re-training based on the current predictor's outputs. The method is obtained by deriving a connection between loss reduction potential and the new feature's correlation with the loss gradient of the current predictor. This leads to a simple yet powerful hypothesis testing procedure, for which we prove consistency. Our theoretical analysis is accompanied by empirical evaluation on standard benchmarks and a large-scale industrial dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1768", "title": "LPQP for MAP: Putting LP Solvers to Better Use", "text": "MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation. We propose a novel MAP relaxation that penalizes the Kullback-Leibler divergence between the LP pairwise auxiliary variables, and QP equivalent terms given by the product of the unaries. We develop two efficient algorithms based on variants of this relaxation. The algorithms minimize the non-convex objective using belief propagation and dual decomposition as building blocks. Experiments on synthetic and real-world data show that the solutions returned by our algorithms substantially improve over the LP relaxation.", "source": "arxiv/ml"}
{"id": "arxiv:1769", "title": "Copula-based Kernel Dependency Measures", "text": "The paper presents a new copula based method for measuring dependence between random variables. Our approach extends the Maximum Mean Discrepancy to the copula of the joint distribution. We prove that this approach has several advantageous properties. Similarly to Shannon mutual information, the proposed dependence measure is invariant to any strictly increasing transformation of the marginal variables. This is important in many applications, for example in feature selection. The estimator is consistent, robust to outliers, and uses rank statistics only. We derive upper bounds on the convergence rate and propose independence tests too. We illustrate the theoretical contributions through a series of experiments in feature selection and low-dimensional embedding of distributions.", "source": "arxiv/ml"}
{"id": "arxiv:1770", "title": "Marginalized Denoising Autoencoders for Domain Adaptation", "text": "Stacked denoising autoencoders (SDAs) have been successfully used to learn new representations for domain adaptation. Recently, they have attained record accuracy on standard benchmark tasks of sentiment analysis across different text domains. SDAs learn robust data representations by reconstruction, recovering original features from data that are artificially corrupted with noise. In this paper, we propose marginalized SDA (mSDA) that addresses two crucial limitations of SDAs: high computational cost and lack of scalability to high-dimensional features. In contrast to SDAs, our approach of mSDA marginalizes noise and thus does not require stochastic gradient descent or other optimization algorithms to learn parameters ? in fact, they are computed in closed-form. Consequently, mSDA, which can be implemented in only 20 lines of MATLAB^{TM}, significantly speeds up SDAs by two orders of magnitude. Furthermore, the representations learnt by mSDA are as effective as the traditional SDAs, attaining almost identical accuracies in benchmark tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1771", "title": "Sparse-GEV: Sparse Latent Space Model for Multivariate Extreme Value Time Serie Modeling", "text": "In many applications of time series models, such as climate analysis and social media analysis, we are often interested in extreme events, such as heatwave, wind gust, and burst of topics. These time series data usually exhibit a heavy-tailed distribution rather than a Gaussian distribution. This poses great challenges to existing approaches due to the significantly different assumptions on the data distributions and the lack of sufficient past data on extreme events. In this paper, we propose the Sparse-GEV model, a latent state model based on the theory of extreme value modeling to automatically learn sparse temporal dependence and make predictions. Our model is theoretically significant because it is among the first models to learn sparse temporal dependencies among multivariate extreme value time series. We demonstrate the superior performance of our algorithm to the state-of-art methods, including Granger causality, copula approach, and transfer entropy, on one synthetic dataset, one climate dataset and two Twitter datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1772", "title": "Discriminative Probabilistic Prototype Learning", "text": "In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft labels indicating, for example, class probabilities. We represent an input datapoint as a mixture of probabilities over the corresponding set of feature vectors where each probability indicates how likely each vector is to belong to an unknown prototype pattern. We propose a probabilistic model that parameterizes these prototype patterns in terms of hidden variables and therefore it can be trained with conventional approaches based on likelihood maximization. More importantly, both the model parameters and the prototype patterns can be learned from data in a discriminative way. We show that our model can be seen as a probabilistic generalization of learning vector quantization (LVQ). We apply our method to the problems of shape classification, hyperspectral imaging classification and people's work class categorization, showing the superior performance of our method compared to the standard prototype-based classification approach and other competitive benchmark methods.", "source": "arxiv/ml"}
{"id": "arxiv:1773", "title": "Feature extraction in protein sequences classification : a new stability measure", "text": "Feature extraction is an unavoidable task, especially in the critical step of preprocessing biological sequences. This step consists for example in transforming the biological sequences into vectors of motifs where each motif is a subsequence that can be seen as a property (or attribute) characterizing the sequence. Hence, we obtain an object-property table where objects are sequences and properties are motifs extracted from sequences. This output can be used to apply standard machine learning tools to perform data mining tasks such as classification. Several previous works have described feature extraction methods for bio-sequence classification, but none of them discussed the robustness of these methods when perturbing the input data. In this work, we introduce the notion of stability of the generated motifs in order to study the robustness of motif extraction methods. We express this robustness in terms of the ability of the method to reveal any change occurring in the input data and also its ability to target the interesting motifs. We use these criteria to evaluate and experimentally compare four existing extraction methods for biological sequences.", "source": "arxiv/ml"}
{"id": "arxiv:1774", "title": "Smoothed Functional Algorithms for Stochastic Optimization using q-Gaussian Distributions", "text": "Smoothed functional (SF) schemes for gradient estimation are known to be efficient in stochastic optimization algorithms, specially when the objective is to improve the performance of a stochastic system. However, the performance of these methods depends on several parameters, such as the choice of a suitable smoothing kernel. Different kernels have been studied in literature, which include Gaussian, Cauchy and uniform distributions among others. This paper studies a new class of kernels based on the q-Gaussian distribution, that has gained popularity in statistical physics over the last decade. Though the importance of this family of distributions is attributed to its ability to generalize the Gaussian distribution, we observe that this class encompasses almost all existing smoothing kernels. This motivates us to study SF schemes for gradient estimation using the q-Gaussian distribution. Using the derived gradient estimates, we propose two-timescale algorithms for optimization of a stochastic objective function in a constrained setting with projected gradient search approach. We prove the convergence of our algorithms to the set of stationary points of an associated ODE. We also demonstrate their performance numerically through simulations on a queuing model.", "source": "arxiv/ml"}
{"id": "arxiv:1775", "title": "Estimating Densities with Non-Parametric Exponential Families", "text": "We propose a novel approach for density estimation with exponential families for the case when the true density may not fall within the chosen family. Our approach augments the sufficient statistics with features designed to accumulate probability mass in the neighborhood of the observed points, resulting in a non-parametric model similar to kernel density estimators. We show that under mild conditions, the resulting model uses only the sufficient statistics if the density is within the chosen exponential family, and asymptotically, it approximates densities outside of the chosen exponential family. Using the proposed approach, we modify the exponential random graph model, commonly used for modeling small-size graph distributions, to address the well-known issue of model degeneracy.", "source": "arxiv/ml"}
{"id": "arxiv:1776", "title": "The Robustness and Super-Robustness of L^p Estimation, when p < 1", "text": "In robust statistics, the breakdown point of an estimator is the percentage of outliers with which an estimator still generates reliable estimation. The upper bound of breakdown point is 50%, which means it is not possible to generate reliable estimation with more than half outliers. In this paper, it is shown that for majority of experiences, when the outliers exceed 50%, but if they are distributed randomly enough, it is still possible to generate a reliable estimation from minority good observations. The phenomenal of that the breakdown point is larger than 50% is named as super robustness. And, in this paper, a robust estimator is called strict robust if it generates a perfect estimation when all the good observations are perfect. More specifically, the super robustness of the maximum likelihood estimator of the exponential power distribution, or L^p estimation, where p<1, is investigated. This paper starts with proving that L^p (p<1) is a strict robust location estimator. Further, it is proved that L^p (p < 1)has the property of strict super-robustness on translation, rotation, scaling transformation and robustness on Euclidean transform.", "source": "arxiv/ml"}
{"id": "arxiv:1777", "title": "Hidden Markov Models with mixtures as emission distributions", "text": "In unsupervised classification, Hidden Markov Models (HMM) are used to account for a neighborhood structure between observations. The emission distributions are often supposed to belong to some parametric family. In this paper, a semiparametric modeling where the emission distributions are a mixture of parametric distributions is proposed to get a higher flexibility. We show that the classical EM algorithm can be adapted to infer the model parameters. For the initialisation step, starting from a large number of components, a hierarchical method to combine them into the hidden states is proposed. Three likelihood-based criteria to select the components to be combined are discussed. To estimate the number of hidden states, BIC-like criteria are derived. A simulation study is carried out both to determine the best combination between the merging criteria and the model selection criteria and to evaluate the accuracy of classification. The proposed method is also illustrated using a biological dataset from the model plant Arabidopsis thaliana. A R package HMMmix is freely available on the CRAN.", "source": "arxiv/ml"}
{"id": "arxiv:1778", "title": "Fast Variational Inference in the Conjugate Exponential Family", "text": "We present a general method for deriving collapsed variational inference algo- rithms for probabilistic models in the conjugate exponential family. Our method unifies many existing approaches to collapsed variational inference. Our collapsed variational inference leads to a new lower bound on the marginal likelihood. We exploit the information geometry of the bound to derive much faster optimization methods based on conjugate gradients for these models. Our approach is very general and is easily applied to any model where the mean field update equations have been derived. Empirically we show significant speed-ups for probabilistic models optimized using our bound.", "source": "arxiv/ml"}
{"id": "arxiv:1779", "title": "Stock prices assessment: proposal of a new index based on volume weighted historical prices through the use of computer modeling", "text": "The importance of considering the volumes to analyze stock prices movements can be considered as a well-accepted practice in the financial area. However, when we look at the scientific production in this field, we still cannot find a unified model that includes volume and price variations for stock assessment purposes. In this paper we present a computer model that could fulfill this gap, proposing a new index to evaluate stock prices based on their historical prices and volumes traded. Besides the model can be considered mathematically very simple, it was able to improve significantly the performance of agents operating with real financial data. Based on the results obtained, and also on the very intuitive logic of our model, we believe that the index proposed here can be very useful to help investors on the activity of determining ideal price ranges for buying and selling stocks in the financial market.", "source": "arxiv/ml"}
{"id": "arxiv:1780", "title": "Analysis of Semi-Supervised Learning with the Yarowsky Algorithm", "text": "The Yarowsky algorithm is a rule-based semi-supervised learning algorithm that has been successfully applied to some problems in computational linguistics. The algorithm was not mathematically well understood until (Abney 2004) which analyzed some specific variants of the algorithm, and also proposed some new algorithms for bootstrapping. In this paper, we extend Abney's work and show that some of his proposed algorithms actually optimize (an upper-bound on) an objective function based on a new definition of cross-entropy which is based on a particular instantiation of the Bregman distance between probability distributions. Moreover, we suggest some new algorithms for rule-based semi-supervised learning and show connections with harmonic functions and minimum multi-way cuts in graph-based semi-supervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:1781", "title": "Shift-Invariance Sparse Coding for Audio Classification", "text": "Sparse coding is an unsupervised learning algorithm that learns a succinct high-level representation of the inputs given only unlabeled data; it represents each input as a sparse linear combination of a set of basis functions. Originally applied to modeling the human visual cortex, sparse coding has also been shown to be useful for self-taught learning, in which the goal is to solve a supervised classification task given access to additional unlabeled data drawn from different classes than that in the supervised learning problem. Shift-invariant sparse coding (SISC) is an extension of sparse coding which reconstructs a (usually time-series) input using all of the basis functions in all possible shifts. In this paper, we present an efficient algorithm for learning SISC bases. Our method is based on iteratively solving two large convex optimization problems: The first, which computes the linear coefficients, is an L1-regularized linear least squares problem with potentially hundreds of thousands of variables. Existing methods typically use a heuristic to select a small subset of the variables to optimize, but we present a way to efficiently compute the exact solution. The second, which solves for bases, is a constrained linear least squares problem. By optimizing over complex-valued variables in the Fourier domain, we reduce the coupling between the different variables, allowing the problem to be solved efficiently. We show that SISC's learned high-level representations of speech and music provide useful features for classification tasks within those domains. When applied to classification, under certain conditions the learned features outperform state of the art spectral and cepstral features.", "source": "arxiv/ml"}
{"id": "arxiv:1782", "title": "Convergent Propagation Algorithms via Oriented Trees", "text": "Inference problems in graphical models are often approximated by casting them as constrained optimization problems. Message passing algorithms, such as belief propagation, have previously been suggested as methods for solving these optimization problems. However, there are few convergence guarantees for such algorithms, and the algorithms are therefore not guaranteed to solve the corresponding optimization problem. Here we present an oriented tree decomposition algorithm that is guaranteed to converge to the global optimum of the Tree-Reweighted (TRW) variational problem. Our algorithm performs local updates in the convex dual of the TRW problem - an unconstrained generalized geometric program. Primal updates, also local, correspond to oriented reparametrization operations that leave the distribution intact.", "source": "arxiv/ml"}
{"id": "arxiv:1783", "title": "A new parameter Learning Method for Bayesian Networks with Qualitative Influences", "text": "We propose a new method for parameter learning in Bayesian networks with qualitative influences. This method extends our previous work from networks of binary variables to networks of discrete variables with ordered values. The specified qualitative influences correspond to certain order restrictions on the parameters in the network. These parameters may therefore be estimated using constrained maximum likelihood estimation. We propose an alternative method, based on the isotonic regression. The constrained maximum likelihood estimates are fairly complicated to compute, whereas computation of the isotonic regression estimates only requires the repeated application of the Pool Adjacent Violators algorithm for linear orders. Therefore, the isotonic regression estimator is to be preferred from the viewpoint of computational complexity. Through experiments on simulated and real data, we show that the new learning method is competitive in performance to the constrained maximum likelihood estimator, and that both estimators improve on the standard estimator.", "source": "arxiv/ml"}
{"id": "arxiv:1784", "title": "Bayesian structure learning using dynamic programming and MCMC", "text": "MCMC methods for sampling from the space of DAGs can mix poorly due to the local nature of the proposals that are commonly used. It has been shown that sampling from the space of node orders yields better results [FK03, EW06]. Recently, Koivisto and Sood showed how one can analytically marginalize over orders using dynamic programming (DP) [KS04, Koi06]. Their method computes the exact marginal posterior edge probabilities, thus avoiding the need for MCMC. Unfortunately, there are four drawbacks to the DP technique: it can only use modular priors, it can only compute posteriors over modular features, it is difficult to compute a predictive density, and it takes exponential time and space. We show how to overcome the first three of these problems by using the DP algorithm as a proposal distribution for MCMC in DAG space. We show that this hybrid technique converges to the posterior faster than other methods, resulting in more accurate structure learning and higher predictive likelihoods on test data.", "source": "arxiv/ml"}
{"id": "arxiv:1785", "title": "Statistical Translation, Heat Kernels and Expected Distances", "text": "High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from high variance and performs poorly in general. We explore novel connections between statistical translation, heat kernels on manifolds and graphs, and expected distances. These connections provide a new framework for unsupervised metric learning for text documents. Experiments indicate that the resulting distances are generally superior to their more standard counterparts.", "source": "arxiv/ml"}
{"id": "arxiv:1786", "title": "Discovering Patterns in Biological Sequences by Optimal Segmentation", "text": "Computational methods for discovering patterns of local correlations in sequences are important in computational biology. Here we show how to determine the optimal partitioning of aligned sequences into non-overlapping segments such that positions in the same segment are strongly correlated while positions in different segments are not. Our approach involves discovering the hidden variables of a Bayesian network that interact with observed sequences so as to form a set of independent mixture models. We introduce a dynamic program to efficiently discover the optimal segmentation, or equivalently the optimal set of hidden variables. We evaluate our approach on two computational biology tasks. One task is related to the design of vaccines against polymorphic pathogens and the other task involves analysis of single nucleotide polymorphisms (SNPs) in human DNA. We show how common tasks in these problems naturally correspond to inference procedures in the learned models. Error rates of our learned models for the prediction of missing SNPs are up to 1/3 less than the error rates of a state-of-the-art SNP prediction method. Source code is available at www.uwm.edu/~joebock/segmentation.", "source": "arxiv/ml"}
{"id": "arxiv:1787", "title": "Mixture-of-Parents Maximum Entropy Markov Models", "text": "We present the mixture-of-parents maximum entropy Markov model (MoP-MEMM), a class of directed graphical models extending MEMMs. The MoP-MEMM allows tractable incorporation of long-range dependencies between nodes by restricting the conditional distribution of each node to be a mixture of distributions given the parents. We show how to efficiently compute the exact marginal posterior node distributions, regardless of the range of the dependencies. This enables us to model non-sequential correlations present within text documents, as well as between interconnected documents, such as hyperlinked web pages. We apply the MoP-MEMM to a named entity recognition task and a web page classification task. In each, our model shows significant improvement over the basic MEMM, and is competitive with other long-range sequence models that use approximate inference.", "source": "arxiv/ml"}
{"id": "arxiv:1788", "title": "Reading Dependencies from Polytree-Like Bayesian Networks", "text": "We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictive.", "source": "arxiv/ml"}
{"id": "arxiv:1789", "title": "Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods", "text": "In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The algorithm's aim is to find a reward function such that the resulting optimal policy matches well the expert's observed behavior. The main difficulty is that the mapping from the parameters to policies is both nonsmooth and highly redundant. Resorting to subdifferentials solves the first difficulty, while the second one is over- come by computing natural gradients. We tested the proposed method in two artificial domains and found it to be more reliable and efficient than some previous methods.", "source": "arxiv/ml"}
{"id": "arxiv:1790", "title": "Consensus ranking under the exponential model", "text": "We analyze the generalized Mallows model, a popular exponential model over rankings. Estimating the central (or consensus) ranking from data is NP-hard. We obtain the following new results: (1) We show that search methods can estimate both the central ranking pi0 and the model parameters theta exactly. The search is n! in the worst case, but is tractable when the true distribution is concentrated around its mode; (2) We show that the generalized Mallows model is jointly exponential in (pi0; theta), and introduce the conjugate prior for this model class; (3) The sufficient statistics are the pairwise marginal probabilities that item i is preferred to item j. Preliminary experiments confirm the theoretical predictions and compare the new algorithm and existing heuristics.", "source": "arxiv/ml"}
{"id": "arxiv:1791", "title": "Collaborative Filtering and the Missing at Random Assumption", "text": "Rating prediction is an important application, and a popular research topic in collaborative filtering. However, both the validity of learning algorithms, and the validity of standard testing procedures rest on the assumption that missing ratings are missing at random (MAR). In this paper we present the results of a user study in which we collect a random sample of ratings from current users of an online radio service. An analysis of the rating data collected in the study shows that the sample of random ratings has markedly different properties than ratings of user-selected songs. When asked to report on their own rating behaviour, a large number of users indicate they believe their opinion of a song does affect whether they choose to rate that song, a violation of the MAR condition. Finally, we present experimental results showing that incorporating an explicit model of the missing data mechanism can lead to significant improvements in prediction performance on the random sample of ratings.", "source": "arxiv/ml"}
{"id": "arxiv:1792", "title": "Nonparametric Bayes Pachinko Allocation", "text": "Recent advances in topic models have explored complicated structured distributions to represent topic correlation. For example, the pachinko allocation model (PAM) captures arbitrary, nested, and possibly sparse correlations between topics using a directed acyclic graph (DAG). While PAM provides more flexibility and greater expressive power than previous models like latent Dirichlet allocation (LDA), it is also more difficult to determine the appropriate topic structure for a specific dataset. In this paper, we propose a nonparametric Bayesian prior for PAM based on a variant of the hierarchical Dirichlet process (HDP). Although the HDP can capture topic correlations defined by nested data structure, it does not automatically discover such correlations from unstructured data. By assuming an HDP-based prior for PAM, we are able to learn both the number of topics and how the topics are correlated. We evaluate our model on synthetic and real-world text datasets, and show that nonparametric PAM achieves performance matching the best of PAM without manually tuning the number of topics.", "source": "arxiv/ml"}
{"id": "arxiv:1793", "title": "On Discarding, Caching, and Recalling Samples in Active Learning", "text": "We address challenges of active learning under scarce informational resources in non-stationary environments. In real-world settings, data labeled and integrated into a predictive model may become invalid over time. However, the data can become informative again with switches in context and such changes may indicate unmodeled cyclic or other temporal dynamics. We explore principles for discarding, caching, and recalling labeled data points in active learning based on computations of value of information. We review key concepts and study the value of the methods via investigations of predictive performance and costs of acquiring data for simulated and real-world data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1794", "title": "Accuracy Bounds for Belief Propagation", "text": "The belief propagation (BP) algorithm is widely applied to perform approximate inference on arbitrary graphical models, in part due to its excellent empirical properties and performance. However, little is known theoretically about when this algorithm will perform well. Using recent analysis of convergence and stability properties in BP and new results on approximations in binary systems, we derive a bound on the error in BP's estimates for pairwise Markov random fields over discrete valued random variables. Our bound is relatively simple to compute, and compares favorably with a previous method of bounding the accuracy of BP.", "source": "arxiv/ml"}
{"id": "arxiv:1795", "title": "Fast Nonparametric Conditional Density Estimation", "text": "Conditional density estimation generalizes regression by modeling a full density f(yjx) rather than only the expected value E(yjx). This is important for many tasks, including handling multi-modality and generating prediction intervals. Though fundamental and widely applicable, nonparametric conditional density estimators have received relatively little attention from statisticians and little or none from the machine learning community. None of that work has been applied to greater than bivariate data, presumably due to the computational difficulty of data-driven bandwidth selection. We describe the double kernel conditional density estimator and derive fast dual-tree-based algorithms for bandwidth selection using a maximum likelihood criterion. These techniques give speedups of up to 3.8 million in our experiments, and enable the first applications to previously intractable large multivariate datasets, including a redshift prediction problem from the Sloan Digital Sky Survey.", "source": "arxiv/ml"}
{"id": "arxiv:1796", "title": "Learning Selectively Conditioned Forest Structures with Applications to DBNs and Classification", "text": "Dealing with uncertainty in Bayesian Network structures using maximum a posteriori (MAP) estimation or Bayesian Model Averaging (BMA) is often intractable due to the superexponential number of possible directed, acyclic graphs. When the prior is decomposable, two classes of graphs where efficient learning can take place are tree structures, and fixed-orderings with limited in-degree. We show how MAP estimates and BMA for selectively conditioned forests (SCF), a combination of these two classes, can be computed efficiently for ordered sets of variables. We apply SCFs to temporal data to learn Dynamic Bayesian Networks having an intra-timestep forest and inter-timestep limited in-degree structure, improving model accuracy over DBNs without the combination of structures. We also apply SCFs to Bayes Net classification to learn selective forest augmented Naive Bayes classifiers. We argue that the built-in feature selection of selective augmented Bayes classifiers makes them preferable to similar non-selective classifiers based on empirical evidence.", "source": "arxiv/ml"}
{"id": "arxiv:1797", "title": "A Characterization of Markov Equivalence Classes for Directed Acyclic Graphs with Latent Variables", "text": "Different directed acyclic graphs (DAGs) may be Markov equivalent in the sense that they entail the same conditional independence relations among the observed variables. Meek (1995) characterizes Markov equivalence classes for DAGs (with no latent variables) by presenting a set of orientation rules that can correctly identify all arrow orientations shared by all DAGs in a Markov equivalence class, given a member of that class. For DAG models with latent variables, maximal ancestral graphs (MAGs) provide a neat representation that facilitates model search. Earlier work (Ali et al. 2005) has identified a set of orientation rules sufficient to construct all arrowheads common to a Markov equivalence class of MAGs. In this paper, we provide extra rules sufficient to construct all common tails as well. We end up with a set of orientation rules sound and complete for identifying commonalities across a Markov equivalence class of MAGs, which is particularly useful for causal inference.", "source": "arxiv/ml"}
{"id": "arxiv:1798", "title": "Bayesian Active Distance Metric Learning", "text": "Distance metric learning is an important component for many tasks, such as statistical classification and content-based image retrieval. Existing approaches for learning distance metrics from pairwise constraints typically suffer from two major problems. First, most algorithms only offer point estimation of the distance metric and can therefore be unreliable when the number of training examples is small. Second, since these algorithms generally select their training examples at random, they can be inefficient if labeling effort is limited. This paper presents a Bayesian framework for distance metric learning that estimates a posterior distribution for the distance metric from labeled pairwise constraints. We describe an efficient algorithm based on the variational method for the proposed Bayesian approach. Furthermore, we apply the proposed Bayesian framework to active distance metric learning by selecting those unlabeled example pairs with the greatest uncertainty in relative distance. Experiments in classification demonstrate that the proposed framework achieves higher classification accuracy and identifies more informative training examples than the non-Bayesian approach and state-of-the-art distance metric learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1799", "title": "MAP Estimation, Linear Programming and Belief Propagation with Convex Free Energies", "text": "Finding the most probable assignment (MAP) in a general graphical model is known to be NP hard but good approximations have been attained with max-product belief propagation (BP) and its variants. In particular, it is known that using BP on a single-cycle graph or tree reweighted BP on an arbitrary graph will give the MAP solution if the beliefs have no ties. In this paper we extend the setting under which BP can be used to provably extract the MAP. We define Convex BP as BP algorithms based on a convex free energy approximation and show that this class includes ordinary BP with single-cycle, tree reweighted BP and many other BP variants. We show that when there are no ties, fixed-points of convex max-product BP will provably give the MAP solution. We also show that convex sum-product BP at sufficiently small temperatures can be used to solve linear programs that arise from relaxing the MAP problem. Finally, we derive a novel condition that allows us to derive the MAP solution even if some of the convex BP beliefs have ties. In experiments, we show that our theorems allow us to find the MAP in many real-world instances of graphical models where exact inference using junction-tree is impossible.", "source": "arxiv/ml"}
{"id": "arxiv:1800", "title": "Imitation Learning with a Value-Based Prior", "text": "The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowledge about the correct behavior, where we assume that this prior knowledge takes the form of a Markov Decision Process (MDP) that is used by the apprentice as a rough and imperfect model of the mentor's behavior. Specifically, taking a Bayesian approach, we treat the value of a policy in this modeling MDP as the log prior probability of the policy. In other words, we assume a priori that the mentor's behavior is likely to be a high value policy in the modeling MDP, though quite possibly different from the optimal policy. We describe an efficient algorithm that, given a modeling MDP and a set of demonstrations by a mentor, provably converges to a stationary point of the log posterior of the mentor's policy, where the posterior is computed with respect to the \"value based\" prior. We also present empirical evidence that this prior does in fact speed learning of the mentor's policy, and is an improvement in our experiments over similar previous methods.", "source": "arxiv/ml"}
{"id": "arxiv:1801", "title": "Improved Dynamic Schedules for Belief Propagation", "text": "Belief propagation and its variants are popular methods for approximate inference, but their running time and even their convergence depend greatly on the schedule used to send the messages. Recently, dynamic update schedules have been shown to converge much faster on hard networks than static schedules, namely the residual BP schedule of Elidan et al. [2006]. But that RBP algorithm wastes message updates: many messages are computed solely to determine their priority, and are never actually performed. In this paper, we show that estimating the residual, rather than calculating it directly, leads to significant decreases in the number of messages required for convergence, and in the total running time. The residual is estimated using an upper bound based on recent work on message errors in BP. On both synthetic and real-world networks, this dramatically decreases the running time of BP, in some cases by a factor of five, without affecting the quality of the solution.", "source": "arxiv/ml"}
{"id": "arxiv:1802", "title": "On Sensitivity of the MAP Bayesian Network Structure to the Equivalent Sample Size Parameter", "text": "BDeu marginal likelihood score is a popular model selection criterion for selecting a Bayesian network structure based on sample data. This non-informative scoring criterion assigns same score for network structures that encode same independence statements. However, before applying the BDeu score, one must determine a single parameter, the equivalent sample size alpha. Unfortunately no generally accepted rule for determining the alpha parameter has been suggested. This is disturbing, since in this paper we show through a series of concrete experiments that the solution of the network structure optimization problem is highly sensitive to the chosen alpha parameter value. Based on these results, we are able to give explanations for how and why this phenomenon happens, and discuss ideas for solving this problem.", "source": "arxiv/ml"}
{"id": "arxiv:1803", "title": "Dynamic Pricing under Finite Space Demand Uncertainty: A Multi-Armed Bandit with Dependent Arms", "text": "We consider a dynamic pricing problem under unknown demand models. In this problem a seller offers prices to a stream of customers and observes either success or failure in each sale attempt. The underlying demand model is unknown to the seller and can take one of N possible forms. In this paper, we show that this problem can be formulated as a multi-armed bandit with dependent arms. We propose a dynamic pricing policy based on the likelihood ratio test. We show that the proposed policy achieves complete learning, i.e., it offers a bounded regret where regret is defined as the revenue loss with respect to the case with a known demand model. This is in sharp contrast with the logarithmic growing regret in multi-armed bandit with independent arms.", "source": "arxiv/ml"}
{"id": "arxiv:1804", "title": "Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and Autoencoders", "text": "We present a new algorithm for Independent Component Analysis (ICA) which has provable performance guarantees. In particular, suppose we are given samples of the form $y = Ax + \\eta$ where $A$ is an unknown $n \\times n$ matrix and $x$ is a random variable whose components are independent and have a fourth moment strictly less than that of a standard Gaussian random variable and $\\eta$ is an $n$-dimensional Gaussian random variable with unknown covariance $\\Sigma$: We give an algorithm that provable recovers $A$ and $\\Sigma$ up to an additive $\\epsilon$ and whose running time and sample complexity are polynomial in $n$ and $1 / \\epsilon$. To accomplish this, we introduce a novel \"quasi-whitening\" step that may be useful in other contexts in which the covariance of Gaussian noise is not known in advance. We also give a general framework for finding all local optima of a function (given an oracle for approximately finding just one) and this is a crucial step in our algorithm, one that has been overlooked in previous attempts, and allows us to control the accumulation of error when we find the columns of $A$ one by one via local search.", "source": "arxiv/ml"}
{"id": "arxiv:1805", "title": "Practical recommendations for gradient-based training of deep architectures", "text": "Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to successfully and efficiently train and debug large-scale and often deep multi-layer neural networks. It closes with open questions about the training difficulties observed with deeper architectures.", "source": "arxiv/ml"}
{"id": "arxiv:1806", "title": "Representation Learning: A Review and New Perspectives", "text": "The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.", "source": "arxiv/ml"}
{"id": "arxiv:1807", "title": "A Geometric Algorithm for Scalable Multiple Kernel Learning", "text": "We present a geometric formulation of the Multiple Kernel Learning (MKL) problem. To do so, we reinterpret the problem of learning kernel weights as searching for a kernel that maximizes the minimum (kernel) distance between two convex polytopes. This interpretation combined with novel structural insights from our geometric formulation allows us to reduce the MKL problem to a simple optimization routine that yields provable convergence as well as quality guarantees. As a result our method scales efficiently to much larger data sets than most prior methods can handle. Empirical evaluation on eleven datasets shows that we are significantly faster and even compare favorably with a uniform unweighted combination of kernels.", "source": "arxiv/ml"}
{"id": "arxiv:1808", "title": "Learning mixtures of spherical Gaussians: moment methods and spectral decompositions", "text": "This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are in general position, a simple spectral decomposition technique yields consistent parameter estimates from low-order observable moments, without additional minimum separation assumptions needed by previous computationally efficient estimation procedures. Thus computational and information-theoretic barriers to efficient estimation in mixture models are precluded when the mixture components have means in general position and spherical covariances. Some connections are made to estimation problems related to independent component analysis.", "source": "arxiv/ml"}
{"id": "arxiv:1809", "title": "Exact Recovery of Sparsely-Used Dictionaries", "text": "We consider the problem of learning sparsely used dictionaries with an arbitrary square dictionary and a random, sparse coefficient matrix. We prove that $O (n \\log n)$ samples are sufficient to uniquely determine the coefficient matrix. Based on this proof, we design a polynomial-time algorithm, called Exact Recovery of Sparsely-Used Dictionaries (ER-SpUD), and prove that it probably recovers the dictionary and coefficient matrix when the coefficient matrix is sufficiently sparse. Simulation results show that ER-SpUD reveals the true dictionary as well as the coefficients with probability higher than many state-of-the-art algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1810", "title": "Graph Based Classification Methods Using Inaccurate External Classifier Information", "text": "In this paper we consider the problem of collectively classifying entities where relational information is available across the entities. In practice inaccurate class distribution for each entity is often available from another (external) classifier. For example this distribution could come from a classifier built using content features or a simple dictionary. Given the relational and inaccurate external classifier information, we consider two graph based settings in which the problem of collective classification can be solved. In the first setting the class distribution is used to fix labels to a subset of nodes and the labels for the remaining nodes are obtained like in a transductive setting. In the other setting the class distributions of all nodes are used to define the fitting function part of a graph regularized objective function. We define a generalized objective function that handles both the settings. Methods like harmonic Gaussian field and local-global consistency (LGC) reported in the literature can be seen as special cases. We extend the LGC and weighted vote relational neighbor classification (WvRN) methods to support usage of external classifier information. We also propose an efficient least squares regularization (LSR) based method and relate it to information regularization methods. All the methods are evaluated on several benchmark and real world datasets. Considering together speed, robustness and accuracy, experimental results indicate that the LSR and WvRN-extension methods perform better than other methods.", "source": "arxiv/ml"}
{"id": "arxiv:1811", "title": "Transductive Classification Methods for Mixed Graphs", "text": "In this paper we provide a principled approach to solve a transductive classification problem involving a similar graph (edges tend to connect nodes with same labels) and a dissimilar graph (edges tend to connect nodes with opposing labels). Most of the existing methods, e.g., Information Regularization (IR), Weighted vote Relational Neighbor classifier (WvRN) etc, assume that the given graph is only a similar graph. We extend the IR and WvRN methods to deal with mixed graphs. We evaluate the proposed extensions on several benchmark datasets as well as two real world datasets and demonstrate the usefulness of our ideas.", "source": "arxiv/ml"}
{"id": "arxiv:1812", "title": "An Additive Model View to Sparse Gaussian Process Classifier Design", "text": "We consider the problem of designing a sparse Gaussian process classifier (SGPC) that generalizes well. Viewing SGPC design as constructing an additive model like in boosting, we present an efficient and effective SGPC design method to perform a stage-wise optimization of a predictive loss function. We introduce new methods for two key components viz., site parameter estimation and basis vector selection in any SGPC design. The proposed adaptive sampling based basis vector selection method aids in achieving improved generalization performance at a reduced computational cost. This method can also be used in conjunction with any other site parameter estimation methods. It has similar computational and storage complexities as the well-known information vector machine and is suitable for large datasets. The hyperparameters can be determined by optimizing a predictive loss function. The experimental results show better generalization performance of the proposed basis vector selection method on several benchmark datasets, particularly for relatively smaller basis vector set sizes or on difficult datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1813", "title": "Predictive Approaches For Gaussian Process Classifier Model Selection", "text": "In this paper we consider the problem of Gaussian process classifier (GPC) model selection with different Leave-One-Out (LOO) Cross Validation (CV) based optimization criteria and provide a practical algorithm using LOO predictive distributions with such criteria to select hyperparameters. Apart from the standard average negative logarithm of predictive probability (NLP), we also consider smoothed versions of criteria such as F-measure and Weighted Error Rate (WER), which are useful for handling imbalanced data. Unlike the regression case, LOO predictive distributions for the classifier case are intractable. We use approximate LOO predictive distributions arrived from Expectation Propagation (EP) approximation. We conduct experiments on several real world benchmark datasets. When the NLP criterion is used for optimizing the hyperparameters, the predictive approaches show better or comparable NLP generalization performance with existing GPC approaches. On the other hand, when the F-measure criterion is used, the F-measure generalization performance improves significantly on several datasets. Overall, the EP-based predictive algorithm comes out as an excellent choice for GP classifier model selection with different optimization criteria.", "source": "arxiv/ml"}
{"id": "arxiv:1814", "title": "Directed Time Series Regression for Control", "text": "We propose directed time series regression, a new approach to estimating parameters of time-series models for use in certainty equivalent model predictive control. The approach combines merits of least squares regression and empirical optimization. Through a computational study involving a stochastic version of a well known inverted pendulum balancing problem, we demonstrate that directed time series regression can generate significant improvements in controller performance over either of the aforementioned alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:1815", "title": "Discrete Elastic Inner Vector Spaces with Application in Time Series and Sequence Mining", "text": "This paper proposes a framework dedicated to the construction of what we call discrete elastic inner product allowing one to embed sets of non-uniformly sampled multivariate time series or sequences of varying lengths into inner product space structures. This framework is based on a recursive definition that covers the case of multiple embedded time elastic dimensions. We prove that such inner products exist in our general framework and show how a simple instance of this inner product class operates on some prospective applications, while generalizing the Euclidean inner product. Classification experimentations on time series and symbolic sequences datasets demonstrate the benefits that we can expect by embedding time series or sequences into elastic inner spaces rather than into classical Euclidean spaces. These experiments show good accuracy when compared to the euclidean distance or even dynamic programming algorithms while maintaining a linear algorithmic complexity at exploitation stage, although a quadratic indexing phase beforehand is required.", "source": "arxiv/ml"}
{"id": "arxiv:1816", "title": "Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena", "text": "The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots. This paper presents a decentralized data fusion and active sensing (D2FAS) algorithm for mobile sensors to actively explore the road network to gather and assimilate the most informative data for predicting the traffic phenomenon. We analyze the time and communication complexity of D2FAS and demonstrate that it can scale well with a large number of observations and sensors. We provide a theoretical guarantee on its predictive performance to be equivalent to that of a sophisticated centralized sparse approximation for the Gaussian process (GP) model: The computation of such a sparse approximate GP model can thus be parallelized and distributed among the mobile sensors (in a Google-like MapReduce paradigm), thereby achieving efficient and scalable prediction. We also theoretically guarantee its active sensing performance that improves under various practical environmental conditions. Empirical evaluation on real-world urban road network data shows that our D2FAS algorithm is significantly more time-efficient and scalable than state-of-the-art centralized algorithms while achieving comparable predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:1817", "title": "Scaling Life-long Off-policy Learning", "text": "We pursue a life-long learning approach to artificial intelligence that makes extensive use of reinforcement learning algorithms. We build on our prior work with general value functions (GVFs) and the Horde architecture. GVFs have been shown able to represent a wide variety of facts about the world's dynamics that may be useful to a long-lived agent (Sutton et al. 2011). We have also previously shown scaling - that thousands of on-policy GVFs can be learned accurately in real-time on a mobile robot (Modayil, White & Sutton 2011). That work was limited in that it learned about only one policy at a time, whereas the greatest potential benefits of life-long learning come from learning about many policies in parallel, as we explore in this paper. Many new challenges arise in this off-policy learning setting. To deal with convergence and efficiency challenges, we utilize the recently introduced GTD({\\lambda}) algorithm. We show that GTD({\\lambda}) with tile coding can simultaneously learn hundreds of predictions for five simple target policies while following a single random behavior policy, assessing accuracy with interspersed on-policy tests. To escape the need for the tests, which preclude further scaling, we introduce and empirically vali- date two online estimators of the off-policy objective (MSPBE). Finally, we use the more efficient of the two estimators to demonstrate off-policy learning at scale - the learning of value functions for one thousand policies in real time on a physical robot. This ability constitutes a significant step towards scaling life-long off-policy learning.", "source": "arxiv/ml"}
{"id": "arxiv:1818", "title": "Learning Markov Network Structure using Brownian Distance Covariance", "text": "In this paper, we present a simple non-parametric method for learning the structure of undirected graphs from data that drawn from an underlying unknown distribution. We propose to use Brownian distance covariance to estimate the conditional independences between the random variables and encodes pairwise Markov graph. This framework can be applied in high-dimensional setting, where the number of parameters much be larger than the sample size.", "source": "arxiv/ml"}
{"id": "arxiv:1819", "title": "Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring", "text": "In this paper we address the following question: Can we approximately sample from a Bayesian posterior distribution if we are only allowed to touch a small mini-batch of data-items for every sample we generate?. An algorithm based on the Langevin equation with stochastic gradients (SGLD) was previously proposed to solve this, but its mixing rate was slow. By leveraging the Bayesian Central Limit Theorem, we extend the SGLD algorithm so that at high mixing rates it will sample from a normal approximation of the posterior, while for slow mixing rates it will mimic the behavior of SGLD with a pre-conditioner matrix. As a bonus, the proposed algorithm is reminiscent of Fisher scoring (with stochastic gradients) and as such an efficient optimizer during burn-in.", "source": "arxiv/ml"}
{"id": "arxiv:1820", "title": "Shortest path distance in random k-nearest neighbor graphs", "text": "Consider a weighted or unweighted k-nearest neighbor graph that has been built on n data points drawn randomly according to some density p on R^d. We study the convergence of the shortest path distance in such graphs as the sample size tends to infinity. We prove that for unweighted kNN graphs, this distance converges to an unpleasant distance function on the underlying space whose properties are detrimental to machine learning. We also study the behavior of the shortest path distance in weighted kNN graphs.", "source": "arxiv/ml"}
{"id": "arxiv:1821", "title": "High-Dimensional Covariance Decomposition into Sparse Markov and Independence Domains", "text": "In this paper, we present a novel framework incorporating a combination of sparse models in different domains. We posit the observed data as generated from a linear combination of a sparse Gaussian Markov model (with a sparse precision matrix) and a sparse Gaussian independence model (with a sparse covariance matrix). We provide efficient methods for decomposition of the data into two domains, \\viz Markov and independence domains. We characterize a set of sufficient conditions for identifiability and model consistency. Our decomposition method is based on a simple modification of the popular $\\ell_1$-penalized maximum-likelihood estimator ($\\ell_1$-MLE). We establish that our estimator is consistent in both the domains, i.e., it successfully recovers the supports of both Markov and independence models, when the number of samples $n$ scales as $n = \\Omega(d^2 \\log p)$, where $p$ is the number of variables and $d$ is the maximum node degree in the Markov model. Our conditions for recovery are comparable to those of $\\ell_1$-MLE for consistent estimation of a sparse Markov model, and thus, we guarantee successful high-dimensional estimation of a richer class of models under comparable conditions. Our experiments validate these results and also demonstrate that our models have better inference accuracy under simple algorithms such as loopy belief propagation.", "source": "arxiv/ml"}
{"id": "arxiv:1822", "title": "Feature Selection via Probabilistic Outputs", "text": "This paper investigates two feature-scoring criteria that make use of estimated class probabilities: one method proposed by \\citet{shen} and a complementary approach proposed below. We develop a theoretical framework to analyze each criterion and show that both estimate the spread (across all values of a given feature) of the probability that an example belongs to the positive class. Based on our analysis, we predict when each scoring technique will be advantageous over the other and give empirical results validating our predictions.", "source": "arxiv/ml"}
{"id": "arxiv:1823", "title": "Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization", "text": "We describe novel subgradient methods for a broad class of matrix optimization problems involving nuclear norm regularization. Unlike existing approaches, our method executes very cheap iterations by combining low-rank stochastic subgradients with efficient incremental SVD updates, made possible by highly optimized and parallelizable dense linear algebra operations on small matrices. Our practical algorithms always maintain a low-rank factorization of iterates that can be conveniently held in memory and efficiently multiplied to generate predictions in matrix completion settings. Empirical comparisons confirm that our approach is highly competitive with several recently proposed state-of-the-art solvers for such problems.", "source": "arxiv/ml"}
{"id": "arxiv:1824", "title": "Improved Estimation in Time Varying Models", "text": "Locally adapted parameterizations of a model (such as locally weighted regression) are expressive but often suffer from high variance. We describe an approach for reducing the variance, based on the idea of estimating simultaneously a transformed space for the model, as well as locally adapted parameterizations in this new space. We present a new problem formulation that captures this idea and illustrate it in the important context of time varying models. We develop an algorithm for learning a set of bases for approximating a time varying sparse network; each learned basis constitutes an archetypal sparse network structure. We also provide an extension for learning task-driven bases. We present empirical results on synthetic data sets, as well as on a BCI EEG classification task.", "source": "arxiv/ml"}
{"id": "arxiv:1825", "title": "How To Grade a Test Without Knowing the Answers --- A Bayesian Graphical Model for Adaptive Crowdsourcing and Aptitude Testing", "text": "We propose a new probabilistic graphical model that jointly models the difficulties of questions, the abilities of participants and the correct answers to questions in aptitude testing and crowdsourcing settings. We devise an active learning/adaptive testing scheme based on a greedy minimization of expected model entropy, which allows a more efficient resource allocation by dynamically choosing the next question to be asked based on the previous responses. We present experimental results that confirm the ability of our model to infer the required parameters and demonstrate that the adaptive testing scheme requires fewer questions to obtain the same accuracy as a static test scenario.", "source": "arxiv/ml"}
{"id": "arxiv:1826", "title": "Fast classification using sparse decision DAGs", "text": "In this paper we propose an algorithm that builds sparse decision DAGs (directed acyclic graphs) from a list of base classifiers provided by an external learning method such as AdaBoost. The basic idea is to cast the DAG design task as a Markov decision process. Each instance can decide to use or to skip each base classifier, based on the current state of the classifier being built. The result is a sparse decision DAG where the base classifiers are selected in a data-dependent way. The method has a single hyperparameter with a clear semantics of controlling the accuracy/speed trade-off. The algorithm is competitive with state-of-the-art cascade detectors on three object-detection benchmarks, and it clearly outperforms them when there is a small number of base classifiers. Unlike cascades, it is also readily applicable for multi-class classification. Using the multi-class setup, we show on a benchmark web page ranking data set that we can significantly improve the decision speed without harming the performance of the ranker.", "source": "arxiv/ml"}
{"id": "arxiv:1827", "title": "Canonical Trends: Detecting Trend Setters in Web Data", "text": "Much information available on the web is copied, reused or rephrased. The phenomenon that multiple web sources pick up certain information is often called trend. A central problem in the context of web data mining is to detect those web sources that are first to publish information which will give rise to a trend. We present a simple and efficient method for finding trends dominating a pool of web sources and identifying those web sources that publish the information relevant to a trend before others. We validate our approach on real data collected from influential technology news feeds.", "source": "arxiv/ml"}
{"id": "arxiv:1828", "title": "Poisoning Attacks against Support Vector Machines", "text": "We investigate a family of poisoning attacks against Support Vector Machines (SVM). Such attacks inject specially crafted training data that increases the SVM's test error. Central to the motivation for these attacks is the fact that most learning algorithms assume that their training data comes from a natural or well-behaved distribution. However, this assumption does not generally hold in security-sensitive settings. As we demonstrate, an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data. The proposed attack uses a gradient ascent strategy in which the gradient is computed based on properties of the SVM's optimal solution. This method can be kernelized and enables the attack to be constructed in the input space even for non-linear kernels. We experimentally demonstrate that our gradient ascent procedure reliably identifies good local maxima of the non-convex validation error surface, which significantly increases the classifier's test error.", "source": "arxiv/ml"}
{"id": "arxiv:1829", "title": "Incorporating Causal Prior Knowledge as Path-Constraints in Bayesian Networks and Maximal Ancestral Graphs", "text": "We consider the incorporation of causal knowledge about the presence or absence of (possibly indirect) causal relations into a causal model. Such causal relations correspond to directed paths in a causal model. This type of knowledge naturally arises from experimental data, among others. Specifically, we consider the formalisms of Causal Bayesian Networks and Maximal Ancestral Graphs and their Markov equivalence classes: Partially Directed Acyclic Graphs and Partially Oriented Ancestral Graphs. We introduce sound and complete procedures which are able to incorporate causal prior knowledge in such models. In simulated experiments, we show that often considering even a few causal facts leads to a significant number of new inferences. In a case study, we also show how to use real experimental data to infer causal knowledge and incorporate it into a real biological causal network. The code is available at mensxmachina.org.", "source": "arxiv/ml"}
{"id": "arxiv:1830", "title": "Gaussian Process Quantile Regression using Expectation Propagation", "text": "Direct quantile regression involves estimating a given quantile of a response variable as a function of input variables. We present a new framework for direct quantile regression where a Gaussian process model is learned, minimising the expected tilted loss function. The integration required in learning is not analytically tractable so to speed up the learning we employ the Expectation Propagation algorithm. We describe how this work relates to other quantile regression methods and apply the method on both synthetic and real data sets. The method is shown to be competitive with state of the art methods whilst allowing for the leverage of the full Gaussian process probabilistic framework.", "source": "arxiv/ml"}
{"id": "arxiv:1831", "title": "Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription", "text": "We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our approach outperforms many traditional models of polyphonic music on a variety of realistic datasets. We show how our musical language model can serve as a symbolic prior to improve the accuracy of polyphonic transcription.", "source": "arxiv/ml"}
{"id": "arxiv:1832", "title": "Local Loss Optimization in Operator Models: A New Insight into Spectral Learning", "text": "This paper re-visits the spectral method for learning latent variable models defined in terms of observable operators. We give a new perspective on the method, showing that operators can be recovered by minimizing a loss defined on a finite subset of the domain. A non-convex optimization similar to the spectral method is derived. We also propose a regularized convex relaxation of this optimization. We show that in practice the availabilty of a continuous regularization parameter (in contrast with the discrete number of states in the original method) allows a better trade-off between accuracy and model complexity. We also prove that in general, a randomized strategy for choosing the local loss will succeed with high probability.", "source": "arxiv/ml"}
{"id": "arxiv:1833", "title": "Nonparametric Link Prediction in Dynamic Networks", "text": "We propose a non-parametric link prediction algorithm for a sequence of graph snapshots over time. The model predicts links based on the features of its endpoints, as well as those of the local neighborhood around the endpoints. This allows for different types of neighborhoods in a graph, each with its own dynamics (e.g, growing or shrinking communities). We prove the consistency of our estimator, and give a fast implementation based on locality-sensitive hashing. Experiments with simulated as well as five real-world dynamic graphs show that we outperform the state of the art, especially when sharp fluctuations or non-linearities are present.", "source": "arxiv/ml"}
{"id": "arxiv:1834", "title": "Convergence Rates for Differentially Private Statistical Estimation", "text": "Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce privacy by adding random noise to a function computed over the data, and the challenge in designing such algorithms is to control the added noise in order to optimize the privacy-accuracy-sample size tradeoff. This work studies differentially-private statistical estimation, and shows upper and lower bounds on the convergence rates of differentially private approximations to statistical estimators. Our results reveal a formal connection between differential privacy and the notion of Gross Error Sensitivity (GES) in robust statistics, by showing that the convergence rate of any differentially private approximation to an estimator that is accurate over a large class of distributions has to grow with the GES of the estimator. We then provide an upper bound on the convergence rate of a differentially private approximation to an estimator with bounded range and bounded GES. We show that the bounded range condition is necessary if we wish to ensure a strict form of differential privacy.", "source": "arxiv/ml"}
{"id": "arxiv:1835", "title": "Joint Optimization and Variable Selection of High-dimensional Gaussian Processes", "text": "Maximizing high-dimensional, non-convex functions through noisy observations is a notoriously hard problem, but one that arises in many applications. In this paper, we tackle this challenge by modeling the unknown function as a sample from a high-dimensional Gaussian process (GP) distribution. Assuming that the unknown function only depends on few relevant variables, we show that it is possible to perform joint variable selection and GP optimization. We provide strong performance guarantees for our algorithm, bounding the sample complexity of variable selection, and as well as providing cumulative regret bounds. We further provide empirical evidence on the effectiveness of our algorithm on several benchmark optimization problems.", "source": "arxiv/ml"}
{"id": "arxiv:1836", "title": "Communications Inspired Linear Discriminant Analysis", "text": "We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label (based on a Shannon entropy measure). By harnessing a recent theoretical result on the gradient of mutual information, the above optimization problem can be solved directly using gradient descent, without requiring simplification of the objective function. Theoretical analysis and empirical comparison are made between the proposed method and two closely related methods (Linear Discriminant Analysis and Information Discriminant Analysis), and comparisons are also made with a method in which Renyi entropy is used to define the mutual information (in this case the gradient may be computed simply, under a special parameter setting). Relative to these alternative approaches, the proposed method achieves promising results on real datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1837", "title": "Learning Parameterized Skills", "text": "We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth manifold on which the skill policies lie. This manifold models how policy parameters change as task parameters vary. The method identifies the number of charts that compose the manifold and then applies non-linear regression in each chart to construct a parameterized skill by predicting policy parameters from task parameters. We evaluate our method on an underactuated simulated robotic arm tasked with learning to accurately throw darts at a parameterized target location.", "source": "arxiv/ml"}
{"id": "arxiv:1838", "title": "Demand-Driven Clustering in Relational Domains for Predicting Adverse Drug Events", "text": "Learning from electronic medical records (EMR) is challenging due to their relational nature and the uncertain dependence between a patient's past and future health status. Statistical relational learning is a natural fit for analyzing EMRs but is less adept at handling their inherent latent structure, such as connections between related medications or diseases. One way to capture the latent structure is via a relational clustering of objects. We propose a novel approach that, instead of pre-clustering the objects, performs a demand-driven clustering during learning. We evaluate our algorithm on three real-world tasks where the goal is to use EMRs to predict whether a patient will have an adverse reaction to a medication. We find that our approach is more accurate than performing no clustering, pre-clustering, and using expert-constructed medical heterarchies.", "source": "arxiv/ml"}
{"id": "arxiv:1839", "title": "Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret", "text": "Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to adapt to the online algorithm's actions. We define the alternative notion of policy regret, which attempts to provide a more meaningful way to measure an online algorithm's performance against adaptive adversaries. Focusing on the online bandit setting, we show that no bandit algorithm can guarantee a sublinear policy regret against an adaptive adversary with unbounded memory. On the other hand, if the adversary's memory is bounded, we present a general technique that converts any bandit algorithm with a sublinear regret bound into an algorithm with a sublinear policy regret bound. We extend this result to other variants of regret, such as switching regret, internal regret, and swap regret.", "source": "arxiv/ml"}
{"id": "arxiv:1840", "title": "Consistent Multilabel Ranking through Univariate Losses", "text": "We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labels. Very recently, this approach was put into question by a negative result showing that commonly used pairwise surrogate losses, such as exponential and logistic losses, are inconsistent. In this paper, we show a positive result which is arguably surprising in light of the previous one: the simpler univariate variants of exponential and logistic surrogates (i.e., defined on single labels) are consistent for rank loss minimization. Instead of directly proving convergence, we give a much stronger result by deriving regret bounds and convergence rates. The proposed losses suggest efficient and scalable algorithms, which are tested experimentally.", "source": "arxiv/ml"}
{"id": "arxiv:1841", "title": "Parallelizing Exploration-Exploitation Tradeoffs with Gaussian Process Bandit Optimization", "text": "Can one parallelize complex exploration exploitation tradeoffs? As an example, consider the problem of optimal high-throughput experimental design, where we wish to sequentially design batches of experiments in order to simultaneously learn a surrogate function mapping stimulus to response and identify the maximum of the function. We formalize the task as a multi-armed bandit problem, where the unknown payoff function is sampled from a Gaussian process (GP), and instead of a single arm, in each round we pull a batch of several arms in parallel. We develop GP-BUCB, a principled algorithm for choosing batches, based on the GP-UCB algorithm for sequential GP optimization. We prove a surprising result; as compared to the sequential approach, the cumulative regret of the parallel algorithm only increases by a constant factor independent of the batch size B. Our results provide rigorous theoretical support for exploiting parallelism in Bayesian global optimization. We demonstrate the effectiveness of our approach on two real-world applications.", "source": "arxiv/ml"}
{"id": "arxiv:1842", "title": "Two Step CCA: A new spectral method for estimating vector models of words", "text": "Unlabeled data is often used to learn representations which can be used to supplement baseline features in a supervised learner. For example, for text applications where the words lie in a very high dimensional space (the size of the vocabulary), one can learn a low rank \"dictionary\" by an eigen-decomposition of the word co-occurrence matrix (e.g. using PCA or CCA). In this paper, we present a new spectral method based on CCA to learn an eigenword dictionary. Our improved procedure computes two set of CCAs, the first one between the left and right contexts of the given word and the second one between the projections resulting from this CCA and the word itself. We prove theoretically that this two-step procedure has lower sample complexity than the simple single step procedure and also illustrate the empirical efficacy of our approach and the richness of representations learned by our Two Step CCA (TSCCA) procedure on the tasks of POS tagging and sentiment classification.", "source": "arxiv/ml"}
{"id": "arxiv:1843", "title": "Policy Gradients with Variance Related Risk Criteria", "text": "Managing risk in dynamic decision problems is of cardinal importance in many fields such as finance and process control. The most common approach to defining risk is through various variance related criteria such as the Sharpe Ratio or the standard deviation adjusted reward. It is known that optimizing many of the variance related risk criteria is NP-hard. In this paper we devise a framework for local policy gradient style algorithms for reinforcement learning for variance related criteria. Our starting point is a new formula for the variance of the cost-to-go in episodic tasks. Using this formula we develop policy gradient algorithms for criteria that involve both the expected cost and the variance of the cost. We prove the convergence of these algorithms to local minima and demonstrate their applicability in a portfolio planning problem.", "source": "arxiv/ml"}
{"id": "arxiv:1844", "title": "Bounded Planning in Passive POMDPs", "text": "In Passive POMDPs actions do not affect the world state, but still incur costs. When the agent is bounded by information-processing constraints, it can only keep an approximation of the belief. We present a variational principle for the problem of maintaining the information which is most useful for minimizing the cost, and introduce an efficient and simple algorithm for finding an optimum.", "source": "arxiv/ml"}
{"id": "arxiv:1845", "title": "Bayesian Optimal Active Search and Surveying", "text": "We consider two active binary-classification problems with atypical objectives. In the first, active search, our goal is to actively uncover as many members of a given class as possible. In the second, active surveying, our goal is to actively query points to ultimately predict the proportion of a given class. Numerous real-world problems can be framed in these terms, and in either case typical model-based concerns such as generalization error are only of secondary importance. We approach these problems via Bayesian decision theory; after choosing natural utility functions, we derive the optimal policies. We provide three contributions. In addition to introducing the active surveying problem, we extend previous work on active search in two ways. First, we prove a novel theoretical result, that less-myopic approximations to the optimal policy can outperform more-myopic approximations by any arbitrary degree. We then derive bounds that for certain models allow us to reduce (in practice dramatically) the exponential search space required by a naive implementation of the optimal policy, enabling further lookahead while still ensuring that optimal decisions are always made.", "source": "arxiv/ml"}
{"id": "arxiv:1846", "title": "Large-Scale Feature Learning With Spike-and-Slab Sparse Coding", "text": "We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new feature learning and extraction procedure based on a factor model we call spike-and-slab sparse coding (S3C). Prior work on S3C has not prioritized the ability to exploit parallel architectures and scale S3C to the enormous problem sizes needed for object recognition. We present a novel inference procedure for appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors that S3C may be trained with. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the spike-and-slab Restricted Boltzmann Machine (ssRBM) on the CIFAR-10 dataset. We use the CIFAR-100 dataset to demonstrate that our method scales to large numbers of classes better than previous methods. Finally, we use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models? Transfer Learning Challenge.", "source": "arxiv/ml"}
{"id": "arxiv:1847", "title": "Sequential Nonparametric Regression", "text": "We present algorithms for nonparametric regression in settings where the data are obtained sequentially. While traditional estimators select bandwidths that depend upon the sample size, for sequential data the effective sample size is dynamically changing. We propose a linear time algorithm that adjusts the bandwidth for each new data point, and show that the estimator achieves the optimal minimax rate of convergence. We also propose the use of online expert mixing algorithms to adapt to unknown smoothness of the regression function. We provide simulations that confirm the theoretical results, and demonstrate the effectiveness of the methods.", "source": "arxiv/ml"}
{"id": "arxiv:1848", "title": "Scaling Up Coordinate Descent Algorithms for Large $\\ell_1$ Regularization Problems", "text": "We present a generic framework for parallel coordinate descent (CD) algorithms that includes, as special cases, the original sequential algorithms Cyclic CD and Stochastic CD, as well as the recent parallel Shotgun algorithm. We introduce two novel parallel algorithms that are also special cases---Thread-Greedy CD and Coloring-Based CD---and give performance measurements for an OpenMP implementation of these.", "source": "arxiv/ml"}
{"id": "arxiv:1849", "title": "On the Partition Function and Random Maximum A-Posteriori Perturbations", "text": "In this paper we relate the partition function to the max-statistics of random variables. In particular, we provide a novel framework for approximating and bounding the partition function using MAP inference on randomly perturbed models. As a result, we can use efficient MAP solvers such as graph-cuts to evaluate the corresponding partition function. We show that our method excels in the typical \"high signal - high coupling\" regime that results in ragged energy landscapes difficult for alternative approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1850", "title": "On the Difficulty of Nearest Neighbor Search", "text": "Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which data properties affect the difficulty of nearest neighbor search and how? This paper introduces the first concrete measure called Relative Contrast that can be used to evaluate the influence of several crucial data characteristics such as dimensionality, sparsity, and database size simultaneously in arbitrary normed metric spaces. Moreover, we present a theoretical analysis to prove how the difficulty measure (relative contrast) determines/affects the complexity of Local Sensitive Hashing, a popular approximate NN search method. Relative contrast also provides an explanation for a family of heuristic hashing algorithms with good practical performance based on PCA. Finally, we show that most of the previous works in measuring NN search meaningfulness/difficulty can be derived as special asymptotic cases for dense vectors of the proposed measure.", "source": "arxiv/ml"}
{"id": "arxiv:1851", "title": "A Simple Algorithm for Semi-supervised Learning with Improved Generalization Error Bound", "text": "In this work, we develop a simple algorithm for semi-supervised regression. The key idea is to use the top eigenfunctions of integral operator derived from both labeled and unlabeled examples as the basis functions and learn the prediction function by a simple linear regression. We show that under appropriate assumptions about the integral operator, this approach is able to achieve an improved regression error bound better than existing bounds of supervised learning. We also verify the effectiveness of the proposed algorithm by an empirical study.", "source": "arxiv/ml"}
{"id": "arxiv:1852", "title": "A Convex Relaxation for Weakly Supervised Classifiers", "text": "This paper introduces a general multi-class approach to weakly supervised classification. Inferring the labels and learning the parameters of the model is usually done jointly through a block-coordinate descent algorithm such as expectation-maximization (EM), which may lead to local minima. To avoid this problem, we propose a cost function based on a convex relaxation of the soft-max loss. We then propose an algorithm specifically designed to efficiently solve the corresponding semidefinite program (SDP). Empirically, our method compares favorably to standard ones on different datasets for multiple instance learning and semi-supervised learning as well as on clustering tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1853", "title": "The Nonparametric Metadata Dependent Relational Model", "text": "We introduce the nonparametric metadata dependent relational (NMDR) model, a Bayesian nonparametric stochastic block model for network data. The NMDR allows the entities associated with each node to have mixed membership in an unbounded collection of latent communities. Learned regression models allow these memberships to depend on, and be predicted from, arbitrary node metadata. We develop efficient MCMC algorithms for learning NMDR models from partially observed node relationships. Retrospective MCMC methods allow our sampler to work directly with the infinite stick-breaking representation of the NMDR, avoiding the need for finite truncations. Our results demonstrate recovery of useful latent communities from real-world social and ecological networks, and the usefulness of metadata in link prediction tasks.", "source": "arxiv/ml"}
{"id": "arxiv:1854", "title": "The Big Data Bootstrap", "text": "The bootstrap provides a simple and powerful means of assessing the quality of estimators. However, in settings involving large datasets, the computation of bootstrap-based quantities can be prohibitively demanding. As an alternative, we present the Bag of Little Bootstraps (BLB), a new procedure which incorporates features of both the bootstrap and subsampling to obtain a robust, computationally efficient means of assessing estimator quality. BLB is well suited to modern parallel and distributed computing architectures and retains the generic applicability, statistical efficiency, and favorable theoretical properties of the bootstrap. We provide the results of an extensive empirical and theoretical investigation of BLB's behavior, including a study of its statistical correctness, its large-scale implementation and performance, selection of hyperparameters, and performance on real data.", "source": "arxiv/ml"}
{"id": "arxiv:1855", "title": "An Infinite Latent Attribute Model for Network Data", "text": "Latent variable models for network data extract a summary of the relational structure underlying an observed network. The simplest possible models subdivide nodes of the network into clusters; the probability of a link between any two nodes then depends only on their cluster assignment. Currently available models can be classified by whether clusters are disjoint or are allowed to overlap. These models can explain a \"flat\" clustering structure. Hierarchical Bayesian models provide a natural approach to capture more complex dependencies. We propose a model in which objects are characterised by a latent feature vector. Each feature is itself partitioned into disjoint groups (subclusters), corresponding to a second layer of hierarchy. In experimental comparisons, the model achieves significantly improved predictive performance on social and biological link prediction tasks. The results indicate that models with a single layer hierarchy over-simplify real networks.", "source": "arxiv/ml"}
{"id": "arxiv:1856", "title": "Learning Task Grouping and Overlap in Multi-task Learning", "text": "In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information across the tasks. We assume that each task parameter vector is a linear combi- nation of a finite number of underlying basis tasks. The coefficients of the linear combina- tion are sparse in nature and the overlap in the sparsity patterns of two tasks controls the amount of sharing across these. Our model is based on on the assumption that task pa- rameters within a group lie in a low dimen- sional subspace but allows the tasks in differ- ent groups to overlap with each other in one or more bases. Experimental results on four datasets show that our approach outperforms competing methods.", "source": "arxiv/ml"}
{"id": "arxiv:1857", "title": "Learning Invariant Representations with Local Transformations", "text": "Learning invariant representations is an important problem in machine learning and pattern recognition. In this paper, we present a novel framework of transformation-invariant feature learning by incorporating linear transformations into the feature learning algorithms. For example, we present the transformation-invariant restricted Boltzmann machine that compactly represents data by its weights and their transformations, which achieves invariance of the feature representation via probabilistic max pooling. In addition, we show that our transformation-invariant feature learning framework can also be extended to other unsupervised learning methods, such as autoencoders or sparse coding. We evaluate our method on several image classification benchmark datasets, such as MNIST variations, CIFAR-10, and STL-10, and show competitive or superior classification performance when compared to the state-of-the-art. Furthermore, our method achieves state-of-the-art performance on phone classification tasks with the TIMIT dataset, which demonstrates wide applicability of our proposed algorithms to other domains.", "source": "arxiv/ml"}
{"id": "arxiv:1858", "title": "Cross-Domain Multitask Learning with Latent Probit Models", "text": "Learning multiple tasks across heterogeneous domains is a challenging problem since the feature space may not be the same for different tasks. We assume the data in multiple tasks are generated from a latent common domain via sparse domain transforms and propose a latent probit model (LPM) to jointly learn the domain transforms, and the shared probit classifier in the common domain. To learn meaningful task relatedness and avoid over-fitting in classification, we introduce sparsity in the domain transforms matrices, as well as in the common classifier. We derive theoretical bounds for the estimation error of the classifier in terms of the sparsity of domain transforms. An expectation-maximization algorithm is derived for learning the LPM. The effectiveness of the approach is demonstrated on several real datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1859", "title": "Distributed Parameter Estimation via Pseudo-likelihood", "text": "Estimating statistical models within sensor networks requires distributed algorithms, in which both data and computation are distributed across the nodes of the network. We propose a general approach for distributed learning based on combining local estimators defined by pseudo-likelihood components, encompassing a number of combination methods, and provide both theoretical and experimental analysis. We show that simple linear combination or max-voting methods, when combined with second-order information, are statistically competitive with more advanced and costly joint optimization. Our algorithms have many attractive properties including low communication and computational cost and \"any-time\" behavior.", "source": "arxiv/ml"}
{"id": "arxiv:1860", "title": "Structured Learning from Partial Annotations", "text": "Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, graphs or sequences. Specifying such detailed ground truth can be tedious or infeasible for large outputs. Our main contribution is a large margin formulation that makes structured learning from only partially annotated data possible. The resulting optimization problem is non-convex, yet can be efficiently solve by concave-convex procedure (CCCP) with novel speedup strategies. We apply our method to a challenging tracking-by-assignment problem of a variable number of divisible objects. On this benchmark, using only 25% of a full annotation we achieve a performance comparable to a model learned with a full annotation. Finally, we offer a unifying perspective of previous work using the hinge, ramp, or max loss for structured learning, followed by an empirical comparison on their practical performance.", "source": "arxiv/ml"}
{"id": "arxiv:1861", "title": "An Online Boosting Algorithm with Theoretical Justifications", "text": "We study the task of online boosting--combining online weak learners into an online strong learner. While batch boosting has a sound theoretical foundation, online boosting deserves more study from the theoretical perspective. In this paper, we carefully compare the differences between online and batch boosting, and propose a novel and reasonable assumption for the online weak learner. Based on the assumption, we design an online boosting algorithm with a strong theoretical guarantee by adapting from the offline SmoothBoost algorithm that matches the assumption closely. We further tackle the task of deciding the number of weak learners using established theoretical results for online convex programming and predicting with expert advice. Experiments on real-world data sets demonstrate that the proposed algorithm compares favorably with existing online boosting algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1862", "title": "A Joint Model of Language and Perception for Grounded Attribute Learning", "text": "As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract representations of the meanings of natural language tied to perception and actuation in the physical world. In this paper, we present an approach for joint learning of language and perception models for grounded attribute induction. Our perception model includes attribute classifiers, for example to detect object color and shape, and the language model is based on a probabilistic categorial grammar that enables the construction of rich, compositional meaning representations. The approach is evaluated on the task of interpreting sentences that describe sets of objects in a physical workspace. We demonstrate accurate task performance and effective latent-variable concept induction in physical grounded scenes.", "source": "arxiv/ml"}
{"id": "arxiv:1863", "title": "Sparse Stochastic Inference for Latent Dirichlet allocation", "text": "We present a hybrid algorithm for Bayesian topic models that combines the efficiency of sparse Gibbs sampling with the scalability of online stochastic inference. We used our algorithm to analyze a corpus of 1.2 million books (33 billion words) with thousands of topics. Our approach reduces the bias of variational inference and generalizes to many Bayesian hidden-variable models.", "source": "arxiv/ml"}
{"id": "arxiv:1864", "title": "A Fast and Simple Algorithm for Training Neural Probabilistic Language Models", "text": "In spite of their superior performance, neural probabilistic language models (NPLMs) remain far less widely used than n-gram models due to their notoriously long training times, which are measured in weeks even for moderately-sized datasets. Training NPLMs is computationally expensive because they are explicitly normalized, which leads to having to consider all words in the vocabulary when computing the log-likelihood gradients. We propose a fast and simple algorithm for training NPLMs based on noise-contrastive estimation, a newly introduced procedure for estimating unnormalized continuous distributions. We investigate the behaviour of the algorithm on the Penn Treebank corpus and show that it reduces the training times by more than an order of magnitude without affecting the quality of the resulting models. The algorithm is also more efficient and much more stable than importance sampling because it requires far fewer noise samples to perform well. We demonstrate the scalability of the proposed approach by training several neural language models on a 47M-word corpus with a 80K-word vocabulary, obtaining state-of-the-art results on the Microsoft Research Sentence Completion Challenge dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1865", "title": "Convergence of the EM Algorithm for Gaussian Mixtures with Unbalanced Mixing Coefficients", "text": "The speed of convergence of the Expectation Maximization (EM) algorithm for Gaussian mixture model fitting is known to be dependent on the amount of overlap among the mixture components. In this paper, we study the impact of mixing coefficients on the convergence of EM. We show that when the mixture components exhibit some overlap, the convergence of EM becomes slower as the dynamic range among the mixing coefficients increases. We propose a deterministic anti-annealing algorithm, that significantly improves the speed of convergence of EM for such mixtures with unbalanced mixing coefficients. The proposed algorithm is compared against other standard optimization techniques like BFGS, Conjugate Gradient, and the traditional EM algorithm. Finally, we propose a similar deterministic anti-annealing based algorithm for the Dirichlet process mixture model and demonstrate its advantages over the conventional variational Bayesian approach.", "source": "arxiv/ml"}
{"id": "arxiv:1866", "title": "A Binary Classification Framework for Two-Stage Multiple Kernel Learning", "text": "With the advent of kernel methods, automating the task of specifying a suitable kernel has become increasingly important. In this context, the Multiple Kernel Learning (MKL) problem of finding a combination of pre-specified base kernels that is suitable for the task at hand has received significant attention from researchers. In this paper we show that Multiple Kernel Learning can be framed as a standard binary classification problem with additional constraints that ensure the positive definiteness of the learned kernel. Framing MKL in this way has the distinct advantage that it makes it easy to leverage the extensive research in binary classification to develop better performing and more scalable MKL algorithms that are conceptually simpler, and, arguably, more accessible to practitioners. Experiments on nine data sets from different domains show that, despite its simplicity, the proposed technique compares favorably with current leading MKL approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1867", "title": "Incorporating Domain Knowledge in Matching Problems via Harmonic Analysis", "text": "Matching one set of objects to another is a ubiquitous task in machine learning and computer vision that often reduces to some form of the quadratic assignment problem (QAP). The QAP is known to be notoriously hard, both in theory and in practice. Here, we investigate if this difficulty can be mitigated when some additional piece of information is available: (a) that all QAP instances of interest come from the same application, and (b) the correct solution for a set of such QAP instances is given. We propose a new approach to accelerate the solution of QAPs based on learning parameters for a modified objective function from prior QAP instances. A key feature of our approach is that it takes advantage of the algebraic structure of permutations, in conjunction with special methods for optimizing functions over the symmetric group Sn in Fourier space. Experiments show that in practical domains the new method can outperform existing approaches.", "source": "arxiv/ml"}
{"id": "arxiv:1868", "title": "Variational Bayesian Inference with Stochastic Search", "text": "Mean-field variational inference is a method for approximate Bayesian posterior inference. It approximates a full posterior distribution with a factorized set of distributions by maximizing a lower bound on the marginal likelihood. This requires the ability to integrate a sum of terms in the log joint likelihood using this factorized distribution. Often not all integrals are in closed form, which is typically handled by using a lower bound. We present an alternative algorithm based on stochastic optimization that allows for direct optimization of the variational lower bound. This method uses control variates to reduce the variance of the stochastic search gradient, in which existing lower bounds can play an important role. We demonstrate the approach on two non-conjugate models: logistic regression and an approximation to the HDP.", "source": "arxiv/ml"}
{"id": "arxiv:1869", "title": "Exact Maximum Margin Structure Learning of Bayesian Networks", "text": "Recently, there has been much interest in finding globally optimal Bayesian network structures. These techniques were developed for generative scores and can not be directly extended to discriminative scores, as desired for classification. In this paper, we propose an exact method for finding network structures maximizing the probabilistic soft margin, a successfully applied discriminative score. Our method is based on branch-and-bound techniques within a linear programming framework and maintains an any-time solution, together with worst-case sub-optimality bounds. We apply a set of order constraints for enforcing the network structure to be acyclic, which allows a compact problem representation and the use of general-purpose optimization techniques. In classification experiments, our methods clearly outperform generatively trained network structures and compete with support vector machines.", "source": "arxiv/ml"}
{"id": "arxiv:1870", "title": "Sparse Support Vector Infinite Push", "text": "In this paper, we address the problem of embedded feature selection for ranking on top of the list problems. We pose this problem as a regularized empirical risk minimization with $p$-norm push loss function ($p=\\infty$) and sparsity inducing regularizers. We leverage the issues related to this challenging optimization problem by considering an alternating direction method of multipliers algorithm which is built upon proximal operators of the loss function and the regularizer. Our main technical contribution is thus to provide a numerical scheme for computing the infinite push loss function proximal operator. Experimental results on toy, DNA microarray and BCI problems show how our novel algorithm compares favorably to competitors for ranking on top while using fewer variables in the scoring function.", "source": "arxiv/ml"}
{"id": "arxiv:1871", "title": "Copula Mixture Model for Dependency-seeking Clustering", "text": "We introduce a copula mixture model to perform dependency-seeking clustering when co-occurring samples from different data sources are available. The model takes advantage of the great flexibility offered by the copulas framework to extend mixtures of Canonical Correlation Analysis to multivariate data with arbitrary continuous marginal densities. We formulate our model as a non-parametric Bayesian mixture, while providing efficient MCMC inference. Experiments on synthetic and real data demonstrate that the increased flexibility of the copula mixture significantly improves the clustering and the interpretability of the results.", "source": "arxiv/ml"}
{"id": "arxiv:1872", "title": "A Generative Process for Sampling Contractive Auto-Encoders", "text": "The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of the Jacobian of the transformation from input to representation. The corresponding singular values specify how much local variation is plausible in directions associated with the corresponding singular vectors, while remaining in a high-density region of the input space. This paper proposes a procedure for generating samples that are consistent with the local structure captured by a contractive auto-encoder. The associated stochastic process defines a distribution from which one can sample, and which experimentally appears to converge quickly and mix well between modes, compared to Restricted Boltzmann Machines and Deep Belief Networks. The intuitions behind this procedure can also be used to train the second layer of contraction that pools lower-level features and learns to be invariant to the local directions of variation discovered in the first layer. We show that this can help learn and represent invariances present in the data and improve classification error.", "source": "arxiv/ml"}
{"id": "arxiv:1873", "title": "Rethinking Collapsed Variational Bayes Inference for LDA", "text": "We propose a novel interpretation of the collapsed variational Bayes inference with a zero-order Taylor expansion approximation, called CVB0 inference, for latent Dirichlet allocation (LDA). We clarify the properties of the CVB0 inference by using the alpha-divergence. We show that the CVB0 inference is composed of two different divergence projections: alpha=1 and -1. This interpretation will help shed light on CVB0 works.", "source": "arxiv/ml"}
{"id": "arxiv:1874", "title": "Efficient Structured Prediction with Latent Variables for General Graphical Models", "text": "In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient message passing algorithm that is guaranteed to converge. We demonstrate its effectiveness in the tasks of image segmentation as well as 3D indoor scene understanding from single images, showing that our approach is superior to latent structured support vector machines and hidden conditional random fields.", "source": "arxiv/ml"}
{"id": "arxiv:1875", "title": "Large Scale Variational Bayesian Inference for Structured Scale Mixture Models", "text": "Natural image statistics exhibit hierarchical dependencies across multiple scales. Representing such prior knowledge in non-factorial latent tree models can boost performance of image denoising, inpainting, deconvolution or reconstruction substantially, beyond standard factorial \"sparse\" methodology. We derive a large scale approximate Bayesian inference algorithm for linear models with non-factorial (latent tree-structured) scale mixture priors. Experimental results on a range of denoising and inpainting problems demonstrate substantially improved performance compared to MAP estimation or to inference with factorial priors.", "source": "arxiv/ml"}
{"id": "arxiv:1876", "title": "Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation", "text": "We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct classifiers with them. We propose a novel approach that jointly learn the both. Specifically, while the method identifies a feature space where data in the source and the target domains are similarly distributed, it also learns the feature space discriminatively, optimizing an information-theoretic metric as an proxy to the expected misclassification error on the target domain. We show how this optimization can be effectively carried out with simple gradient-based methods and how hyperparameters can be cross-validated without demanding any labeled data from the target domain. Empirical studies on benchmark tasks of object recognition and sentiment analysis validated our modeling assumptions and demonstrated significant improvement of our method over competing ones in classification accuracies.", "source": "arxiv/ml"}
{"id": "arxiv:1877", "title": "Gap Filling in the Plant Kingdom---Trait Prediction Using Hierarchical Probabilistic Matrix Factorization", "text": "Plant traits are a key to understanding and predicting the adaptation of ecosystems to environmental changes, which motivates the TRY project aiming at constructing a global database for plant traits and becoming a standard resource for the ecological community. Despite its unprecedented coverage, a large percentage of missing data substantially constrains joint trait analysis. Meanwhile, the trait data is characterized by the hierarchical phylogenetic structure of the plant kingdom. While factorization based matrix completion techniques have been widely used to address the missing data problem, traditional matrix factorization methods are unable to leverage the phylogenetic structure. We propose hierarchical probabilistic matrix factorization (HPMF), which effectively uses hierarchical phylogenetic information for trait prediction. We demonstrate HPMF's high accuracy, effectiveness of incorporating hierarchical structure and ability to capture trait correlation through experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1878", "title": "Predicting Preference Flips in Commerce Search", "text": "Traditional approaches to ranking in web search follow the paradigm of rank-by-score: a learned function gives each query-URL combination an absolute score and URLs are ranked according to this score. This paradigm ensures that if the score of one URL is better than another then one will always be ranked higher than the other. Scoring contradicts prior work in behavioral economics that showed that users' preferences between two items depend not only on the items but also on the presented alternatives. Thus, for the same query, users' preference between items A and B depends on the presence/absence of item C. We propose a new model of ranking, the Random Shopper Model, that allows and explains such behavior. In this model, each feature is viewed as a Markov chain over the items to be ranked, and the goal is to find a weighting of the features that best reflects their importance. We show that our model can be learned under the empirical risk minimization framework, and give an efficient learning algorithm. Experiments on commerce search logs demonstrate that our algorithm outperforms scoring-based approaches including regression and listwise ranking.", "source": "arxiv/ml"}
{"id": "arxiv:1879", "title": "A Topic Model for Melodic Sequences", "text": "We examine the problem of learning a probabilistic model for melody directly from musical sequences belonging to the same genre. This is a challenging task as one needs to capture not only the rich temporal structure evident in music, but also the complex statistical dependencies among different music components. To address this problem we introduce the Variable-gram Topic Model, which couples the latent topic formalism with a systematic model for contextual information. We evaluate the model on next-step prediction. Additionally, we present a novel way of model evaluation, where we directly compare model samples with data sequences using the Maximum Mean Discrepancy of string kernels, to assess how close is the model distribution to the data distribution. We show that the model has the highest performance under both evaluation measures when compared to LDA, the Topic Bigram and related non-topic models.", "source": "arxiv/ml"}
{"id": "arxiv:1880", "title": "Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss", "text": "We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, of all convex loss functions, for the misclassification error rate of the resulting linear predictor in terms of the best possible margin error rate. We also provide lower bounds for specific convex surrogates that show how different commonly used losses qualitatively differ from each other.", "source": "arxiv/ml"}
{"id": "arxiv:1881", "title": "Isoelastic Agents and Wealth Updates in Machine Learning Markets", "text": "Recently, prediction markets have shown considerable promise for developing flexible mechanisms for machine learning. In this paper, agents with isoelastic utilities are considered. It is shown that the costs associated with homogeneous markets of agents with isoelastic utilities produce equilibrium prices corresponding to alpha-mixtures, with a particular form of mixing component relating to each agent's wealth. We also demonstrate that wealth accumulation for logarithmic and other isoelastic agents (through payoffs on prediction of training targets) can implement both Bayesian model updates and mixture weight updates by imposing different market payoff structures. An iterative algorithm is given for market equilibrium computation. We demonstrate that inhomogeneous markets of agents with isoelastic utilities outperform state of the art aggregate classifiers such as random forests, as well as single classifiers (neural networks, decision trees) on a number of machine learning benchmarks, and show that isoelastic combination methods are generally better than their logarithmic counterparts.", "source": "arxiv/ml"}
{"id": "arxiv:1882", "title": "Statistical Linear Estimation with Penalized Estimators: an Application to Reinforcement Learning", "text": "Motivated by value function estimation in reinforcement learning, we study statistical linear inverse problems, i.e., problems where the coefficients of a linear system to be solved are observed in noise. We consider penalized estimators, where performance is evaluated using a matrix-weighted two-norm of the defect of the estimator measured with respect to the true, unknown coefficients. Two objective functions are considered depending whether the error of the defect measured with respect to the noisy coefficients is squared or unsquared. We propose simple, yet novel and theoretically well-founded data-dependent choices for the regularization parameters for both cases that avoid data-splitting. A distinguishing feature of our analysis is that we derive deterministic error bounds in terms of the error of the coefficients, thus allowing the complete separation of the analysis of the stochastic properties of these errors. We show that our results lead to new insights and bounds for linear value function estimation in reinforcement learning.", "source": "arxiv/ml"}
{"id": "arxiv:1883", "title": "Deep Lambertian Networks", "text": "Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it for recognition. The object albedo and surface normals are examples of such representations. In this paper, we introduce a multilayer generative model where the latent variables include the albedo, surface normals, and the light source. Combining Deep Belief Nets with the Lambertian reflectance assumption, our model can learn good priors over the albedo from 2D images. Illumination variations can be explained by changing only the lighting latent variable in our model. By transferring learned knowledge from similar objects, albedo and surface normals estimation from a single image is possible in our model. Experiments demonstrate that our model is able to generalize as well as improve over standard baselines in one-shot face recognition.", "source": "arxiv/ml"}
{"id": "arxiv:1884", "title": "Agglomerative Bregman Clustering", "text": "This manuscript develops the theory of agglomerative clustering with Bregman divergences. Geometric smoothing techniques are developed to deal with degenerate clusters. To allow for cluster models based on exponential families with overcomplete representations, Bregman divergences are developed for nondifferentiable convex functions.", "source": "arxiv/ml"}
{"id": "arxiv:1885", "title": "Small-sample Brain Mapping: Sparse Recovery on Spatially Correlated Designs with Randomization and Clustering", "text": "Functional neuroimaging can measure the brain?s response to an external stimulus. It is used to perform brain mapping: identifying from these observations the brain regions involved. This problem can be cast into a linear supervised learning task where the neuroimaging data are used as predictors for the stimulus. Brain mapping is then seen as a support recovery problem. On functional MRI (fMRI) data, this problem is particularly challenging as i) the number of samples is small due to limited acquisition time and ii) the variables are strongly correlated. We propose to overcome these difficulties using sparse regression models over new variables obtained by clustering of the original variables. The use of randomization techniques, e.g. bootstrap samples, and clustering of the variables improves the recovery properties of sparse methods. We demonstrate the benefit of our approach on an extensive simulation study as well as two fMRI datasets.", "source": "arxiv/ml"}
{"id": "arxiv:1886", "title": "Online Alternating Direction Method", "text": "Online optimization has emerged as powerful tool in large scale optimization. In this paper, we introduce efficient online algorithms based on the alternating directions method (ADM). We introduce a new proof technique for ADM in the batch setting, which yields the O(1/T) convergence rate of ADM and forms the basis of regret analysis in the online setting. We consider two scenarios in the online setting, based on whether the solution needs to lie in the feasible set or not. In both settings, we establish regret bounds for both the objective function as well as constraint violation for general and strongly convex functions. Preliminary results are presented to illustrate the performance of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1887", "title": "Monte Carlo Bayesian Reinforcement Learning", "text": "Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them. This paper presents Monte Carlo BRL (MC-BRL), a simple and general approach to BRL. MC-BRL samples a priori a finite set of hypotheses for the model parameter values and forms a discrete partially observable Markov decision process (POMDP) whose state space is a cross product of the state space for the reinforcement learning task and the sampled model parameter space. The POMDP does not require conjugate distributions for belief representation, as earlier works do, and can be solved relatively easily with point-based approximation algorithms. MC-BRL naturally handles both fully and partially observable worlds. Theoretical and experimental results show that the discrete POMDP approximates the underlying BRL task well with guaranteed performance.", "source": "arxiv/ml"}
{"id": "arxiv:1888", "title": "Conditional Sparse Coding and Grouped Multivariate Regression", "text": "We study the problem of multivariate regression where the data are naturally grouped, and a regression matrix is to be estimated for each group. We propose an approach in which a dictionary of low rank parameter matrices is estimated across groups, and a sparse linear combination of the dictionary elements is estimated to form a model within each group. We refer to the method as conditional sparse coding since it is a coding procedure for the response vectors Y conditioned on the covariate vectors X. This approach captures the shared information across the groups while adapting to the structure within each group. It exploits the same intuition behind sparse coding that has been successfully developed in computer vision and computational neuroscience. We propose an algorithm for conditional sparse coding, analyze its theoretical properties in terms of predictive accuracy, and present the results of simulation and brain imaging experiments that compare the new technique to reduced rank regression.", "source": "arxiv/ml"}
{"id": "arxiv:1889", "title": "The Greedy Miser: Learning under Test-time Budgets", "text": "As machine learning algorithms enter applications in industrial settings, there is increased interest in controlling their cpu-time during testing. The cpu-time consists of the running time of the algorithm and the extraction time of the features. The latter can vary drastically when the feature set is diverse. In this paper, we propose an algorithm, the Greedy Miser, that incorporates the feature extraction cost during training to explicitly minimize the cpu-time during testing. The algorithm is a straightforward extension of stage-wise regression and is equally suitable for regression or multi-class classification. Compared to prior work, it is significantly more cost-effective and scales to larger data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1890", "title": "Smoothness and Structure Learning by Proxy", "text": "As data sets grow in size, the ability of learning methods to find structure in them is increasingly hampered by the time needed to search the large spaces of possibilities and generate a score for each that takes all of the observed data into account. For instance, Bayesian networks, the model chosen in this paper, have a super-exponentially large search space for a fixed number of variables. One possible method to alleviate this problem is to use a proxy, such as a Gaussian Process regressor, in place of the true scoring function, training it on a selection of sampled networks. We prove here that the use of such a proxy is well-founded, as we can bound the smoothness of a commonly-used scoring function for Bayesian network structure learning. We show here that, compared to an identical search strategy using the network?s exact scores, our proxy-based search is able to get equivalent or better scores on a number of data sets in a fraction of the time.", "source": "arxiv/ml"}
{"id": "arxiv:1891", "title": "Adaptive Canonical Correlation Analysis Based On Matrix Manifolds", "text": "In this paper, we formulate the Canonical Correlation Analysis (CCA) problem on matrix manifolds. This framework provides a natural way for dealing with matrix constraints and tools for building efficient algorithms even in an adaptive setting. Finally, an adaptive CCA algorithm is proposed and applied to a change detection problem in EEG signals.", "source": "arxiv/ml"}
{"id": "arxiv:1892", "title": "Hierarchical Exploration for Accelerating Contextual Bandits", "text": "Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically reduces the amount of exploration required. Intuitively, user preferences can be reasonably embedded in a coarse low-dimensional feature space that can be explored efficiently, requiring exploration in the high-dimensional space only as necessary. We introduce a bandit algorithm that explores within this coarse-to-fine spectrum, and prove performance guarantees that depend on how well the coarse space captures the user's preferences. We demonstrate substantial improvement over conventional bandit algorithms through extensive simulation as well as a live user study in the setting of personalized news recommendation.", "source": "arxiv/ml"}
{"id": "arxiv:1893", "title": "Regularizers versus Losses for Nonlinear Dimensionality Reduction: A Factored View with New Convex Relaxations", "text": "We demonstrate that almost all non-parametric dimensionality reduction methods can be expressed by a simple procedure: regularized loss minimization plus singular value truncation. By distinguishing the role of the loss and regularizer in such a process, we recover a factored perspective that reveals some gaps in the current literature. Beyond identifying a useful new loss for manifold unfolding, a key contribution is to derive new convex regularizers that combine distance maximization with rank reduction. These regularizers can be applied to any loss.", "source": "arxiv/ml"}
{"id": "arxiv:1894", "title": "Lognormal and Gamma Mixed Negative Binomial Regression", "text": "In regression analysis of counts, a lack of simple and efficient algorithms for posterior computation has made Bayesian approaches appear unattractive and thus underdeveloped. We propose a lognormal and gamma mixed negative binomial (NB) regression model for counts, and present efficient closed-form Bayesian inference; unlike conventional Poisson models, the proposed approach has two free parameters to include two different kinds of random effects, and allows the incorporation of prior information, such as sparsity in the regression coefficients. By placing a gamma distribution prior on the NB dispersion parameter r, and connecting a lognormal distribution prior with the logit of the NB probability parameter p, efficient Gibbs sampling and variational Bayes inference are both developed. The closed-form updates are obtained by exploiting conditional conjugacy via both a compound Poisson representation and a Polya-Gamma distribution based data augmentation approach. The proposed Bayesian inference can be implemented routinely, while being easily generalizable to more complex settings involving multivariate dependence structures. The algorithms are illustrated using real examples.", "source": "arxiv/ml"}
{"id": "arxiv:1895", "title": "Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations", "text": "This paper analyzes the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al, 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, Srinivas et al proved that the regret vanishes at the approximate rate of $O(1/\\sqrt{t})$, where t is the number of observations. To complement their result, we attack the deterministic case and attain a much faster exponential convergence rate. Under some regularity assumptions, we show that the regret decreases asymptotically according to $O(e^{-\\frac{\\tau t}{(\\ln t)^{d/4}}})$ with high probability. Here, d is the dimension of the search space and tau is a constant that depends on the behaviour of the objective function near its global maximum.", "source": "arxiv/ml"}
{"id": "arxiv:1896", "title": "Batch Active Learning via Coordinated Matching", "text": "Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an entire batch of examples at once, for example, when labels can be acquired in parallel. This motivates us to study batch active learning, which iteratively selects batches of $k>1$ examples to be labeled. We propose a novel batch active learning method that leverages the availability of high-quality and efficient sequential active-learning policies by attempting to approximate their behavior when applied for $k$ steps. Specifically, our algorithm first uses Monte-Carlo simulation to estimate the distribution of unlabeled examples selected by a sequential policy over $k$ step executions. The algorithm then attempts to select a set of $k$ examples that best matches this distribution, leading to a combinatorial optimization problem that we term \"bounded coordinated matching\". While we show this problem is NP-hard in general, we give an efficient greedy solution, which inherits approximation bounds from supermodular minimization theory. Our experimental results on eight benchmark datasets show that the proposed approach is highly effective", "source": "arxiv/ml"}
{"id": "arxiv:1897", "title": "Bayesian Conditional Cointegration", "text": "Cointegration is an important topic for time-series, and describes a relationship between two series in which a linear combination is stationary. Classically, the test for cointegration is based on a two stage process in which first the linear relation between the series is estimated by Ordinary Least Squares. Subsequently a unit root test is performed on the residuals. A well-known deficiency of this classical approach is that it can lead to erroneous conclusions about the presence of cointegration. As an alternative, we present a framework for estimating whether cointegration exists using Bayesian inference which is empirically superior to the classical approach. Finally, we apply our technique to model segmented cointegration in which cointegration may exist only for limited time. In contrast to previous approaches our model makes no restriction on the number of possible cointegration segments.", "source": "arxiv/ml"}
{"id": "arxiv:1898", "title": "Output Space Search for Structured Prediction", "text": "We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a time-bounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the search. This framework can be instantiated for a wide range of search spaces and search procedures, and easily incorporates arbitrary structured-prediction loss functions. In this paper, we make two main technical contributions. First, we define the limited-discrepancy search space over structured outputs, which is able to leverage powerful classification learning algorithms to improve the search space quality. Second, we give a generic cost function learning approach, where the key idea is to learn a cost function that attempts to mimic the behavior of conducting searches guided by the true loss function. Our experiments on six benchmark domains demonstrate that using our framework with only a small amount of search is sufficient for significantly improving on state-of-the-art structured-prediction performance.", "source": "arxiv/ml"}
{"id": "arxiv:1899", "title": "On the Sample Complexity of Reinforcement Learning with a Generative Model", "text": "We consider the problem of learning the optimal action-value function in the discounted-reward Markov decision processes (MDPs). We prove a new PAC bound on the sample-complexity of model-based value iteration algorithm in the presence of the generative model, which indicates that for an MDP with N state-action pairs and the discount factor \\gamma\\in[0,1) only O(N\\log(N/\\delta)/((1-\\gamma)^3\\epsilon^2)) samples are required to find an \\epsilon-optimal estimation of the action-value function with the probability 1-\\delta. We also prove a matching lower bound of \\Theta (N\\log(N/\\delta)/((1-\\gamma)^3\\epsilon^2)) on the sample complexity of estimating the optimal action-value function by every RL algorithm. To the best of our knowledge, this is the first matching result on the sample complexity of estimating the optimal (action-) value function in which the upper bound matches the lower bound of RL in terms of N, \\epsilon, \\delta and 1/(1-\\gamma). Also, both our lower bound and our upper bound significantly improve on the state-of-the-art in terms of 1/(1-\\gamma).", "source": "arxiv/ml"}
{"id": "arxiv:1900", "title": "Learning Object Arrangements in 3D Scenes using Human Context", "text": "We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objects. We design appropriate density functions based on 3D spatial features to capture this. We learn the distribution of human poses in a scene using a variant of the Dirichlet process mixture model that allows sharing of the density function parameters across the same object types. Then we can reason about arrangements of the objects in the room based on these meaningful human poses. In our extensive experiments on 20 different rooms with a total of 47 objects, our algorithm predicted correct placements with an average error of 1.6 meters from ground truth. In arranging five real scenes, it received a score of 4.3/5 compared to 3.7 for the best baseline method.", "source": "arxiv/ml"}
{"id": "arxiv:1901", "title": "An Iterative Locally Linear Embedding Algorithm", "text": "Local Linear embedding (LLE) is a popular dimension reduction method. In this paper, we first show LLE with nonnegative constraint is equivalent to the widely used Laplacian embedding. We further propose to iterate the two steps in LLE repeatedly to improve the results. Thirdly, we relax the kNN constraint of LLE and present a sparse similarity learning algorithm. The final Iterative LLE combines these three improvements. Extensive experiment results show that iterative LLE algorithm significantly improve both classification and clustering results.", "source": "arxiv/ml"}
{"id": "arxiv:1902", "title": "Estimating the Hessian by Back-propagating Curvature", "text": "In this work we develop Curvature Propagation (CP), a general technique for efficiently computing unbiased approximations of the Hessian of any function that is computed using a computational graph. At the cost of roughly two gradient evaluations, CP can give a rank-1 approximation of the whole Hessian, and can be repeatedly applied to give increasingly precise unbiased estimates of any or all of the entries of the Hessian. Of particular interest is the diagonal of the Hessian, for which no general approach is known to exist that is both efficient and accurate. We show in experiments that CP turns out to work well in practice, giving very accurate estimates of the Hessian of neural networks, for example, with a relatively small amount of work. We also apply CP to Score Matching, where a diagonal of a Hessian plays an integral role in the Score Matching objective, and where it is usually computed exactly using inefficient algorithms which do not scale to larger and more complex models.", "source": "arxiv/ml"}
{"id": "arxiv:1903", "title": "Bayesian Efficient Multiple Kernel Learning", "text": "Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on the computational efficiency issue. However, it is still not feasible to combine many kernels using existing Bayesian approaches due to their high time complexity. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation, which allows us to combine hundreds or thousands of kernels very efficiently. We briefly explain how the proposed method can be extended for multiclass learning and semi-supervised learning. Experiments with large numbers of kernels on benchmark data sets show that our inference method is quite fast, requiring less than a minute. On one bioinformatics and three image recognition data sets, our method outperforms previously reported results with better generalization performance.", "source": "arxiv/ml"}
{"id": "arxiv:1904", "title": "Semi-Supervised Collective Classification via Hybrid Label Regularization", "text": "Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for \"collective classification\" (CC) often increase accuracy for such data graphs, but usually require a fully-labeled training graph. In contrast, we examine how to improve the semi-supervised learning of CC models when given only a sparsely-labeled graph, a common situation. We first describe how to use novel combinations of classifiers to exploit the different characteristics of the relational features vs. the non-relational features. We also extend the ideas of \"label regularization\" to such hybrid classifiers, enabling them to leverage the unlabeled data to bias the learning process. We find that these techniques, which are efficient and easy to implement, significantly increase accuracy on three real datasets. In addition, our results explain conflicting findings from prior related studies.", "source": "arxiv/ml"}
{"id": "arxiv:1905", "title": "Variational Inference in Non-negative Factorial Hidden Markov Models for Efficient Audio Source Separation", "text": "The past decade has seen substantial work on the use of non-negative matrix factorization and its probabilistic counterparts for audio source separation. Although able to capture audio spectral structure well, these models neglect the non-stationarity and temporal dynamics that are important properties of audio. The recently proposed non-negative factorial hidden Markov model (N-FHMM) introduces a temporal dimension and improves source separation performance. However, the factorial nature of this model makes the complexity of inference exponential in the number of sound sources. Here, we present a Bayesian variant of the N-FHMM suited to an efficient variational inference algorithm, whose complexity is linear in the number of sound sources. Our algorithm performs comparably to exact inference in the original N-FHMM but is significantly faster. In typical configurations of the N-FHMM, our method achieves around a 30x increase in speed.", "source": "arxiv/ml"}
{"id": "arxiv:1906", "title": "Inferring Latent Structure From Mixed Real and Categorical Relational Data", "text": "We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each subject and attribute is characterized by a latent binary feature vector, and an inferred matrix maps each row-column pair of binary feature vectors to an observed matrix element. The latent binary features of the rows are modeled via a multivariate Gaussian distribution with low-rank covariance matrix, and the Gaussian random variables are mapped to latent binary features via a probit link. The same type construction is applied jointly to the columns. The model infers latent, low-dimensional binary features associated with each row and each column, as well correlation structure between all rows and between all columns.", "source": "arxiv/ml"}
{"id": "arxiv:1907", "title": "A Combinatorial Algebraic Approach for the Identifiability of Low-Rank Matrix Completion", "text": "In this paper, we review the problem of matrix completion and expose its intimate relations with algebraic geometry, combinatorics and graph theory. We present the first necessary and sufficient combinatorial conditions for matrices of arbitrary rank to be identifiable from a set of matrix entries, yielding theoretical constraints and new algorithms for the problem of matrix completion. We conclude by algorithmically evaluating the tightness of the given conditions and algorithms for practically relevant matrix sizes, showing that the algebraic-combinatoric approach can lead to improvements over state-of-the-art matrix completion methods.", "source": "arxiv/ml"}
{"id": "arxiv:1908", "title": "On Causal and Anticausal Learning", "text": "We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning. We argue that causal knowledge may facilitate some approaches for a given problem, and rule out others. In particular, we formulate a hypothesis for when semi-supervised learning can help, and corroborate it with empirical results.", "source": "arxiv/ml"}
{"id": "arxiv:1909", "title": "An Efficient Approach to Sparse Linear Discriminant Analysis", "text": "We present a novel approach to the formulation and the resolution of sparse Linear Discriminant Analysis (LDA). Our proposal, is based on penalized Optimal Scoring. It has an exact equivalence with penalized LDA, contrary to the multi-class approaches based on the regression of class indicator that have been proposed so far. Sparsity is obtained thanks to a group-Lasso penalty that selects the same features in all discriminant directions. Our experiments demonstrate that this approach generates extremely parsimonious models without compromising prediction performances. Besides prediction, the resulting sparse discriminant directions are also amenable to low-dimensional representations of data. Our algorithm is highly efficient for medium to large number of variables, and is thus particularly well suited to the analysis of gene expression data.", "source": "arxiv/ml"}
{"id": "arxiv:1910", "title": "Compositional Planning Using Optimal Option Models", "text": "In this paper we introduce a framework for option model composition. Option models are temporal abstractions that, like macro-operators in classical planning, jump directly from a start state to an end state. Prior work has focused on constructing option models from primitive actions, by intra-option model learning; or on using option models to construct a value function, by inter-option planning. We present a unified view of intra- and inter-option model learning, based on a major generalisation of the Bellman equation. Our fundamental operation is the recursive composition of option models into other option models. This key idea enables compositional planning over many levels of abstraction. We illustrate our framework using a dynamic programming algorithm that simultaneously constructs optimal option models for multiple subgoals, and also searches over those option models to provide rapid progress towards other subgoals.", "source": "arxiv/ml"}
{"id": "arxiv:1911", "title": "Estimation of Simultaneously Sparse and Low Rank Matrices", "text": "The paper introduces a penalized matrix estimation procedure aiming at solutions which are sparse and low-rank at the same time. Such structures arise in the context of social networks or protein interactions where underlying graphs have adjacency matrices which are block-diagonal in the appropriate basis. We introduce a convex mixed penalty which involves $\\ell_1$-norm and trace norm simultaneously. We obtain an oracle inequality which indicates how the two effects interact according to the nature of the target matrix. We bound generalization error in the link prediction problem. We also develop proximal descent strategies to solve the optimization problem efficiently and evaluate performance on synthetic and real data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1912", "title": "A Split-Merge Framework for Comparing Clusterings", "text": "Clustering evaluation measures are frequently used to evaluate the performance of algorithms. However, most measures are not properly normalized and ignore some information in the inherent structure of clusterings. We model the relation between two clusterings as a bipartite graph and propose a general component-based decomposition formula based on the components of the graph. Most existing measures are examples of this formula. In order to satisfy consistency in the component, we further propose a split-merge framework for comparing clusterings of different data sets. Our framework gives measures that are conditionally normalized, and it can make use of data point information, such as feature vectors and pairwise distances. We use an entropy-based instance of the framework and a coreference resolution data set to demonstrate empirically the utility of our framework over other measures.", "source": "arxiv/ml"}
{"id": "arxiv:1913", "title": "Similarity Learning for Provably Accurate Sparse Linear Classification", "text": "In recent years, the crucial importance of metrics in machine learning algorithms has led to an increasing interest for optimizing distance and similarity functions. Most of the state of the art focus on learning Mahalanobis distances (requiring to fulfill a constraint of positive semi-definiteness) for use in a local k-NN algorithm. However, no theoretical link is established between the learned metrics and their performance in classification. In this paper, we make use of the formal framework of good similarities introduced by Balcan et al. to design an algorithm for learning a non PSD linear similarity optimized in a nonlinear feature space, which is then used to build a global linear classifier. We show that our approach has uniform stability and derive a generalization bound on the classification error. Experiments performed on various datasets confirm the effectiveness of our approach compared to state-of-the-art methods and provide evidence that (i) it is fast, (ii) robust to overfitting and (iii) produces very sparse classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:1914", "title": "Discovering Support and Affiliated Features from Very High Dimensions", "text": "In this paper, a novel learning paradigm is presented to automatically identify groups of informative and correlated features from very high dimensions. Specifically, we explicitly incorporate correlation measures as constraints and then propose an efficient embedded feature selection method using recently developed cutting plane strategy. The benefits of the proposed algorithm are two-folds. First, it can identify the optimal discriminative and uncorrelated feature subset to the output labels, denoted here as Support Features, which brings about significant improvements in prediction performance over other state of the art feature selection methods considered in the paper. Second, during the learning process, the underlying group structures of correlated features associated with each support feature, denoted as Affiliated Features, can also be discovered without any additional cost. These affiliated features serve to improve the interpretations on the learning tasks. Extensive empirical studies on both synthetic and very high dimensional real-world datasets verify the validity and efficiency of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1915", "title": "Maximum Margin Output Coding", "text": "In this paper we study output coding for multi-label prediction. For a multi-label output coding to be discriminative, it is important that codewords for different label vectors are significantly different from each other. In the meantime, unlike in traditional coding theory, codewords in output coding are to be predicted from the input, so it is also critical to have a predictable label encoding. To find output codes that are both discriminative and predictable, we first propose a max-margin formulation that naturally captures these two properties. We then convert it to a metric learning formulation, but with an exponentially large number of constraints as commonly encountered in structured prediction problems. Without a label structure for tractable inference, we use overgenerating (i.e., relaxation) techniques combined with the cutting plane method for optimization. In our empirical study, the proposed output coding scheme outperforms a variety of existing multi-label prediction methods for image, text and music classification.", "source": "arxiv/ml"}
{"id": "arxiv:1916", "title": "The Landmark Selection Method for Multiple Output Prediction", "text": "Conditional modeling x \\to y is a central problem in machine learning. A substantial research effort is devoted to such modeling when x is high dimensional. We consider, instead, the case of a high dimensional y, where x is either low dimensional or high dimensional. Our approach is based on selecting a small subset y_L of the dimensions of y, and proceed by modeling (i) x \\to y_L and (ii) y_L \\to y. Composing these two models, we obtain a conditional model x \\to y that possesses convenient statistical properties. Multi-label classification and multivariate regression experiments on several datasets show that this model outperforms the one vs. all approach as well as several sophisticated multiple output prediction methods.", "source": "arxiv/ml"}
{"id": "arxiv:1917", "title": "A Dantzig Selector Approach to Temporal Difference Learning", "text": "LSTD is a popular algorithm for value function approximation. Whenever the number of features is larger than the number of samples, it must be paired with some form of regularization. In particular, L1-regularization methods tend to perform feature selection by promoting sparsity, and thus, are well-suited for high-dimensional problems. However, since LSTD is not a simple regression algorithm, but it solves a fixed--point problem, its integration with L1-regularization is not straightforward and might come with some drawbacks (e.g., the P-matrix assumption for LASSO-TD). In this paper, we introduce a novel algorithm obtained by integrating LSTD with the Dantzig Selector. We investigate the performance of the proposed algorithm and its relationship with the existing regularized approaches, and show how it addresses some of their drawbacks.", "source": "arxiv/ml"}
{"id": "arxiv:1918", "title": "Cross Language Text Classification via Subspace Co-Regularized Multi-View Learning", "text": "In many multilingual text classification problems, the documents in different languages often share the same set of categories. To reduce the labeling cost of training a classification model for each individual language, it is important to transfer the label knowledge gained from one language to another language by conducting cross language classification. In this paper we develop a novel subspace co-regularized multi-view learning method for cross language text classification. This method is built on parallel corpora produced by machine translation. It jointly minimizes the training error of each classifier in each language while penalizing the distance between the subspace representations of parallel documents. Our empirical study on a large set of cross language text classification tasks shows the proposed method consistently outperforms a number of inductive methods, domain adaptation methods, and multi-view learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:1919", "title": "Modeling Images using Transformed Indian Buffet Processes", "text": "Latent feature models are attractive for image modeling, since images generally contain multiple objects. However, many latent feature models ignore that objects can appear at different locations or require pre-segmentation of images. While the transformed Indian buffet process (tIBP) provides a method for modeling transformation-invariant features in unsegmented binary images, its current form is inappropriate for real images because of its computational cost and modeling assumptions. We combine the tIBP with likelihoods appropriate for real images and develop an efficient inference, using the cross-correlation between images and features, that is theoretically and empirically faster than existing inference techniques. Our method discovers reasonable components and achieve effective image reconstruction in natural images.", "source": "arxiv/ml"}
{"id": "arxiv:1920", "title": "Subgraph Matching Kernels for Attributed Graphs", "text": "We propose graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs. While recently proposed kernels based on common subgraphs (Wale et al., 2008; Shervashidze et al., 2009) in general can not be applied to attributed graphs, our approach allows to rate mappings of subgraphs by a flexible scoring scheme comparing vertex and edge attributes by kernels. We show that subgraph matching kernels generalize several known kernels. To compute the kernel we propose a graph-theoretical algorithm inspired by a classical relation between common subgraphs of two graphs and cliques in their product graph observed by Levi (1973). Encouraging experimental results on a classification task of real-world graphs are presented.", "source": "arxiv/ml"}
{"id": "arxiv:1921", "title": "Apprenticeship Learning for Model Parameters of Partially Observable Environments", "text": "We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialogue system. We show that we can extract information about the environment model by inferring action selection process behind the demonstration, under the assumption that the expert is choosing optimal actions based on knowledge of the true model of the target environment. Proposed algorithms can achieve more accurate estimates of POMDP parameters and better policies from a short demonstration, compared to methods that learns only from the reaction from the environment.", "source": "arxiv/ml"}
{"id": "arxiv:1922", "title": "Greedy Algorithms for Sparse Reinforcement Learning", "text": "Feature selection and regularization are becoming increasingly prominent tools in the efforts of the reinforcement learning (RL) community to expand the reach and applicability of RL. One approach to the problem of feature selection is to impose a sparsity-inducing form of regularization on the learning method. Recent work on $L_1$ regularization has adapted techniques from the supervised learning literature for use with RL. Another approach that has received renewed attention in the supervised learning community is that of using a simple algorithm that greedily adds new features. Such algorithms have many of the good properties of the $L_1$ regularization methods, while also being extremely efficient and, in some cases, allowing theoretical guarantees on recovery of the true form of a sparse target function from sampled data. This paper considers variants of orthogonal matching pursuit (OMP) applied to reinforcement learning. The resulting algorithms are analyzed and compared experimentally with existing $L_1$ regularized approaches. We demonstrate that perhaps the most natural scenario in which one might hope to achieve sparse recovery fails; however, one variant, OMP-BRM, provides promising theoretical guarantees under certain assumptions on the feature dictionary. Another variant, OMP-TD, empirically outperforms prior methods both in approximation accuracy and efficiency on several benchmark problems.", "source": "arxiv/ml"}
{"id": "arxiv:1923", "title": "Flexible Modeling of Latent Task Structures in Multitask Learning", "text": "Multitask learning algorithms are typically designed assuming some fixed, a priori known latent structure shared by all the tasks. However, it is usually unclear what type of latent task structure is the most appropriate for a given multitask learning problem. Ideally, the \"right\" latent task structure should be learned in a data-driven manner. We present a flexible, nonparametric Bayesian model that posits a mixture of factor analyzers structure on the tasks. The nonparametric aspect makes the model expressive enough to subsume many existing models of latent task structures (e.g, mean-regularized tasks, clustered tasks, low-rank or linear/non-linear subspace assumption on tasks, etc.). Moreover, it can also learn more general task structures, addressing the shortcomings of such models. We present a variational inference algorithm for our model. Experimental results on synthetic and real-world datasets, on both regression and classification problems, demonstrate the effectiveness of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:1924", "title": "An Adaptive Algorithm for Finite Stochastic Partial Monitoring", "text": "We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both \"easy\" and \"hard\" problems. For easy problems, it additionally achieves logarithmic individual regret. Most importantly, the algorithm is adaptive in the sense that if the opponent strategy is in an \"easy region\" of the strategy space then the regret grows as if the problem was easy. As an implication, we show that under some reasonable additional assumptions, the algorithm enjoys an O(\\sqrt{T}) regret in Dynamic Pricing, proven to be hard by Bartok et al. (2011).", "source": "arxiv/ml"}
{"id": "arxiv:1925", "title": "The Nonparanormal SKEPTIC", "text": "We propose a semiparametric approach, named nonparanormal skeptic, for estimating high dimensional undirected graphical models. In terms of modeling, we consider the nonparanormal family proposed by Liu et al (2009). In terms of estimation, we exploit nonparametric rank-based correlation coefficient estimators including the Spearman's rho and Kendall's tau. In high dimensional settings, we prove that the nonparanormal skeptic achieves the optimal parametric rate of convergence in both graph and parameter estimation. This result suggests that the nonparanormal graphical models are a safe replacement of the Gaussian graphical models, even when the data are Gaussian.", "source": "arxiv/ml"}
{"id": "arxiv:1926", "title": "A concentration theorem for projections", "text": "X in R^D has mean zero and finite second moments. We show that there is a precise sense in which almost all linear projections of X into R^d (for d < D) look like a scale-mixture of spherical Gaussians -- specifically, a mixture of distributions N(0, sigma^2 I_d) where the weight of the particular sigma component is P (| X |^2 = sigma^2 D). The extent of this effect depends upon the ratio of d to D, and upon a particular coefficient of eccentricity of X's distribution. We explore this result in a variety of experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1927", "title": "An Empirical Comparison of Algorithms for Aggregating Expert Predictions", "text": "Predicting the outcomes of future events is a challenging problem for which a variety of solution methods have been explored and attempted. We present an empirical comparison of a variety of online and offline adaptive algorithms for aggregating experts' predictions of the outcomes of five years of US National Football League games (1319 games) using expert probability elicitations obtained from an Internet contest called ProbabilitySports. We find that it is difficult to improve over simple averaging of the predictions in terms of prediction accuracy, but that there is room for improvement in quadratic loss. Somewhat surprisingly, a Bayesian estimation algorithm which estimates the variance of each expert's prediction exhibits the most consistent superior performance over simple averaging among our collection of algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1928", "title": "Discriminative Learning via Semidefinite Probabilistic Models", "text": "Discriminative linear models are a popular tool in machine learning. These can be generally divided into two types: The first is linear classifiers, such as support vector machines, which are well studied and provide state-of-the-art results. One shortcoming of these models is that their output (known as the 'margin') is not calibrated, and cannot be translated naturally into a distribution over the labels. Thus, it is difficult to incorporate such models as components of larger systems, unlike probabilistic based approaches. The second type of approach constructs class conditional distributions using a nonlinearity (e.g. log-linear models), but is occasionally worse in terms of classification error. We propose a supervised learning method which combines the best of both approaches. Specifically, our method provides a distribution over the labels, which is a linear function of the model parameters. As a consequence, differences between probabilities are linear functions, a property which most probabilistic models (e.g. log-linear) do not have. Our model assumes that classes correspond to linear subspaces (rather than to half spaces). Using a relaxed projection operator, we construct a measure which evaluates the degree to which a given vector 'belongs' to a subspace, resulting in a distribution over labels. Interestingly, this view is closely related to similar concepts in quantum detection theory. The resulting models can be trained either to maximize the margin or to optimize average likelihood measures. The corresponding optimization problems are semidefinite programs which can be solved efficiently. We illustrate the performance of our algorithm on real world datasets, and show that it outperforms 2nd order kernel methods.", "source": "arxiv/ml"}
{"id": "arxiv:1929", "title": "Gene Expression Time Course Clustering with Countably Infinite Hidden Markov Models", "text": "Most existing approaches to clustering gene expression time course data treat the different time points as independent dimensions and are invariant to permutations, such as reversal, of the experimental time course. Approaches utilizing HMMs have been shown to be helpful in this regard, but are hampered by having to choose model architectures with appropriate complexities. Here we propose for a clustering application an HMM with a countably infinite state space; inference in this model is possible by recasting it in the hierarchical Dirichlet process (HDP) framework (Teh et al. 2006), and hence we call it the HDP-HMM. We show that the infinite model outperforms model selection methods over finite models, and traditional time-independent methods, as measured by a variety of external and internal indices for clustering on two large publicly available data sets. Moreover, we show that the infinite models utilize more hidden states and employ richer architectures (e.g. state-to-state transitions) without the damaging effects of overfitting.", "source": "arxiv/ml"}
{"id": "arxiv:1930", "title": "Advances in exact Bayesian structure discovery in Bayesian networks", "text": "We consider a Bayesian method for learning the Bayesian network structure from complete data. Recently, Koivisto and Sood (2004) presented an algorithm that for any single edge computes its marginal posterior probability in O(n 2^n) time, where n is the number of attributes; the number of parents per attribute is bounded by a constant. In this paper we show that the posterior probabilities for all the n (n - 1) potential edges can be computed in O(n 2^n) total time. This result is achieved by a forward-backward technique and fast Moebius transform algorithms, which are of independent interest. The resulting speedup by a factor of about n^2 allows us to experimentally study the statistical power of learning moderate-size networks. We report results from a simulation study that covers data sets with 20 to 10,000 records over 5 to 25 discrete attributes", "source": "arxiv/ml"}
{"id": "arxiv:1931", "title": "The AI&M Procedure for Learning from Incomplete Data", "text": "We investigate methods for parameter learning from incomplete data that is not missing at random. Likelihood-based methods then require the optimization of a profile likelihood that takes all possible missingness mechanisms into account. Optimzing this profile likelihood poses two main difficulties: multiple (local) maxima, and its very high-dimensional parameter space. In this paper a new method is presented for optimizing the profile likelihood that addresses the second difficulty: in the proposed AI&M (adjusting imputation and mazimization) procedure the optimization is performed by operations in the space of data completions, rather than directly in the parameter space of the profile likelihood. We apply the AI&M method to learning parameters for Bayesian networks. The method is compared against conservative inference, which takes into account each possible data completion, and against EM. The results indicate that likelihood-based inference is still feasible in the case of unknown missingness mechanisms, and that conservative inference is unnecessarily weak. On the other hand, our results also provide evidence that the EM algorithm is still quite effective when the data is not missing at random.", "source": "arxiv/ml"}
{"id": "arxiv:1932", "title": "Convex Structure Learning for Bayesian Networks: Polynomial Feature Selection and Approximate Ordering", "text": "We present a new approach to learning the structure and parameters of a Bayesian network based on regularized estimation in an exponential family representation. Here we show that, given a fixed variable order, the optimal structure and parameters can be learned efficiently, even without restricting the size of the parent sets. We then consider the problem of optimizing the variable order for a given set of features. This is still a computationally hard problem, but we present a convex relaxation that yields an optimal 'soft' ordering in polynomial time. One novel aspect of the approach is that we do not perform a discrete search over DAG structures, nor over variable orders, but instead solve a continuous relaxation that can then be rounded to obtain a valid network structure. We conduct an experimental comparison against standard structure search procedures over standard objectives, which cope with local minima, and evaluate the advantages of using convex relaxations that reduce the effects of local minima.", "source": "arxiv/ml"}
{"id": "arxiv:1933", "title": "Matrix Tile Analysis", "text": "Many tasks require finding groups of elements in a matrix of numbers, symbols or class likelihoods. One approach is to use efficient bi- or tri-linear factorization techniques including PCA, ICA, sparse matrix factorization and plaid analysis. These techniques are not appropriate when addition and multiplication of matrix elements are not sensibly defined. More directly, methods like bi-clustering can be used to classify matrix elements, but these methods make the overly-restrictive assumption that the class of each element is a function of a row class and a column class. We introduce a general computational problem, `matrix tile analysis' (MTA), which consists of decomposing a matrix into a set of non-overlapping tiles, each of which is defined by a subset of usually nonadjacent rows and columns. MTA does not require an algebra for combining tiles, but must search over discrete combinations of tile assignments. Exact MTA is a computationally intractable integer programming problem, but we describe an approximate iterative technique and a computationally efficient sum-product relaxation of the integer program. We compare the effectiveness of these methods to PCA and plaid on hundreds of randomly generated tasks. Using double-gene-knockout data, we show that MTA finds groups of interacting yeast genes that have biologically-related functions.", "source": "arxiv/ml"}
{"id": "arxiv:1934", "title": "Continuous Time Markov Networks", "text": "A central task in many applications is reasoning about processes that change in a continuous time. The mathematical framework of Continuous Time Markov Processes provides the basic foundations for modeling such systems. Recently, Nodelman et al introduced continuous time Bayesian networks (CTBNs), which allow a compact representation of continuous-time processes over a factored state space. In this paper, we introduce continuous time Markov networks (CTMNs), an alternative representation language that represents a different type of continuous-time dynamics. In many real life processes, such as biological and chemical systems, the dynamics of the process can be naturally described as an interplay between two forces - the tendency of each entity to change its state, and the overall fitness or energy function of the entire system. In our model, the first force is described by a continuous-time proposal process that suggests possible local changes to the state of the system at different rates. The second force is represented by a Markov network that encodes the fitness, or desirability, of different states; a proposed local change is then accepted with a probability that is a function of the change in the fitness distribution. We show that the fitness distribution is also the stationary distribution of the Markov process, so that this representation provides a characterization of a temporal process whose stationary distribution has a compact graphical representation. This allows us to naturally capture a different type of structure in complex dynamical processes, such as evolving biological sequences. We describe the semantics of the representation, its basic properties, and how it compares to CTBNs. We also provide algorithms for learning such models from data, and discuss its applicability to biological sequence evolution.", "source": "arxiv/ml"}
{"id": "arxiv:1935", "title": "Chi-square Tests Driven Method for Learning the Structure of Factored MDPs", "text": "SDYNA is a general framework designed to address large stochastic reinforcement learning problems. Unlike previous model based methods in FMDPs, it incrementally learns the structure and the parameters of a RL problem using supervised learning techniques. Then, it integrates decision-theoric planning algorithms based on FMDPs to compute its policy. SPITI is an instanciation of SDYNA that exploits ITI, an incremental decision tree algorithm, to learn the reward function and the Dynamic Bayesian Networks with local structures representing the transition function of the problem. These representations are used by an incremental version of the Structured Value Iteration algorithm. In order to learn the structure, SPITI uses Chi-Square tests to detect the independence between two probability distributions. Thus, we study the relation between the threshold used in the Chi-Square test, the size of the model built and the relative error of the value function of the induced policy with respect to the optimal value. We show that, on stochastic problems, one can tune the threshold so as to generate both a compact model and an efficient policy. Then, we show that SPITI, while keeping its model compact, uses the generalization property of its learning method to perform better than a stochastic classical tabular algorithm in large RL problem with an unknown structure. We also introduce a new measure based on Chi-Square to qualify the accuracy of the model learned by SPITI. We qualitatively show that the generalization property in SPITI within the FMDP framework may prevent an exponential growth of the time required to learn the structure of large stochastic RL problems.", "source": "arxiv/ml"}
{"id": "arxiv:1936", "title": "Gibbs Sampling for (Coupled) Infinite Mixture Models in the Stick Breaking Representation", "text": "Nonparametric Bayesian approaches to clustering, information retrieval, language modeling and object recognition have recently shown great promise as a new paradigm for unsupervised data analysis. Most contributions have focused on the Dirichlet process mixture models or extensions thereof for which efficient Gibbs samplers exist. In this paper we explore Gibbs samplers for infinite complexity mixture models in the stick breaking representation. The advantage of this representation is improved modeling flexibility. For instance, one can design the prior distribution over cluster sizes or couple multiple infinite mixture models (e.g. over time) at the level of their parameters (i.e. the dependent Dirichlet process model). However, Gibbs samplers for infinite mixture models (as recently introduced in the statistics literature) seem to mix poorly over cluster labels. Among others issues, this can have the adverse effect that labels for the same cluster in coupled mixture models are mixed up. We introduce additional moves in these samplers to improve mixing over cluster labels and to bring clusters into correspondence. An application to modeling of storm trajectories is used to illustrate these ideas.", "source": "arxiv/ml"}
{"id": "arxiv:1937", "title": "Approximate Separability for Weak Interaction in Dynamic Systems", "text": "One approach to monitoring a dynamic system relies on decomposition of the system into weakly interacting subsystems. An earlier paper introduced a notion of weak interaction called separability, and showed that it leads to exact propagation of marginals for prediction. This paper addresses two questions left open by the earlier paper: can we define a notion of approximate separability that occurs naturally in practice, and do separability and approximate separability lead to accurate monitoring? The answer to both questions is afirmative. The paper also analyzes the structure of approximately separable decompositions, and provides some explanation as to why these models perform well.", "source": "arxiv/ml"}
{"id": "arxiv:1938", "title": "Identifying the Relevant Nodes Without Learning the Model", "text": "We propose a method to identify all the nodes that are relevant to compute all the conditional probability distributions for a given set of nodes. Our method is simple, effcient, consistent, and does not require learning a Bayesian network first. Therefore, our method can be applied to high-dimensional databases, e.g. gene expression databases.", "source": "arxiv/ml"}
{"id": "arxiv:1939", "title": "A compact, hierarchical Q-function decomposition", "text": "Previous work in hierarchical reinforcement learning has faced a dilemma: either ignore the values of different possible exit states from a subroutine, thereby risking suboptimal behavior, or represent those values explicitly thereby incurring a possibly large representation cost because exit values refer to nonlocal aspects of the world (i.e., all subsequent rewards). This paper shows that, in many cases, one can avoid both of these problems. The solution is based on recursively decomposing the exit value function in terms of Q-functions at higher levels of the hierarchy. This leads to an intuitively appealing runtime architecture in which a parent subroutine passes to its child a value function on the exit states and the child reasons about how its choices affect the exit value. We also identify structural conditions on the value function and transition distributions that allow much more concise representations of exit state distributions, leading to further state abstraction. In essence, the only variables whose exit values need be considered are those that the parent cares about and the child affects. We demonstrate the utility of our algorithms on a series of increasingly complex environments.", "source": "arxiv/ml"}
{"id": "arxiv:1940", "title": "Structured Priors for Structure Learning", "text": "Traditional approaches to Bayes net structure learning typically assume little regularity in graph structure other than sparseness. However, in many cases, we expect more systematicity: variables in real-world systems often group into classes that predict the kinds of probabilistic dependencies they participate in. Here we capture this form of prior knowledge in a hierarchical Bayesian framework, and exploit it to enable structure learning and type discovery from small datasets. Specifically, we present a nonparametric generative model for directed acyclic graphs as a prior for Bayes net structure learning. Our model assumes that variables come in one or more classes and that the prior probability of an edge existing between two variables is a function only of their classes. We derive an MCMC algorithm for simultaneous inference of the number of classes, the class assignments of variables, and the Bayes net structure over variables. For several realistic, sparse datasets, we show that the bias towards systematicity of connections provided by our model yields more accurate learned networks than a traditional, uniform prior approach, and that the classes found by our model are appropriate.", "source": "arxiv/ml"}
{"id": "arxiv:1941", "title": "Faster Gaussian Summation: Theory and Experiment", "text": "We provide faster algorithms for the problem of Gaussian summation, which occurs in many machine learning methods. We develop two new extensions - an O(Dp) Taylor expansion for the Gaussian kernel with rigorous error bounds and a new error control scheme integrating any arbitrary approximation method - within the best discretealgorithmic framework using adaptive hierarchical data structures. We rigorously evaluate these techniques empirically in the context of optimal bandwidth selection in kernel density estimation, revealing the strengths and weaknesses of current state-of-the-art approaches for the first time. Our results demonstrate that the new error control scheme yields improved performance, whereas the series expansion approach is only effective in low dimensions (five or less).", "source": "arxiv/ml"}
{"id": "arxiv:1942", "title": "Sequential Document Representations and Simplicial Curves", "text": "The popular bag of words assumption represents a document as a histogram of word occurrences. While computationally efficient, such a representation is unable to maintain any sequential information. We present a continuous and differentiable sequential document representation that goes beyond the bag of words assumption, and yet is efficient and effective. This representation employs smooth curves in the multinomial simplex to account for sequential information. We discuss the representation and its geometric properties and demonstrate its applicability for the task of text classification.", "source": "arxiv/ml"}
{"id": "arxiv:1943", "title": "Predicting Conditional Quantiles via Reduction to Classification", "text": "We show how to reduce the process of predicting general order statistics (and the median in particular) to solving classification. The accompanying theoretical statement shows that the regret of the classifier bounds the regret of the quantile regression under a quantile loss. We also test this reduction empirically against existing quantile regression methods on large real-world datasets and discover that it provides state-of-the-art performance.", "source": "arxiv/ml"}
{"id": "arxiv:1944", "title": "On the Number of Samples Needed to Learn the Correct Structure of a Bayesian Network", "text": "Bayesian Networks (BNs) are useful tools giving a natural and compact representation of joint probability distributions. In many applications one needs to learn a Bayesian Network (BN) from data. In this context, it is important to understand the number of samples needed in order to guarantee a successful learning. Previous work have studied BNs sample complexity, yet it mainly focused on the requirement that the learned distribution will be close to the original distribution which generated the data. In this work, we study a different aspect of the learning, namely the number of samples needed in order to learn the correct structure of the network. We give both asymptotic results, valid in the large sample limit, and experimental results, demonstrating the learning behavior for feasible sample sizes. We show that structure learning is a more difficult task, compared to approximating the correct distribution, in the sense that it requires a much larger number of samples, regardless of the computational power available for the learner.", "source": "arxiv/ml"}
{"id": "arxiv:1945", "title": "Bayesian Multicategory Support Vector Machines", "text": "We show that the multi-class support vector machine (MSVM) proposed by Lee et. al. (2004), can be viewed as a MAP estimation procedure under an appropriate probabilistic interpretation of the classifier. We also show that this interpretation can be extended to a hierarchical Bayesian architecture and to a fully-Bayesian inference procedure for multi-class classification based on data augmentation. We present empirical results that show that the advantages of the Bayesian formalism are obtained without a loss in classification accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:1946", "title": "Infinite Hidden Relational Models", "text": "In many cases it makes sense to model a relationship symmetrically, not implying any particular directionality. Consider the classical example of a recommendation system where the rating of an item by a user should symmetrically be dependent on the attributes of both the user and the item. The attributes of the (known) relationships are also relevant for predicting attributes of entities and for predicting attributes of new relations. In recommendation systems, the exploitation of relational attributes is often referred to as collaborative filtering. Again, in many applications one might prefer to model the collaborative effect in a symmetrical way. In this paper we present a relational model, which is completely symmetrical. The key innovation is that we introduce for each entity (or object) an infinite-dimensional latent variable as part of a Dirichlet process (DP) model. We discuss inference in the model, which is based on a DP Gibbs sampler, i.e., the Chinese restaurant process. We extend the Chinese restaurant process to be applicable to relational modeling. Our approach is evaluated in three applications. One is a recommendation system based on the MovieLens data set. The second application concerns the prediction of the function of yeast genes/proteins on the data set of KDD Cup 2001 using a multi-relational model. The third application involves a relational medical domain. The experimental results show that our model gives significantly improved estimates of attributes describing relationships or entities in complex relational models.", "source": "arxiv/ml"}
{"id": "arxiv:1947", "title": "A Non-Parametric Bayesian Method for Inferring Hidden Causes", "text": "We present a non-parametric Bayesian approach to structure learning with hidden causes. Previous Bayesian treatments of this problem define a prior over the number of hidden causes and use algorithms such as reversible jump Markov chain Monte Carlo to move between solutions. In contrast, we assume that the number of hidden causes is unbounded, but only a finite number influence observable variables. This makes it possible to use a Gibbs sampler to approximate the distribution over causal structures. We evaluate the performance of both approaches in discovering hidden causes in simulated data, and use our non-parametric approach to discover hidden causes in a real medical dataset.", "source": "arxiv/ml"}
{"id": "arxiv:1948", "title": "Bayesian Random Fields: The Bethe-Laplace Approximation", "text": "While learning the maximum likelihood value of parameters of an undirected graphical model is hard, modelling the posterior distribution over parameters given data is harder. Yet, undirected models are ubiquitous in computer vision and text modelling (e.g. conditional random fields). But where Bayesian approaches for directed models have been very successful, a proper Bayesian treatment of undirected models in still in its infant stages. We propose a new method for approximating the posterior of the parameters given data based on the Laplace approximation. This approximation requires the computation of the covariance matrix over features which we compute using the linear response approximation based in turn on loopy belief propagation. We develop the theory for conditional and 'unconditional' random fields with or without hidden variables. In the conditional setting we introduce a new variant of bagging suitable for structured domains. Here we run the loopy max-product algorithm on a 'super-graph' composed of graphs for individual models sampled from the posterior and connected by constraints. Experiments on real world data validate the proposed methods.", "source": "arxiv/ml"}
{"id": "arxiv:1949", "title": "Incremental Model-based Learners With Formal Learning-Time Guarantees", "text": "Model-based learning algorithms have been shown to use experience efficiently when learning to solve Markov Decision Processes (MDPs) with finite state and action spaces. However, their high computational cost due to repeatedly solving an internal model inhibits their use in large-scale problems. We propose a method based on real-time dynamic programming (RTDP) to speed up two model-based algorithms, RMAX and MBIE (model-based interval estimation), resulting in computationally much faster algorithms with little loss compared to existing bounds. Specifically, our two new learning algorithms, RTDP-RMAX and RTDP-IE, have considerably smaller computational demands than RMAX and MBIE. We develop a general theoretical framework that allows us to prove that both are efficient learners in a PAC (probably approximately correct) sense. We also present an experimental evaluation of these new algorithms that helps quantify the tradeoff between computational and experience demands.", "source": "arxiv/ml"}
{"id": "arxiv:1950", "title": "Ranking by Dependence - A Fair Criteria", "text": "Estimating the dependences between random variables, and ranking them accordingly, is a prevalent problem in machine learning. Pursuing frequentist and information-theoretic approaches, we first show that the p-value and the mutual information can fail even in simplistic situations. We then propose two conditions for regularizing an estimator of dependence, which leads to a simple yet effective new measure. We discuss its advantages and compare it to well-established model-selection criteria. Apart from that, we derive a simple constraint for regularizing parameter estimates in a graphical model. This results in an analytical approximation for the optimal value of the equivalent sample size, which agrees very well with the more involved Bayesian approach in our experiments.", "source": "arxiv/ml"}
{"id": "arxiv:1951", "title": "A Self-Supervised Terrain Roughness Estimator for Off-Road Autonomous Driving", "text": "We present a machine learning approach for estimating the second derivative of a drivable surface, its roughness. Robot perception generally focuses on the first derivative, obstacle detection. However, the second derivative is also important due to its direct relation (with speed) to the shock the vehicle experiences. Knowing the second derivative allows a vehicle to slow down in advance of rough terrain. Estimating the second derivative is challenging due to uncertainty. For example, at range, laser readings may be so sparse that significant information about the surface is missing. Also, a high degree of precision is required in projecting laser readings. This precision may be unavailable due to latency or error in the pose estimation. We model these sources of error as a multivariate polynomial. Its coefficients are learned using the shock data as ground truth -- the accelerometers are used to train the lasers. The resulting classifier operates on individual laser readings from a road surface described by a 3D point cloud. The classifier identifies sections of road where the second derivative is likely to be large. Thus, the vehicle can slow down in advance, reducing the shock it experiences. The algorithm is an evolution of one we used in the 2005 DARPA Grand Challenge. We analyze it using data from that route.", "source": "arxiv/ml"}
{"id": "arxiv:1952", "title": "Variable noise and dimensionality reduction for sparse Gaussian processes", "text": "The sparse pseudo-input Gaussian process (SPGP) is a new approximation method for speeding up GP regression in the case of a large number of data points N. The approximation is controlled by the gradient optimization of a small set of M `pseudo-inputs', thereby reducing complexity from N^3 to NM^2. One limitation of the SPGP is that this optimization space becomes impractically big for high dimensional data sets. This paper addresses this limitation by performing automatic dimensionality reduction. A projection of the input space to a low dimensional space is learned in a supervised manner, alongside the pseudo-inputs, which now live in this reduced space. The paper also investigates the suitability of the SPGP for modeling data with input-dependent noise. A further extension of the model is made to make it even more powerful in this regard - we learn an uncertainty parameter for each pseudo-input. The combination of sparsity, reduced dimension, and input-dependent noise makes it possible to apply GPs to much larger and more complex data sets than was previously practical. We demonstrate the benefits of these methods on several synthetic and real world problems.", "source": "arxiv/ml"}
{"id": "arxiv:1953", "title": "Learning Neighborhoods for Metric Learning", "text": "Metric learning methods have been shown to perform well on different learning tasks. Many of them rely on target neighborhood relationships that are computed in the original feature space and remain fixed throughout learning. As a result, the learned metric reflects the original neighborhood relations. We propose a novel formulation of the metric learning problem in which, in addition to the metric, the target neighborhood relations are also learned in a two-step iterative approach. The new formulation can be seen as a generalization of many existing metric learning methods. The formulation includes a target neighbor assignment rule that assigns different numbers of neighbors to instances according to their quality; `high quality' instances get more neighbors. We experiment with two of its instantiations that correspond to the metric learning algorithms LMNN and MCML and compare it to other metric learning methods on a number of datasets. The experimental results show state-of-the-art performance and provide evidence that learning the neighborhood relations does improve predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:1954", "title": "A Hybrid Method for Distance Metric Learning", "text": "We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can provide information that is not encoded in feature vectors but yet relates to perceived similarity between objects. Experiments with synthetic data as well as a real medical image retrieval problem demonstrate that leveraging class labels through use of our method improves retrieval performance significantly.", "source": "arxiv/ml"}
{"id": "arxiv:1955", "title": "Implicit Density Estimation by Local Moment Matching to Sample from Auto-Encoders", "text": "Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps define better justified sampling algorithms for deep learning based on auto-encoder variants. We consider an MCMC where each step samples from a Gaussian whose mean and covariance matrix depend on the previous state, defines through its asymptotic distribution a target density. First, we show that good choices (in the sense of consistency) for these mean and covariance functions are the local expected value and local covariance under that target density. Then we show that an auto-encoder with a contractive penalty captures estimators of these local moments in its reconstruction function and its Jacobian. A contribution of this work is thus a novel alternative to maximum-likelihood density estimation, which we call local moment matching. It also justifies a recently proposed sampling algorithm for the Contractive Auto-Encoder and extends it to the Denoising Auto-Encoder.", "source": "arxiv/ml"}
{"id": "arxiv:1956", "title": "Density-Difference Estimation", "text": "We address the problem of estimating the difference between two probability densities. A naive approach is a two-step procedure of first estimating two densities separately and then computing their difference. However, such a two-step procedure does not necessarily work well because the first step is performed without regard to the second step and thus a small error incurred in the first stage can cause a big error in the second stage. In this paper, we propose a single-shot procedure for directly estimating the density difference without separately estimating two densities. We derive a non-parametric finite-sample error bound for the proposed single-shot density-difference estimator and show that it achieves the optimal convergence rate. The usefulness of the proposed method is also demonstrated experimentally.", "source": "arxiv/ml"}
{"id": "arxiv:1957", "title": "Differentiable Pooling for Hierarchical Feature Learning", "text": "We introduce a parametric form of pooling, based on a Gaussian, which can be optimized alongside the features in a single global objective function. By contrast, existing pooling schemes are based on heuristics (e.g. local maximum) and have no clear link to the cost function of the model. Furthermore, the variables of the Gaussian explicitly store location information, distinct from the appearance captured by the features, thus providing a what/where decomposition of the input signal. Although the differentiable pooling scheme can be incorporated in a wide range of hierarchical models, we demonstrate it in the context of a Deconvolutional Network model (Zeiler et al. ICCV 2011). We also explore a number of secondary issues within this model and present detailed experiments on MNIST digits.", "source": "arxiv/ml"}
{"id": "arxiv:1958", "title": "On Multilabel Classification and Ranking with Partial Feedback", "text": "We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show O(T^{1/2} log T) regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on real-world multilabel datasets, often obtaining comparable performance.", "source": "arxiv/ml"}
{"id": "arxiv:1959", "title": "Surrogate Regret Bounds for Bipartite Ranking via Strongly Proper Losses", "text": "The problem of bipartite ranking, where instances are labeled positive or negative and the goal is to learn a scoring function that minimizes the probability of mis-ranking a pair of positive and negative instances (or equivalently, that maximizes the area under the ROC curve), has been widely studied in recent years. A dominant theoretical and algorithmic framework for the problem has been to reduce bipartite ranking to pairwise classification; in particular, it is well known that the bipartite ranking regret can be formulated as a pairwise classification regret, which in turn can be upper bounded using usual regret bounds for classification problems. Recently, Kotlowski et al. (2011) showed regret bounds for bipartite ranking in terms of the regret associated with balanced versions of the standard (non-pairwise) logistic and exponential losses. In this paper, we show that such (non-pairwise) surrogate regret bounds for bipartite ranking can be obtained in terms of a broad class of proper (composite) losses that we term as strongly proper. Our proof technique is much simpler than that of Kotlowski et al. (2011), and relies on properties of proper (composite) losses as elucidated recently by Reid and Williamson (2010, 2011) and others. Our result yields explicit surrogate bounds (with no hidden balancing terms) in terms of a variety of strongly proper losses, including for example logistic, exponential, squared and squared hinge losses as special cases. We also obtain tighter surrogate bounds under certain low-noise conditions via a recent result of Clemencon and Robbiano (2011).", "source": "arxiv/ml"}
{"id": "arxiv:1960", "title": "Applying Deep Belief Networks to Word Sense Disambiguation", "text": "In this paper, we applied a novel learning algorithm, namely, Deep Belief Networks (DBN) to word sense disambiguation (WSD). DBN is a probabilistic generative model composed of multiple layers of hidden units. DBN uses Restricted Boltzmann Machine (RBM) to greedily train layer by layer as a pretraining. Then, a separate fine tuning step is employed to improve the discriminative power. We compared DBN with various state-of-the-art supervised learning algorithms in WSD such as Support Vector Machine (SVM), Maximum Entropy model (MaxEnt), Naive Bayes classifier (NB) and Kernel Principal Component Analysis (KPCA). We used all words in the given paragraph, surrounding context words and part-of-speech of surrounding words as our knowledge sources. We conducted our experiment on the SENSEVAL-2 data set. We observed that DBN outperformed all other learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:1961", "title": "Algorithms for Approximate Minimization of the Difference Between Submodular Functions, with Applications", "text": "We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a difference between submodular functions. Similar to [30], our new algorithms are guaranteed to monotonically reduce the objective function at every step. We empirically and theoretically show that the per-iteration cost of our algorithms is much less than [30], and our algorithms can be used to efficiently minimize a difference between submodular functions under various combinatorial constraints, a problem not previously addressed. We provide computational bounds and a hardness result on the mul- tiplicative inapproximability of minimizing the difference between submodular functions. We show, however, that it is possible to give worst-case additive bounds by providing a polynomial time computable lower-bound on the minima. Finally we show how a number of machine learning problems can be modeled as minimizing the difference between submodular functions. We experimentally show the validity of our algorithms by testing them on the problem of feature selection with submodular cost features.", "source": "arxiv/ml"}
{"id": "arxiv:1962", "title": "Robust Dequantized Compressive Sensing", "text": "We consider the reconstruction problem in compressed sensing in which the observations are recorded in a finite number of bits. They may thus contain quantization errors (from being rounded to the nearest representable value) and saturation errors (from being outside the range of representable values). Our formulation has an objective of weighted $\\ell_2$-$\\ell_1$ type, along with constraints that account explicitly for quantization and saturation errors, and is solved with an augmented Lagrangian method. We prove a consistency result for the recovered solution, stronger than those that have appeared to date in the literature, showing in particular that asymptotic consistency can be obtained without oversampling. We present extensive computational comparisons with formulations proposed previously, and variants thereof.", "source": "arxiv/ml"}
{"id": "arxiv:1963", "title": "Improving neural networks by preventing co-adaptation of feature detectors", "text": "When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This \"overfitting\" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random \"dropout\" gives big improvements on many benchmark tasks and sets new records for speech and object recognition.", "source": "arxiv/ml"}
{"id": "arxiv:1964", "title": "Local Water Diffusion Phenomenon Clustering From High Angular Resolution Diffusion Imaging (HARDI)", "text": "The understanding of neurodegenerative diseases undoubtedly passes through the study of human brain white matter fiber tracts. To date, diffusion magnetic resonance imaging (dMRI) is the unique technique to obtain information about the neural architecture of the human brain, thus permitting the study of white matter connections and their integrity. However, a remaining challenge of the dMRI community is to better characterize complex fiber crossing configurations, where diffusion tensor imaging (DTI) is limited but high angular resolution diffusion imaging (HARDI) now brings solutions. This paper investigates the development of both identification and classification process of the local water diffusion phenomenon based on HARDI data to automatically detect imaging voxels where there are single and crossing fiber bundle populations. The technique is based on knowledge extraction processes and is validated on a dMRI phantom dataset with ground truth.", "source": "arxiv/ml"}
{"id": "arxiv:1965", "title": "The OS* Algorithm: a Joint Approach to Exact Optimization and Sampling", "text": "Most current sampling algorithms for high-dimensional distributions are based on MCMC techniques and are approximate in the sense that they are valid only asymptotically. Rejection sampling, on the other hand, produces valid samples, but is unrealistically slow in high-dimension spaces. The OS* algorithm that we propose is a unified approach to exact optimization and sampling, based on incremental refinements of a functional upper bound, which combines ideas of adaptive rejection sampling and of A* optimization search. We show that the choice of the refinement can be done in a way that ensures tractability in high-dimension spaces, and we present first experiments in two different settings: inference in high-order HMMs and in large discrete graphical models.", "source": "arxiv/ml"}
{"id": "arxiv:1966", "title": "Hybrid Template Update System for Unimodal Biometric Systems", "text": "Semi-supervised template update systems allow to automatically take into account the intra-class variability of the biometric data over time. Such systems can be inefficient by including too many impostor's samples or skipping too many genuine's samples. In the first case, the biometric reference drifts from the real biometric data and attracts more often impostors. In the second case, the biometric reference does not evolve quickly enough and also progressively drifts from the real biometric data. We propose a hybrid system using several biometric sub-references in order to increase per- formance of self-update systems by reducing the previously cited errors. The proposition is validated for a keystroke- dynamics authentication system (this modality suffers of high variability over time) on two consequent datasets from the state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:1967", "title": "Web-Based Benchmark for Keystroke Dynamics Biometric Systems: A Statistical Analysis", "text": "Most keystroke dynamics studies have been evaluated using a specific kind of dataset in which users type an imposed login and password. Moreover, these studies are optimistics since most of them use different acquisition protocols, private datasets, controlled environment, etc. In order to enhance the accuracy of keystroke dynamics' performance, the main contribution of this paper is twofold. First, we provide a new kind of dataset in which users have typed both an imposed and a chosen pairs of logins and passwords. In addition, the keystroke dynamics samples are collected in a web-based uncontrolled environment (OS, keyboards, browser, etc.). Such kind of dataset is important since it provides us more realistic results of keystroke dynamics' performance in comparison to the literature (controlled environment, etc.). Second, we present a statistical analysis of well known assertions such as the relationship between performance and password size, impact of fusion schemes on system overall performance, and others such as the relationship between performance and entropy. We put into obviousness in this paper some new results on keystroke dynamics in realistic conditions.", "source": "arxiv/ml"}
{"id": "arxiv:1968", "title": "PAC-Bayesian Majority Vote for Late Classifier Fusion", "text": "A lot of attention has been devoted to multimedia indexing over the past few years. In the literature, we often consider two kinds of fusion schemes: The early fusion and the late fusion. In this paper we focus on late classifier fusion, where one combines the scores of each modality at the decision level. To tackle this problem, we investigate a recent and elegant well-founded quadratic program named MinCq coming from the Machine Learning PAC-Bayes theory. MinCq looks for the weighted combination, over a set of real-valued functions seen as voters, leading to the lowest misclassification rate, while making use of the voters' diversity. We provide evidence that this method is naturally adapted to late fusion procedure. We propose an extension of MinCq by adding an order- preserving pairwise loss for ranking, helping to improve Mean Averaged Precision measure. We confirm the good behavior of the MinCq-based fusion approaches with experiments on a real image benchmark.", "source": "arxiv/ml"}
{"id": "arxiv:1969", "title": "Inferring land use from mobile phone activity", "text": "Understanding the spatiotemporal distribution of people within a city is crucial to many planning applications. Obtaining data to create required knowledge, currently involves costly survey methods. At the same time ubiquitous mobile sensors from personal GPS devices to mobile phones are collecting massive amounts of data on urban systems. The locations, communications, and activities of millions of people are recorded and stored by new information technologies. This work utilizes novel dynamic data, generated by mobile phone users, to measure spatiotemporal changes in population. In the process, we identify the relationship between land use and dynamic population over the course of a typical week. A machine learning classification algorithm is used to identify clusters of locations with similar zoned uses and mobile phone activity patterns. It is shown that the mobile phone data is capable of delivering useful information on actual land use that supplements zoning regulations.", "source": "arxiv/ml"}
{"id": "arxiv:1970", "title": "Unsupervised spectral learning", "text": "In spectral clustering and spectral image segmentation, the data is partioned starting from a given matrix of pairwise similarities S. the matrix S is constructed by hand, or learned on a separate training set. In this paper we show how to achieve spectral clustering in unsupervised mode. Our algorithm starts with a set of observed pairwise features, which are possible components of an unknown, parametric similarity function. This function is learned iteratively, at the same time as the clustering of the data. The algorithm shows promosing results on synthetic and real data.", "source": "arxiv/ml"}
{"id": "arxiv:1971", "title": "Learning from Sparse Data by Exploiting Monotonicity Constraints", "text": "When training data is sparse, more domain knowledge must be incorporated into the learning algorithm in order to reduce the effective size of the hypothesis space. This paper builds on previous work in which knowledge about qualitative monotonicities was formally represented and incorporated into learning algorithms (e.g., Clark & Matwin's work with the CN2 rule learning algorithm). We show how to interpret knowledge of qualitative influences, and in particular of monotonicities, as constraints on probability distributions, and to incorporate this knowledge into Bayesian network learning algorithms. We show that this yields improved accuracy, particularly with very small training sets (e.g. less than 10 examples).", "source": "arxiv/ml"}
{"id": "arxiv:1972", "title": "Learning Factor Graphs in Polynomial Time & Sample Complexity", "text": "We study computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded factor size and bounded connectivity can be learned in polynomial time and polynomial number of samples, assuming that the data is generated by a network in this class. This result covers both parameter estimation for a known network structure and structure learning. It implies as a corollary that we can learn factor graphs for both Bayesian networks and Markov networks of bounded degree, in polynomial time and sample complexity. Unlike maximum likelihood estimation, our method does not require inference in the underlying network, and so applies to networks where inference is intractable. We also show that the error of our learned model degrades gracefully when the generating distribution is not a member of the target class of networks.", "source": "arxiv/ml"}
{"id": "arxiv:1973", "title": "On the Detection of Concept Changes in Time-Varying Data Stream by Testing Exchangeability", "text": "A martingale framework for concept change detection based on testing data exchangeability was recently proposed (Ho, 2005). In this paper, we describe the proposed change-detection test based on the Doob's Maximal Inequality and show that it is an approximation of the sequential probability ratio test (SPRT). The relationship between the threshold value used in the proposed test and its size and power is deduced from the approximation. The mean delay time before a change is detected is estimated using the average sample number of a SPRT. The performance of the test using various threshold values is examined on five different data stream scenarios simulated using two synthetic data sets. Finally, experimental results show that the test is effective in detecting changes in time-varying data streams simulated using three benchmark data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1974", "title": "Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework", "text": "A software library for constructing and learning probabilistic models is presented. The library offers a set of building blocks from which a large variety of static and dynamic models can be built. These include hierarchical models for variances of other variables and many nonlinear models. The underlying variational Bayesian machinery, providing for fast and robust estimation but being mathematically rather involved, is almost completely hidden from the user thus making it very easy to use the library. The building blocks include Gaussian, rectified Gaussian and mixture-of-Gaussians variables and computational nodes which can be combined rather freely.", "source": "arxiv/ml"}
{"id": "arxiv:1975", "title": "Maximum Margin Bayesian Networks", "text": "We consider the problem of learning Bayesian network classifiers that maximize the marginover a set of classification variables. We find that this problem is harder for Bayesian networks than for undirected graphical models like maximum margin Markov networks. The main difficulty is that the parameters in a Bayesian network must satisfy additional normalization constraints that an undirected graphical model need not respect. These additional constraints complicate the optimization task. Nevertheless, we derive an effective training algorithm that solves the maximum margin training problem for a range of Bayesian network topologies, and converges to an approximate solution for arbitrary network topologies. Experimental results show that the method can demonstrate improved generalization performance over Markov networks when the directed graphical structure encodes relevant knowledge. In practice, the training technique allows one to combine prior knowledge expressed as a directed (causal) model with state of the art discriminative learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:1976", "title": "Learning Bayesian Network Parameters with Prior Knowledge about Context-Specific Qualitative Influences", "text": "We present a method for learning the parameters of a Bayesian network with prior knowledge about the signs of influences between variables. Our method accommodates not just the standard signs, but provides for context-specific signs as well. We show how the various signs translate into order constraints on the network parameters and how isotonic regression can be used to compute order-constrained estimates from the available data. Our experimental results show that taking prior knowledge about the signs of influences into account leads to an improved fit of the true distribution, especially when only a small sample of data is available. Moreover, the computed estimates are guaranteed to be consistent with the specified signs, thereby resulting in a network that is more likely to be accepted by experts in its domain of application.", "source": "arxiv/ml"}
{"id": "arxiv:1977", "title": "Learning about individuals from group statistics", "text": "We propose a new problem formulation which is similar to, but more informative than, the binary multiple-instance learning problem. In this setting, we are given groups of instances (described by feature vectors) along with estimates of the fraction of positively-labeled instances per group. The task is to learn an instance level classifier from this information. That is, we are trying to estimate the unknown binary labels of individuals from knowledge of group statistics. We propose a principled probabilistic model to solve this problem that accounts for uncertainty in the parameters and in the unknown individual labels. This model is trained with an efficient MCMC algorithm. Its performance is demonstrated on both synthetic and real-world data arising in general object recognition.", "source": "arxiv/ml"}
{"id": "arxiv:1978", "title": "Toward Practical N2 Monte Carlo: the Marginal Particle Filter", "text": "Sequential Monte Carlo techniques are useful for state estimation in non-linear, non-Gaussian dynamic models. These methods allow us to approximate the joint posterior distribution using sequential importance sampling. In this framework, the dimension of the target distribution grows with each time step, thus it is necessary to introduce some resampling steps to ensure that the estimates provided by the algorithm have a reasonable variance. In many applications, we are only interested in the marginal filtering distribution which is defined on a space of fixed dimension. We present a Sequential Monte Carlo algorithm called the Marginal Particle Filter which operates directly on the marginal distribution, hence avoiding having to perform importance sampling on a space of growing dimension. Using this idea, we also derive an improved version of the auxiliary particle filter. We show theoretic and empirical results which demonstrate a reduction in variance over conventional particle filtering, and present techniques for reducing the cost of the marginal particle filter with N particles from O(N2) to O(N logN).", "source": "arxiv/ml"}
{"id": "arxiv:1979", "title": "Obtaining Calibrated Probabilities from Boosting", "text": "Boosted decision trees typically yield good accuracy, precision, and ROC area. However, because the outputs from boosting are not well calibrated posterior probabilities, boosting yields poor squared error and cross-entropy. We empirically demonstrate why AdaBoost predicts distorted probabilities and examine three calibration methods for correcting this distortion: Platt Scaling, Isotonic Regression, and Logistic Correction. We also experiment with boosting using log-loss instead of the usual exponential loss. Experiments show that Logistic Correction and boosting with log-loss work well when boosting weak models such as decision stumps, but yield poor performance when boosting more complex models such as full decision trees. Platt Scaling and Isotonic Regression, however, significantly improve the probabilities predicted by", "source": "arxiv/ml"}
{"id": "arxiv:1980", "title": "A submodular-supermodular procedure with applications to discriminative structure learning", "text": "In this paper, we present an algorithm for minimizing the difference between two submodular functions using a variational framework which is based on (an extension of) the concave-convex procedure [17]. Because several commonly used metrics in machine learning, like mutual information and conditional mutual information, are submodular, the problem of minimizing the difference of two submodular problems arises naturally in many machine learning applications. Two such applications are learning discriminatively structured graphical models and feature selection under computational complexity constraints. A commonly used metric for measuring discriminative capacity is the EAR measure which is the difference between two conditional mutual information terms. Feature selection taking complexity considerations into account also fall into this framework because both the information that a set of features provide and the cost of computing and using the features can be modeled as submodular functions. This problem is NP-hard, and we give a polynomial time heuristic for it. We also present results on synthetic data to show that classifiers based on discriminative graphical models using this algorithm can significantly outperform classifiers based on generative graphical models.", "source": "arxiv/ml"}
{"id": "arxiv:1981", "title": "A Conditional Random Field for Discriminatively-trained Finite-state String Edit Distance", "text": "The need to measure sequence similarity arises in information extraction, object identity, data mining, biological sequence analysis, and other domains. This paper presents discriminative string-edit CRFs, a finitestate conditional random field model for edit sequences between strings. Conditional random fields have advantages over generative approaches to this problem, such as pair HMMs or the work of Ristad and Yianilos, because as conditionally-trained methods, they enable the use of complex, arbitrary actions and features of the input strings. As in generative models, the training data does not have to specify the edit sequences between the given string pairs. Unlike generative models, however, our model is trained on both positive and negative instances of string pairs. We present positive experimental results on several data sets.", "source": "arxiv/ml"}
{"id": "arxiv:1982", "title": "Piecewise Training for Undirected Models", "text": "For many large undirected models that arise in real-world applications, exact maximumlikelihood training is intractable, because it requires computing marginal distributions of the model. Conditional training is even more difficult, because the partition function depends not only on the parameters, but also on the observed input, requiring repeated inference over each training example. An appealing idea for such models is to independently train a local undirected classifier over each clique, afterwards combining the learned weights into a single global model. In this paper, we show that this piecewise method can be justified as minimizing a new family of upper bounds on the log partition function. On three natural-language data sets, piecewise training is more accurate than pseudolikelihood, and often performs comparably to global training using belief propagation.", "source": "arxiv/ml"}
{"id": "arxiv:1983", "title": "Discovery of non-gaussian linear causal models using ICA", "text": "In recent years, several methods have been proposed for the discovery of causal structure from non-experimental data (Spirtes et al. 2000; Pearl 2000). Such methods make various assumptions on the data generating process to facilitate its identification from purely observational data. Continuing this line of research, we show how to discover the complete causal structure of continuous-valued data, under the assumptions that (a) the data generating process is linear, (b) there are no unobserved confounders, and (c) disturbance variables have non-gaussian distributions of non-zero variances. The solution relies on the use of the statistical method known as independent component analysis (ICA), and does not require any pre-specified time-ordering of the variables. We provide a complete Matlab package for performing this LiNGAM analysis (short for Linear Non-Gaussian Acyclic Model), and demonstrate the effectiveness of the method using artificially generated data.", "source": "arxiv/ml"}
{"id": "arxiv:1984", "title": "Two-Way Latent Grouping Model for User Preference Prediction", "text": "We introduce a novel latent grouping model for predicting the relevance of a new document to a user. The model assumes a latent group structure for both users and documents. We compared the model against a state-of-the-art method, the User Rating Profile model, where only users have a latent group structure. We estimate both models by Gibbs sampling. The new method predicts relevance more accurately for new documents that have few known ratings. The reason is that generalization over documents then becomes necessary and hence the twoway grouping is profitable.", "source": "arxiv/ml"}
{"id": "arxiv:1985", "title": "The DLR Hierarchy of Approximate Inference", "text": "We propose a hierarchy for approximate inference based on the Dobrushin, Lanford, Ruelle (DLR) equations. This hierarchy includes existing algorithms, such as belief propagation, and also motivates novel algorithms such as factorized neighbors (FN) algorithms and variants of mean field (MF) algorithms. In particular, we show that extrema of the Bethe free energy correspond to approximate solutions of the DLR equations. In addition, we demonstrate a close connection between these approximate algorithms and Gibbs sampling. Finally, we compare and contrast various of the algorithms in the DLR hierarchy on spin-glass problems. The experiments show that algorithms higher up in the hierarchy give more accurate results when they converge but tend to be less stable.", "source": "arxiv/ml"}
{"id": "arxiv:1986", "title": "A Function Approximation Approach to Estimation of Policy Gradient for POMDP with Structured Policies", "text": "We consider the estimation of the policy gradient in partially observable Markov decision processes (POMDP) with a special class of structured policies that are finite-state controllers. We show that the gradient estimation can be done in the Actor-Critic framework, by making the critic compute a \"value\" function that does not depend on the states of POMDP. This function is the conditional mean of the true value function that depends on the states. We show that the critic can be implemented using temporal difference (TD) methods with linear function approximations, and the analytical results on TD and Actor-Critic can be transfered to this case. Although Actor-Critic algorithms have been used extensively in Markov decision processes (MDP), up to now they have not been proposed for POMDP as an alternative to the earlier proposal GPOMDP algorithm, an actor-only method. Furthermore, we show that the same idea applies to semi-Markov problems with a subset of finite-state controllers.", "source": "arxiv/ml"}
{"id": "arxiv:1987", "title": "Mining Associated Text and Images with Dual-Wing Harmoniums", "text": "We propose a multi-wing harmonium model for mining multimedia data that extends and improves on earlier models based on two-layer random fields, which capture bidirectional dependencies between hidden topic aspects and observed inputs. This model can be viewed as an undirected counterpart of the two-layer directed models such as LDA for similar tasks, but bears significant difference in inference/learning cost tradeoffs, latent topic representations, and topic mixing mechanisms. In particular, our model facilitates efficient inference and robust topic mixing, and potentially provides high flexibilities in modeling the latent topic spaces. A contrastive divergence and a variational algorithm are derived for learning. We specialized our model to a dual-wing harmonium for captioned images, incorporating a multivariate Poisson for word-counts and a multivariate Gaussian for color histogram. We present empirical results on the applications of this model to classification, retrieval and image annotation on news video collections, and we report an extensive comparison with various extant models.", "source": "arxiv/ml"}
{"id": "arxiv:1988", "title": "Ordering-Based Search: A Simple and Effective Algorithm for Learning Bayesian Networks", "text": "One of the basic tasks for Bayesian networks (BNs) is that of learning a network structure from data. The BN-learning problem is NP-hard, so the standard solution is heuristic search. Many approaches have been proposed for this task, but only a very small number outperform the baseline of greedy hill-climbing with tabu lists; moreover, many of the proposed algorithms are quite complex and hard to implement. In this paper, we propose a very simple and easy-to-implement method for addressing this task. Our approach is based on the well-known fact that the best network (of bounded in-degree) consistent with a given node ordering can be found very efficiently. We therefore propose a search not over the space of structures, but over the space of orderings, selecting for each ordering the best network consistent with it. This search space is much smaller, makes more global search steps, has a lower branching factor, and avoids costly acyclicity checks. We present results for this algorithm on both synthetic and real data sets, evaluating both the score of the network found and in the running time. We show that ordering-based search outperforms the standard baseline, and is competitive with recent algorithms that are much harder to implement.", "source": "arxiv/ml"}
{"id": "arxiv:1989", "title": "Robust Online Hamiltonian Learning", "text": "In this work we combine two distinct machine learning methodologies, sequential Monte Carlo and Bayesian experimental design, and apply them to the problem of inferring the dynamical parameters of a quantum system. We design the algorithm with practicality in mind by including parameters that control trade-offs between the requirements on computational and experimental resources. The algorithm can be implemented online (during experimental data collection), avoiding the need for storage and post-processing. Most importantly, our algorithm is capable of learning Hamiltonian parameters even when the parameters change from experiment-to-experiment, and also when additional noise processes are present and unknown. The algorithm also numerically estimates the Cramer-Rao lower bound, certifying its own performance.", "source": "arxiv/ml"}
{"id": "arxiv:1990", "title": "Forecasting electricity consumption by aggregating specialized experts", "text": "We consider the setting of sequential prediction of arbitrary sequences based on specialized experts. We first provide a review of the relevant literature and present two theoretical contributions: a general analysis of the specialist aggregation rule of Freund et al. (1997) and an adaptation of fixed-share rules of Herbster and Warmuth (1998) in this setting. We then apply these rules to the sequential short-term (one-day-ahead) forecasting of electricity consumption; to do so, we consider two data sets, a Slovakian one and a French one, respectively concerned with hourly and half-hourly predictions. We follow a general methodology to perform the stated empirical studies and detail in particular tuning issues of the learning parameters. The introduced aggregation rules demonstrate an improved accuracy on the data sets at hand; the improvements lie in a reduced mean squared error but also in a more robust behavior with respect to large occasional errors.", "source": "arxiv/ml"}
{"id": "arxiv:1991", "title": "Estimating a Causal Order among Groups of Variables in Linear Models", "text": "The machine learning community has recently devoted much attention to the problem of inferring causal relationships from statistical data. Most of this work has focused on uncovering connections among scalar random variables. We generalize existing methods to apply to collections of multi-dimensional random vectors, focusing on techniques applicable to linear models. The performance of the resulting algorithms is evaluated and compared in simulations, which show that our methods can, in many cases, provide useful information on causal relationships even for relatively small sample sizes.", "source": "arxiv/ml"}
{"id": "arxiv:1992", "title": "Comparative Study for Inference of Hidden Classes in Stochastic Block Models", "text": "Inference of hidden classes in stochastic block model is a classical problem with important applications. Most commonly used methods for this problem involve na\\\"{\\i}ve mean field approaches or heuristic spectral methods. Recently, belief propagation was proposed for this problem. In this contribution we perform a comparative study between the three methods on synthetically created networks. We show that belief propagation shows much better performance when compared to na\\\"{\\i}ve mean field and spectral approaches. This applies to accuracy, computational efficiency and the tendency to overfit the data.", "source": "arxiv/ml"}
{"id": "arxiv:1993", "title": "Pseudo-likelihood methods for community detection in large sparse networks", "text": "Many algorithms have been proposed for fitting network models with communities, but most of them do not scale well to large networks, and often fail on sparse networks. Here we propose a new fast pseudo-likelihood method for fitting the stochastic block model for networks, as well as a variant that allows for an arbitrary degree distribution by conditioning on degrees. We show that the algorithms perform well under a range of settings, including on very sparse networks, and illustrate on the example of a network of political blogs. We also propose spectral clustering with perturbations, a method of independent interest, which works well on sparse networks where regular spectral clustering fails, and use it to provide an initial value for pseudo-likelihood. We prove that pseudo-likelihood provides consistent estimates of the communities under a mild condition on the starting value, for the case of a block model with two communities.", "source": "arxiv/ml"}
{"id": "arxiv:1994", "title": "Kernelized Supervised Dictionary Learning", "text": "In this paper, we propose supervised dictionary learning (SDL) by incorporating information on class labels into the learning of the dictionary. To this end, we propose to learn the dictionary in a space where the dependency between the signals and their corresponding labels is maximized. To maximize this dependency, the recently introduced Hilbert Schmidt independence criterion (HSIC) is used. One of the main advantages of this novel approach for SDL is that it can be easily kernelized by incorporating a kernel, particularly a data-derived kernel such as normalized compression distance, into the formulation. The learned dictionary is compact and the proposed approach is fast. We show that it outperforms other unsupervised and supervised dictionary learning approaches in the literature, using real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:1995", "title": "A Spectral Learning Approach to Range-Only SLAM", "text": "We present a novel spectral learning algorithm for simultaneous localization and mapping (SLAM) from range data with known correspondences. This algorithm is an instance of a general spectral system identification framework, from which it inherits several desirable properties, including statistical consistency and no local optima. Compared with popular batch optimization or multiple-hypothesis tracking (MHT) methods for range-only SLAM, our spectral approach offers guaranteed low computational requirements and good tracking performance. Compared with popular extended Kalman filter (EKF) or extended information filter (EIF) approaches, and many MHT ones, our approach does not need to linearize a transition or measurement model; such linearizations can cause severe errors in EKFs and EIFs, and to a lesser extent MHT, particularly for the highly non-Gaussian posteriors encountered in range-only SLAM. We provide a theoretical analysis of our method, including finite-sample error bounds. Finally, we demonstrate on a real-world robotic SLAM problem that our algorithm is not only theoretically justified, but works well in practice: in a comparison of multiple methods, the lowest errors come from a combination of our algorithm with batch optimization, but our method alone produces nearly as good a result at far lower computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:1996", "title": "Near-Optimal Algorithms for Differentially-Private Principal Components", "text": "Principal components analysis (PCA) is a standard tool for identifying good low-dimensional approximations to data in high dimension. Many data sets of interest contain private or sensitive information about individuals. Algorithms which operate on such data should be sensitive to the privacy risks in publishing their outputs. Differential privacy is a framework for developing tradeoffs between privacy and the utility of these outputs. In this paper we investigate the theory and empirical performance of differentially private approximations to PCA and propose a new method which explicitly optimizes the utility of the output. We show that the sample complexity of the proposed method differs from the existing procedure in the scaling with the data dimension, and that our method is nearly optimal in terms of this scaling. We furthermore illustrate our results, showing that on real data there is a large performance gap between the existing method and our method.", "source": "arxiv/ml"}
{"id": "arxiv:1997", "title": "Expectation Propagation in Gaussian Process Dynamical Systems: Extended Version", "text": "Rich and complex time-series data, such as those generated from engineering systems, financial markets, videos or neural recordings, are now a common feature of modern data analysis. Explaining the phenomena underlying these diverse data sets requires flexible and accurate models. In this paper, we promote Gaussian process dynamical systems (GPDS) as a rich model class that is appropriate for such analysis. In particular, we present a message passing algorithm for approximate inference in GPDSs based on expectation propagation. By posing inference as a general message passing problem, we iterate forward-backward smoothing. Thus, we obtain more accurate posterior distributions over latent structures, resulting in improved predictive performance compared to state-of-the-art GPDS smoothers, which are special cases of our general message passing algorithm. Hence, we provide a unifying approach within which to contextualize message passing in GPDSs.", "source": "arxiv/ml"}
{"id": "arxiv:1998", "title": "Optimal rates for first-order stochastic convex optimization under Tsybakov noise condition", "text": "We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function around its minimizer $x^*_{f,S}$, as quantified by a Tsybakov-like noise condition. Specifically, we prove that if $f$ grows at least as fast as $\\|x-x^*_{f,S}\\|^\\kappa$ around its minimum, for some $\\kappa > 1$, then the optimal rate of learning $f(x^*_{f,S})$ is $\\Theta(T^{-\\frac{\\kappa}{2\\kappa-2}})$. The classic rate $\\Theta(1/\\sqrt T)$ for convex functions and $\\Theta(1/T)$ for strongly convex functions are special cases of our result for $\\kappa \\rightarrow \\infty$ and $\\kappa=2$, and even faster rates are attained for $\\kappa <2$. We also derive tight bounds for the complexity of learning $x_{f,S}^*$, where the optimal rate is $\\Theta(T^{-\\frac{1}{2\\kappa-2}})$. Interestingly, these precise rates for convex optimization also characterize the complexity of active learning and our results further strengthen the connections between the two fields, both of which rely on feedback-driven queries.", "source": "arxiv/ml"}
{"id": "arxiv:1999", "title": "Distributed Strongly Convex Optimization", "text": "A lot of effort has been invested into characterizing the convergence rates of gradient based algorithms for non-linear convex optimization. Recently, motivated by large datasets and problems in machine learning, the interest has shifted towards distributed optimization. In this work we present a distributed algorithm for strongly convex constrained optimization. Each node in a network of n computers converges to the optimum of a strongly convex, L-Lipchitz continuous, separable objective at a rate O(log (sqrt(n) T) / T) where T is the number of iterations. This rate is achieved in the online setting where the data is revealed one at a time to the nodes, and in the batch setting where each node has access to its full local dataset from the start. The same convergence rate is achieved in expectation when the subgradients used at each node are corrupted with additive zero-mean noise.", "source": "arxiv/ml"}
{"id": "arxiv:2000", "title": "Supervised Texture Classification Using a Novel Compression-Based Similarity Measure", "text": "Supervised pixel-based texture classification is usually performed in the feature space. We propose to perform this task in (dis)similarity space by introducing a new compression-based (dis)similarity measure. The proposed measure utilizes two dimensional MPEG-1 encoder, which takes into consideration the spatial locality and connectivity of pixels in the images. The proposed formulation has been carefully designed based on MPEG encoder functionality. To this end, by design, it solely uses P-frame coding to find the (dis)similarity among patches/images. We show that the proposed measure works properly on both small and large patch sizes. Experimental results show that the proposed approach significantly improves the performance of supervised pixel-based texture classification on Brodatz and outdoor images compared to other compression-based dissimilarity measures as well as approaches performed in feature space. It also improves the computation speed by about 40% compared to its rivals.", "source": "arxiv/ml"}
{"id": "arxiv:2001", "title": "Tracking Tetrahymena Pyriformis Cells using Decision Trees", "text": "Matching cells over time has long been the most difficult step in cell tracking. In this paper, we approach this problem by recasting it as a classification problem. We construct a feature set for each cell, and compute a feature difference vector between a cell in the current frame and a cell in a previous frame. Then we determine whether the two cells represent the same cell over time by training decision trees as our binary classifiers. With the output of decision trees, we are able to formulate an assignment problem for our cell association task and solve it using a modified version of the Hungarian algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2002", "title": "The Price of Privacy in Untrusted Recommendation Engines", "text": "Recent increase in online privacy concerns prompts the following question: can a recommender system be accurate if users do not entrust it with their private data? To answer this, we study the problem of learning item-clusters under local differential privacy, a powerful, formal notion of data privacy. We develop bounds on the sample-complexity of learning item-clusters from privatized user inputs. Significantly, our results identify a sample-complexity separation between learning in an information-rich and an information-scarce regime, thereby highlighting the interaction between privacy and the amount of information (ratings) available to each user. In the information-rich regime, where each user rates at least a constant fraction of items, a spectral clustering approach is shown to achieve a sample-complexity lower bound derived from a simple information-theoretic argument based on Fano's inequality. However, the information-scarce regime, where each user rates only a vanishing fraction of items, is found to require a fundamentally different approach both for lower bounds and algorithms. To this end, we develop new techniques for bounding mutual information under a notion of channel-mismatch, and also propose a new algorithm, MaxSense, and show that it achieves optimal sample-complexity in this setting. The techniques we develop for bounding mutual information may be of broader interest. To illustrate this, we show their applicability to $(i)$ learning based on 1-bit sketches, and $(ii)$ adaptive learning, where queries can be adapted based on answers to past queries.", "source": "arxiv/ml"}
{"id": "arxiv:2003", "title": "Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking", "text": "Visual tracking usually requires an object appearance model that is robust to changing illumination, pose and other factors encountered in video. In this paper, we construct an appearance model using the 3D discrete cosine transform (3D-DCT). The 3D-DCT is based on a set of cosine basis functions, which are determined by the dimensions of the 3D signal and thus independent of the input video data. In addition, the 3D-DCT can generate a compact energy spectrum whose high-frequency coefficients are sparse if the appearance samples are similar. By discarding these high-frequency coefficients, we simultaneously obtain a compact 3D-DCT based object representation and a signal reconstruction-based similarity measure (reflecting the information loss from signal reconstruction). To efficiently update the object representation, we propose an incremental 3D-DCT algorithm, which decomposes the 3D-DCT into successive operations of the 2D discrete cosine transform (2D-DCT) and 1D discrete cosine transform (1D-DCT) on the input video data.", "source": "arxiv/ml"}
{"id": "arxiv:2004", "title": "Dimension Reduction by Mutual Information Feature Extraction", "text": "During the past decades, to study high-dimensional data in a large variety of problems, researchers have proposed many Feature Extraction algorithms. One of the most effective approaches for optimal feature extraction is based on mutual information (MI). However it is not always easy to get an accurate estimation for high dimensional MI. In terms of MI, the optimal feature extraction is creating a feature set from the data which jointly have the largest dependency on the target class and minimum redundancy. In this paper, a component-by-component gradient ascent method is proposed for feature extraction which is based on one-dimensional MI estimates. We will refer to this algorithm as Mutual Information Feature Extraction (MIFX). The performance of this proposed method is evaluated using UCI databases. The results indicate that MIFX provides a robust performance over different data sets which are almost always the best or comparable to the best ones.", "source": "arxiv/ml"}
{"id": "arxiv:2005", "title": "MahNMF: Manhattan Non-negative Matrix Factorization", "text": "Non-negative matrix factorization (NMF) approximates a non-negative matrix $X$ by a product of two non-negative low-rank factor matrices $W$ and $H$. NMF and its extensions minimize either the Kullback-Leibler divergence or the Euclidean distance between $X$ and $W^T H$ to model the Poisson noise or the Gaussian noise. In practice, when the noise distribution is heavy tailed, they cannot perform well. This paper presents Manhattan NMF (MahNMF) which minimizes the Manhattan distance between $X$ and $W^T H$ for modeling the heavy tailed Laplacian noise. Similar to sparse and low-rank matrix decompositions, MahNMF robustly estimates the low-rank part and the sparse part of a non-negative matrix and thus performs effectively when data are contaminated by outliers. We extend MahNMF for various practical applications by developing box-constrained MahNMF, manifold regularized MahNMF, group sparse MahNMF, elastic net inducing MahNMF, and symmetric MahNMF. The major contribution of this paper lies in two fast optimization algorithms for MahNMF and its extensions: the rank-one residual iteration (RRI) method and Nesterov's smoothing method. In particular, by approximating the residual matrix by the outer product of one row of W and one row of $H$ in MahNMF, we develop an RRI method to iteratively update each variable of $W$ and $H$ in a closed form solution. Although RRI is efficient for small scale MahNMF and some of its extensions, it is neither scalable to large scale matrices nor flexible enough to optimize all MahNMF extensions. Since the objective functions of MahNMF and its extensions are neither convex nor smooth, we apply Nesterov's smoothing method to recursively optimize one factor matrix with another matrix fixed. By setting the smoothing parameter inversely proportional to the iteration number, we improve the approximation accuracy iteratively for both MahNMF and its extensions.", "source": "arxiv/ml"}
{"id": "arxiv:2006", "title": "Improved brain pattern recovery through ranking approaches", "text": "Inferring the functional specificity of brain regions from functional Magnetic Resonance Images (fMRI) data is a challenging statistical problem. While the General Linear Model (GLM) remains the standard approach for brain mapping, supervised learning techniques (a.k.a.} decoding) have proven to be useful to capture multivariate statistical effects distributed across voxels and brain regions. Up to now, much effort has been made to improve decoding by incorporating prior knowledge in the form of a particular regularization term. In this paper we demonstrate that further improvement can be made by accounting for non-linearities using a ranking approach rather than the commonly used least-square regression. Through simulation, we compare the recovery properties of our approach to linear models commonly used in fMRI based decoding. We demonstrate the superiority of ranking with a real fMRI dataset.", "source": "arxiv/ml"}
{"id": "arxiv:2007", "title": "Diagnosing client faults using SVM-based intelligent inference from TCP packet traces", "text": "We present the Intelligent Automated Client Diagnostic (IACD) system, which only relies on inference from Transmission Control Protocol (TCP) packet traces for rapid diagnosis of client device problems that cause network performance issues. Using soft-margin Support Vector Machine (SVM) classifiers, the system (i) distinguishes link problems from client problems, and (ii) identifies characteristics unique to client faults to report the root cause of the client device problem. Experimental evaluation demonstrated the capability of the IACD system to distinguish between faulty and healthy links and to diagnose the client faults with 98% accuracy in healthy links. The system can perform fault diagnosis independent of the client's specific TCP implementation, enabling diagnosis capability on diverse range of client computers.", "source": "arxiv/ml"}
{"id": "arxiv:2008", "title": "Learning to rank from medical imaging data", "text": "Medical images can be used to predict a clinical score coding for the severity of a disease, a pain level or the complexity of a cognitive task. In all these cases, the predicted variable has a natural order. While a standard classifier discards this information, we would like to take it into account in order to improve prediction performance. A standard linear regression does model such information, however the linearity assumption is likely not be satisfied when predicting from pixel intensities in an image. In this paper we address these modeling challenges with a supervised learning procedure where the model aims to order or rank images. We use a linear model for its robustness in high dimension and its possible interpretation. We show on simulations and two fMRI datasets that this approach is able to predict the correct ordering on pairs of images, yielding higher prediction accuracy than standard regression and multiclass classification techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2009", "title": "Fusing image representations for classification using support vector machines", "text": "In order to improve classification accuracy different image representations are usually combined. This can be done by using two different fusing schemes. In feature level fusion schemes, image representations are combined before the classification process. In classifier fusion, the decisions taken separately based on individual representations are fused to make a decision. In this paper the main methods derived for both strategies are evaluated. Our experimental results show that classifier fusion performs better. Specifically Bayes belief integration is the best performing strategy for image classification task.", "source": "arxiv/ml"}
{"id": "arxiv:2010", "title": "Towards a Self-Organized Agent-Based Simulation Model for Exploration of Human Synaptic Connections", "text": "In this paper, the early design of our self-organized agent-based simulation model for exploration of synaptic connections that faithfully generates what is observed in natural situation is given. While we take inspiration from neuroscience, our intent is not to create a veridical model of processes in neurodevelopmental biology, nor to represent a real biological system. Instead, our goal is to design a simulation model that learns acting in the same way of human nervous system by using findings on human subjects using reflex methodologies in order to estimate unknown connections.", "source": "arxiv/ml"}
{"id": "arxiv:2011", "title": "Surrogate Losses in Passive and Active Learning", "text": "Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a classifier of relatively low risk, as measured under the 0-1 loss, ideally using fewer label requests than the number of random labeled data points sufficient to achieve the same. This work investigates the potential uses of surrogate loss functions in the context of active learning. Specifically, it presents an active learning algorithm based on an arbitrary classification-calibrated surrogate loss function, along with an analysis of the number of label requests sufficient for the classifier returned by the algorithm to achieve a given risk under the 0-1 loss. Interestingly, these results cannot be obtained by simply optimizing the surrogate risk via active learning to an extent sufficient to provide a guarantee on the 0-1 loss, as is common practice in the analysis of surrogate losses for passive learning. Some of the results have additional implications for the use of surrogate losses in passive learning.", "source": "arxiv/ml"}
{"id": "arxiv:2012", "title": "Accuracy Measures for the Comparison of Classifiers", "text": "The selection of the best classification algorithm for a given dataset is a very widespread problem. It is also a complex one, in the sense it requires to make several important methodological choices. Among them, in this work we focus on the measure used to assess the classification performance and rank the algorithms. We present the most popular measures and discuss their properties. Despite the numerous measures proposed over the years, many of them turn out to be equivalent in this specific case, to have interpretation problems, or to be unsuitable for our purpose. Consequently, classic overall success rate or marginal rates should be preferred for this specific task.", "source": "arxiv/ml"}
{"id": "arxiv:2013", "title": "Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning", "text": "We consider the estimation of an i.i.d. (possibly non-Gaussian) vector $\\xbf \\in \\R^n$ from measurements $\\ybf \\in \\R^m$ obtained by a general cascade model consisting of a known linear transform followed by a probabilistic componentwise (possibly nonlinear) measurement channel. A novel method, called adaptive generalized approximate message passing (Adaptive GAMP), that enables joint learning of the statistics of the prior and measurement channel along with estimation of the unknown vector $\\xbf$ is presented. The proposed algorithm is a generalization of a recently-developed EM-GAMP that uses expectation-maximization (EM) iterations where the posteriors in the E-steps are computed via approximate message passing. The methodology can be applied to a large class of learning problems including the learning of sparse priors in compressed sensing or identification of linear-nonlinear cascade models in dynamical systems and neural spiking processes. We prove that for large i.i.d. Gaussian transform matrices the asymptotic componentwise behavior of the adaptive GAMP algorithm is predicted by a simple set of scalar state evolution equations. In addition, we show that when a certain maximum-likelihood estimation can be performed in each step, the adaptive GAMP method can yield asymptotically consistent parameter estimates, which implies that the algorithm achieves a reconstruction quality equivalent to the oracle algorithm that knows the correct parameter values. Remarkably, this result applies to essentially arbitrary parametrizations of the unknown distributions, including ones that are nonlinear and non-Gaussian. The adaptive GAMP methodology thus provides a systematic, general and computationally efficient method applicable to a large range of complex linear-nonlinear models with provable guarantees.", "source": "arxiv/ml"}
{"id": "arxiv:2014", "title": "Ensemble Clustering with Logic Rules", "text": "In this article, the logic rule ensembles approach to supervised learning is applied to the unsupervised or semi-supervised clustering. Logic rules which were obtained by combining simple conjunctive rules are used to partition the input space and an ensemble of these rules is used to define a similarity matrix. Similarity partitioning is used to partition the data in an hierarchical manner. We have used internal and external measures of cluster validity to evaluate the quality of clusterings or to identify the number of clusters.", "source": "arxiv/ml"}
{"id": "arxiv:2015", "title": "A Two-Stage Combined Classifier in Scale Space Texture Classification", "text": "Textures often show multiscale properties and hence multiscale techniques are considered useful for texture analysis. Scale-space theory as a biologically motivated approach may be used to construct multiscale textures. In this paper various ways are studied to combine features on different scales for texture classification of small image patches. We use the N-jet of derivatives up to the second order at different scales to generate distinct pattern representations (DPR) of feature subsets. Each feature subset in the DPR is given to a base classifier (BC) of a two-stage combined classifier. The decisions made by these BCs are combined in two stages over scales and derivatives. Various combining systems and their significances and differences are discussed. The learning curves are used to evaluate the performances. We found for small sample sizes combining classifiers performs significantly better than combining feature spaces (CFS). It is also shown that combining classifiers performs better than the support vector machine on CFS in multiscale texture classification.", "source": "arxiv/ml"}
{"id": "arxiv:2016", "title": "The Minimum Information Principle for Discriminative Learning", "text": "Exponential models of distributions are widely used in machine learning for classiffication and modelling. It is well known that they can be interpreted as maximum entropy models under empirical expectation constraints. In this work, we argue that for classiffication tasks, mutual information is a more suitable information theoretic measure to be optimized. We show how the principle of minimum mutual information generalizes that of maximum entropy, and provides a comprehensive framework for building discriminative classiffiers. A game theoretic interpretation of our approach is then given, and several generalization bounds provided. We present iterative algorithms for solving the minimum information problem and its convex dual, and demonstrate their performance on various classiffication tasks. The results show that minimum information classiffiers outperform the corresponding maximum entropy models.", "source": "arxiv/ml"}
{"id": "arxiv:2017", "title": "Algebraic Statistics in Model Selection", "text": "We develop the necessary theory in computational algebraic geometry to place Bayesian networks into the realm of algebraic statistics. We present an algebra{statistics dictionary focused on statistical modeling. In particular, we link the notion of effiective dimension of a Bayesian network with the notion of algebraic dimension of a variety. We also obtain the independence and non{independence constraints on the distributions over the observable variables implied by a Bayesian network with hidden variables, via a generating set of an ideal of polynomials associated to the network. These results extend previous work on the subject. Finally, the relevance of these results for model selection is discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2018", "title": "On-line Prediction with Kernels and the Complexity Approximation Principle", "text": "The paper describes an application of Aggregating Algorithm to the problem of regression. It generalizes earlier results concerned with plain linear regression to kernel techniques and presents an on-line algorithm which performs nearly as well as any oblivious kernel predictor. The paper contains the derivation of an estimate on the performance of this algorithm. The estimate is then used to derive an application of the Complexity Approximation Principle to kernel methods.", "source": "arxiv/ml"}
{"id": "arxiv:2019", "title": "Iterative Conditional Fitting for Gaussian Ancestral Graph Models", "text": "Ancestral graph models, introduced by Richardson and Spirtes (2002), generalize both Markov random fields and Bayesian networks to a class of graphs with a global Markov property that is closed under conditioning and marginalization. By design, ancestral graphs encode precisely the conditional independence structures that can arise from Bayesian networks with selection and unobserved (hidden/latent) variables. Thus, ancestral graph models provide a potentially very useful framework for exploratory model selection when unobserved variables might be involved in the data-generating process but no particular hidden structure can be specified. In this paper, we present the Iterative Conditional Fitting (ICF) algorithm for maximum likelihood estimation in Gaussian ancestral graph models. The name reflects that in each step of the procedure a conditional distribution is estimated, subject to constraints, while a marginal distribution is held fixed. This approach is in duality to the well-known Iterative Proportional Fitting algorithm, in which marginal distributions are fitted while conditional distributions are held fixed.", "source": "arxiv/ml"}
{"id": "arxiv:2020", "title": "Applying Discrete PCA in Data Analysis", "text": "Methods for analysis of principal components in discrete data have existed for some time under various names such as grade of membership modelling, probabilistic latent semantic analysis, and genotype inference with admixture. In this paper we explore a number of extensions to the common theory, and present some application of these methods to some common statistical tasks. We show that these methods can be interpreted as a discrete version of ICA. We develop a hierarchical version yielding components at different levels of detail, and additional techniques for Gibbs sampling. We compare the algorithms on a text prediction task using support vector machines, and to information retrieval.", "source": "arxiv/ml"}
{"id": "arxiv:2021", "title": "Exponential Families for Conditional Random Fields", "text": "In this paper we de ne conditional random elds in reproducing kernel Hilbert spaces and show connections to Gaussian Process classi cation. More speci cally, we prove decomposition results for undirected graphical models and we give constructions for kernels. Finally we present e cient means of solving the optimization problem using reduced rank decompositions and we show how stationarity can be exploited e ciently in the optimization process.", "source": "arxiv/ml"}
{"id": "arxiv:2022", "title": "MOB-ESP and other Improvements in Probability Estimation", "text": "A key prerequisite to optimal reasoning under uncertainty in intelligent systems is to start with good class probability estimates. This paper improves on the current best probability estimation trees (Bagged-PETs) and also presents a new ensemble-based algorithm (MOB-ESP). Comparisons are made using several benchmark datasets and multiple metrics. These experiments show that MOB-ESP outputs significantly more accurate class probabilities than either the baseline BPETs algorithm or the enhanced version presented here (EB-PETs). These results are based on metrics closely associated with the average accuracy of the predictions. MOB-ESP also provides much better probability rankings than B-PETs. The paper further suggests how these estimation techniques can be applied in concert with a broader category of classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:2023", "title": "\"Ideal Parent\" Structure Learning for Continuous Variable Networks", "text": "In recent years, there is a growing interest in learning Bayesian networks with continuous variables. Learning the structure of such networks is a computationally expensive procedure, which limits most applications to parameter learning. This problem is even more acute when learning networks with hidden variables. We present a general method for significantly speeding the structure search algorithm for continuous variable networks with common parametric distributions. Importantly, our method facilitates the addition of new hidden variables into the network structure efficiently. We demonstrate the method on several data sets, both for learning structure on fully observable data, and for introducing new hidden variables during structure search.", "source": "arxiv/ml"}
{"id": "arxiv:2024", "title": "Bayesian Learning in Undirected Graphical Models: Approximate MCMC algorithms", "text": "Bayesian learning in undirected graphical models|computing posterior distributions over parameters and predictive quantities is exceptionally difficult. We conjecture that for general undirected models, there are no tractable MCMC (Markov Chain Monte Carlo) schemes giving the correct equilibrium distribution over parameters. While this intractability, due to the partition function, is familiar to those performing parameter optimisation, Bayesian learning of posterior distributions over undirected model parameters has been unexplored and poses novel challenges. we propose several approximate MCMC schemes and test on fully observed binary models (Boltzmann machines) for a small coronary heart disease data set and larger artificial systems. While approximations must perform well on the model, their interaction with the sampling scheme is also important. Samplers based on variational mean- field approximations generally performed poorly, more advanced methods using loopy propagation, brief sampling and stochastic dynamics lead to acceptable parameter posteriors. Finally, we demonstrate these techniques on a Markov random field with hidden variables.", "source": "arxiv/ml"}
{"id": "arxiv:2025", "title": "Active Model Selection", "text": "Classical learning assumes the learner is given a labeled data sample, from which it learns a model. The field of Active Learning deals with the situation where the learner begins not with a training sample, but instead with resources that it can use to obtain information to help identify the optimal model. To better understand this task, this paper presents and analyses the simplified \"(budgeted) active model selection\" version, which captures the pure exploration aspect of many active learning problems in a clean and simple problem formulation. Here the learner can use a fixed budget of \"model probes\" (where each probe evaluates the specified model on a random indistinguishable instance) to identify which of a given set of possible models has the highest expected accuracy. Our goal is a policy that sequentially determines which model to probe next, based on the information observed so far. We present a formal description of this task, and show that it is NPhard in general. We then investigate a number of algorithms for this task, including several existing ones (eg, \"Round-Robin\", \"Interval Estimation\", \"Gittins\") as well as some novel ones (e.g., \"Biased-Robin\"), describing first their approximation properties and then their empirical performance on various problem instances. We observe empirically that the simple biased-robin algorithm significantly outperforms the other algorithms in the case of identical costs and priors.", "source": "arxiv/ml"}
{"id": "arxiv:2026", "title": "An Extended Cencov-Campbell Characterization of Conditional Information Geometry", "text": "We formulate and prove an axiomatic characterization of conditional information geometry, for both the normalized and the nonnormalized cases. This characterization extends the axiomatic derivation of the Fisher geometry by Cencov and Campbell to the cone of positive conditional models, and as a special case to the manifold of conditional distributions. Due to the close connection between the conditional I-divergence and the product Fisher information metric the characterization provides a new axiomatic interpretation of the primal problems underlying logistic regression and AdaBoost.", "source": "arxiv/ml"}
{"id": "arxiv:2027", "title": "Conditional Chow-Liu Tree Structures for Modeling Discrete-Valued Vector Time Series", "text": "We consider the problem of modeling discrete-valued vector time series data using extensions of Chow-Liu tree models to capture both dependencies across time and dependencies across variables. Conditional Chow-Liu tree models are introduced, as an extension to standard Chow-Liu trees, for modeling conditional rather than joint densities. We describe learning algorithms for such models and show how they can be used to learn parsimonious representations for the output distributions in hidden Markov models. These models are applied to the important problem of simulating and forecasting daily precipitation occurrence for networks of rain stations. To demonstrate the effectiveness of the models, we compare their performance versus a number of alternatives using historical precipitation data from Southwestern Australia and the Western United States. We illustrate how the structure and parameters of the models can be used to provide an improved meteorological interpretation of such data.", "source": "arxiv/ml"}
{"id": "arxiv:2028", "title": "A Generative Bayesian Model for Aggregating Experts' Probabilities", "text": "In order to improve forecasts, a decisionmaker often combines probabilities given by various sources, such as human experts and machine learning classifiers. When few training data are available, aggregation can be improved by incorporating prior knowledge about the event being forecasted and about salient properties of the experts. To this end, we develop a generative Bayesian aggregation model for probabilistic classi cation. The model includes an event-specific prior, measures of individual experts' bias, calibration, accuracy, and a measure of dependence betweeen experts. Rather than require absolute measures, we show that aggregation may be expressed in terms of relative accuracy between experts. The model results in a weighted logarithmic opinion pool (LogOps) that satis es consistency criteria such as the external Bayesian property. We derive analytic solutions for independent and for exchangeable experts. Empirical tests demonstrate the model's use, comparing its accuracy with other aggregation methods.", "source": "arxiv/ml"}
{"id": "arxiv:2029", "title": "A Bayesian Approach toward Active Learning for Collaborative Filtering", "text": "Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples given by the active user, the more accurate the predicted ratings will be. Active learning provides an effective way to acquire the most informative rated examples from active users. Previous work on active learning for collaborative filtering only considers the expected loss function based on the estimated model, which can be misleading when the estimated model is inaccurate. This paper takes one step further by taking into account of the posterior distribution of the estimated model, which results in more robust active learning algorithm. Empirical studies with datasets of movie ratings show that when the number of ratings from the active user is restricted to be small, active learning methods only based on the estimated model don't perform well while the active learning method using the model distribution achieves substantially better performance.", "source": "arxiv/ml"}
{"id": "arxiv:2030", "title": "Dynamical Systems Trees", "text": "We propose dynamical systems trees (DSTs) as a flexible class of models for describing multiple processes that interact via a hierarchy of aggregating parent chains. DSTs extend Kalman filters, hidden Markov models and nonlinear dynamical systems to an interactive group scenario. Various individual processes interact as communities and sub-communities in a tree structure that is unrolled in time. To accommodate nonlinear temporal activity, each individual leaf process is modeled as a dynamical system containing discrete and/or continuous hidden states with discrete and/or Gaussian emissions. Subsequent higher level parent processes act like hidden Markov models and mediate the interaction between leaf processes or between other parent processes in the hierarchy. Aggregator chains are parents of child processes that they combine and mediate, yielding a compact overall parameterization. We provide tractable inference and learning algorithms for arbitrary DST topologies via an efficient structured mean-field algorithm. The diverse applicability of DSTs is demonstrated by experiments on gene expression data and by modeling group behavior in the setting of an American football game.", "source": "arxiv/ml"}
{"id": "arxiv:2031", "title": "From Fields to Trees", "text": "We present new MCMC algorithms for computing the posterior distributions and expectations of the unknown variables in undirected graphical models with regular structure. For demonstration purposes, we focus on Markov Random Fields (MRFs). By partitioning the MRFs into non-overlapping trees, it is possible to compute the posterior distribution of a particular tree exactly by conditioning on the remaining tree. These exact solutions allow us to construct efficient blocked and Rao-Blackwellised MCMC algorithms. We show empirically that tree sampling is considerably more efficient than other partitioned sampling schemes and the naive Gibbs sampler, even in cases where loopy belief propagation fails to converge. We prove that tree sampling exhibits lower variance than the naive Gibbs sampler and other naive partitioning schemes using the theoretical measure of maximal correlation. We also construct new information theory tools for comparing different MCMC schemes and show that, under these, tree sampling is more efficient.", "source": "arxiv/ml"}
{"id": "arxiv:2032", "title": "PAC-learning bounded tree-width Graphical Models", "text": "We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Ho gen ([7]) have shown that this class is PAC-learnable by reducing it to a combinatorial optimization problem. However, for k > 1, this problem is NP-complete ([15]), and so unless P=NP, these approaches will take exponential amounts of time. Our approach differs significantly from these, in that it first attempts to find approximate conditional independencies by solving (polynomially many) submodular optimization problems, and then using a dynamic programming formulation to combine the approximate conditional independence information to derive a graphical model with underlying graph of the tree-width specified. This gives us an efficient (polynomial time in the number of random variables) PAC-learning algorithm which requires only polynomial number of samples of the true distribution, and only polynomial running time.", "source": "arxiv/ml"}
{"id": "arxiv:2033", "title": "Maximum Entropy for Collaborative Filtering", "text": "Within the task of collaborative filtering two challenges for computing conditional probabilities exist. First, the amount of training data available is typically sparse with respect to the size of the domain. Thus, support for higher-order interactions is generally not present. Second, the variables that we are conditioning upon vary for each query. That is, users label different variables during each query. For this reason, there is no consistent input to output mapping. To address these problems we purpose a maximum entropy approach using a non-standard measure of entropy. This approach can be simplified to solving a set of linear equations that can be efficiently solved.", "source": "arxiv/ml"}
{"id": "arxiv:2034", "title": "Similarity-Driven Cluster Merging Method for Unsupervised Fuzzy Clustering", "text": "In this paper, a similarity-driven cluster merging method is proposed for unsuper-vised fuzzy clustering. The cluster merging method is used to resolve the problem of cluster validation. Starting with an overspecified number of clusters in the data, pairs of similar clusters are merged based on the proposed similarity-driven cluster merging criterion. The similarity between clusters is calculated by a fuzzy cluster similarity matrix, while an adaptive threshold is used for merging. In addition, a modified generalized ob- jective function is used for prototype-based fuzzy clustering. The function includes the p-norm distance measure as well as principal components of the clusters. The number of the principal components is determined automatically from the data being clustered. The properties of this unsupervised fuzzy clustering algorithm are illustrated by several experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2035", "title": "Graph partition strategies for generalized mean field inference", "text": "An autonomous variational inference algorithm for arbitrary graphical models requires the ability to optimize variational approximations over the space of model parameters as well as over the choice of tractable families used for the variational approximation. In this paper, we present a novel combination of graph partitioning algorithms with a generalized mean field (GMF) inference algorithm. This combination optimizes over disjoint clustering of variables and performs inference using those clusters. We provide a formal analysis of the relationship between the graph cut and the GMF approximation, and explore several graph partition strategies empirically. Our empirical results provide rather clear support for a weighted version of MinCut as a useful clustering algorithm for GMF inference, which is consistent with the implications from the formal analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2036", "title": "An Integrated, Conditional Model of Information Extraction and Coreference with Applications to Citation Matching", "text": "Although information extraction and coreference resolution appear together in many applications, most current systems perform them as ndependent steps. This paper describes an approach to integrated inference for extraction and coreference based on conditionally-trained undirected graphical models. We discuss the advantages of conditional probability training, and of a coreference model structure based on graph partitioning. On a data set of research paper citations, we show significant reduction in error by using extraction uncertainty to improve coreference citation matching accuracy, and using coreference to improve the accuracy of the extracted fields.", "source": "arxiv/ml"}
{"id": "arxiv:2037", "title": "On the Choice of Regions for Generalized Belief Propagation", "text": "Generalized belief propagation (GBP) has proven to be a promising technique for approximate inference tasks in AI and machine learning. However, the choice of a good set of clusters to be used in GBP has remained more of an art then a science until this day. This paper proposes a sequential approach to adding new clusters of nodes and their interactions (i.e. \"regions\") to the approximation. We first review and analyze the recently introduced region graphs and find that three kinds of operations (\"split\", \"merge\" and \"death\") leave the free energy and (under some conditions) the fixed points of GBP invariant. This leads to the notion of \"weakly irreducible\" regions as the natural candidates to be added to the approximation. Computational complexity of the GBP algorithm is controlled by restricting attention to regions with small \"region-width\". Combining the above with an efficient (i.e. local in the graph) measure to predict the improved accuracy of GBP leads to the sequential \"region pursuit\" algorithm for adding new regions bottom-up to the region graph. Experiments show that this algorithm can indeed perform close to optimally.", "source": "arxiv/ml"}
{"id": "arxiv:2038", "title": "ARMA Time-Series Modeling with Graphical Models", "text": "We express the classic ARMA time-series model as a directed graphical model. In doing so, we find that the deterministic relationships in the model make it effectively impossible to use the EM algorithm for learning model parameters. To remedy this problem, we replace the deterministic relationships with Gaussian distributions having a small variance, yielding the stochastic ARMA (ARMA) model. This modification allows us to use the EM algorithm to learn parmeters and to forecast,even in situations where some data is missing. This modification, in conjunction with the graphicalmodel approach, also allows us to include cross predictors in situations where there are multiple times series and/or additional nontemporal covariates. More surprising,experiments suggest that the move to stochastic ARMA yields improved accuracy through better smoothing. We demonstrate improvements afforded by cross prediction and better smoothing on real data.", "source": "arxiv/ml"}
{"id": "arxiv:2039", "title": "Factored Latent Analysis for far-field tracking data", "text": "This paper uses Factored Latent Analysis (FLA) to learn a factorized, segmental representation for observations of tracked objects over time. Factored Latent Analysis is latent class analysis in which the observation space is subdivided and each aspect of the original space is represented by a separate latent class model. One could simply treat these factors as completely independent and ignore their interdependencies or one could concatenate them together and attempt to learn latent class structure for the complete observation space. Alternatively, FLA allows the interdependencies to be exploited in estimating an effective model, which is also capable of representing a factored latent state. In this paper, FLA is used to learn a set of factored latent classes to represent different modalities of observations of tracked objects. Different characteristics of the state of tracked objects are each represented by separate latent class models, including normalized size, normalized speed, normalized direction, and position. This model also enables effective temporal segmentation of these sequences. This method is data-driven, unsupervised using only pairwise observation statistics. This data-driven and unsupervised activity classi- fication technique exhibits good performance in multiple challenging environments.", "source": "arxiv/ml"}
{"id": "arxiv:2040", "title": "Predictive State Representations: A New Theory for Modeling Dynamical Systems", "text": "Modeling dynamical systems, both for control purposes and to make predictions about their behavior, is ubiquitous in science and engineering. Predictive state representations (PSRs) are a recently introduced class of models for discrete-time dynamical systems. The key idea behind PSRs and the closely related OOMs (Jaeger's observable operator models) is to represent the state of the system as a set of predictions of observable outcomes of experiments one can do in the system. This makes PSRs rather different from history-based models such as nth-order Markov models and hidden-state-based models such as HMMs and POMDPs. We introduce an interesting construct, the systemdynamics matrix, and show how PSRs can be derived simply from it. We also use this construct to show formally that PSRs are more general than both nth-order Markov models and HMMs/POMDPs. Finally, we discuss the main difference between PSRs and OOMs and conclude with directions for future work.", "source": "arxiv/ml"}
{"id": "arxiv:2041", "title": "The Author-Topic Model for Authors and Documents", "text": "We introduce the author-topic model, a generative model for documents that extends Latent Dirichlet Allocation (LDA; Blei, Ng, & Jordan, 2003) to include authorship information. Each author is associated with a multinomial distribution over topics and each topic is associated with a multinomial distribution over words. A document with multiple authors is modeled as a distribution over topics that is a mixture of the distributions associated with the authors. We apply the model to a collection of 1,700 NIPS conference papers and 160,000 CiteSeer abstracts. Exact inference is intractable for these datasets and we use Gibbs sampling to estimate the topic and author distributions. We compare the performance with two other generative models for documents, which are special cases of the author-topic model: LDA (a topic model) and a simple author model in which each author is associated with a distribution over words rather than a distribution over topics. We show topics recovered by the author-topic model, and demonstrate applications to computing similarity between authors and entropy of author output.", "source": "arxiv/ml"}
{"id": "arxiv:2042", "title": "Variational Chernoff Bounds for Graphical Models", "text": "Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual parameters that are often used as heuristic estimates of the marginal probabilities required in inference and learning. However these variational estimates do not give rigorous bounds on marginal probabilities, nor do they give estimates for probabilities of more general events than simple marginals. In this paper we build on this recent work by deriving rigorous upper and lower bounds on event probabilities for graphical models. Our approach is based on the use of generalized Chernoff bounds to express bounds on event probabilities in terms of convex optimization problems; these optimization problems, in turn, require estimates of generalized log partition functions. Simulations indicate that this technique can result in useful, rigorous bounds to complement the heuristic variational estimates, with comparable computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:2043", "title": "A Hierarchical Graphical Model for Record Linkage", "text": "The task of matching co-referent records is known among other names as rocord linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonable clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised methods. In this paper, we describe a hierarchical graphical model framework for the linakge-problem in an unsupervised setting. In addition to proposing new methods, we also cast existing unsupervised probabilistic record-linkage methods in this framework. Some of the techniques we propose to minimize overfitting in the above model are of interest in the general graphical model setting. We describe a method for incorporating monotinicity constraints in a graphical model. We also outline a bootstrapping approach of using \"single-field\" classifiers to noisily label latent variables in a hierarchical model. Experimental results show that our proposed unsupervised methods perform quite competitively even with fully supervised record-linkage methods.", "source": "arxiv/ml"}
{"id": "arxiv:2044", "title": "On the Statistical Efficiency of $\\ell_{1,p}$ Multi-Task Learning of Gaussian Graphical Models", "text": "In this paper, we present $\\ell_{1,p}$ multi-task structure learning for Gaussian graphical models. We analyze the sufficient number of samples for the correct recovery of the support union and edge signs. We also analyze the necessary number of samples for any conceivable method by providing information-theoretic lower bounds. We compare the statistical efficiency of multi-task learning versus that of single-task learning. For experiments, we use a block coordinate descent method that is provably convergent and generates a sequence of positive definite solutions. We provide experimental validation on synthetic data as well as on two publicly available real-world data sets, including functional magnetic resonance imaging and gene expression data.", "source": "arxiv/ml"}
{"id": "arxiv:2045", "title": "Better Mixing via Deep Representations", "text": "It has previously been hypothesized, and supported with some experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of variation. We study the following related conjecture: better representations, in the sense of better disentangling, can be exploited to produce faster-mixing Markov chains. Consequently, mixing would be more efficient at higher levels of representation. To better understand why and how this is happening, we propose a secondary conjecture: the higher-level samples fill more uniformly the space they occupy and the high-density manifolds tend to unfold when represented at higher levels. The paper discusses these hypotheses and tests them experimentally through visualization and measurements of mixing and interpolating between samples.", "source": "arxiv/ml"}
{"id": "arxiv:2046", "title": "Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions", "text": "We develop and analyze stochastic optimization algorithms for problems in which the expected loss is strongly convex, and the optimum is (approximately) sparse. Previous approaches are able to exploit only one of these two structures, yielding an $\\order(\\pdim/T)$ convergence rate for strongly convex objectives in $\\pdim$ dimensions, and an $\\order(\\sqrt{(\\spindex \\log \\pdim)/T})$ convergence rate when the optimum is $\\spindex$-sparse. Our algorithm is based on successively solving a series of $\\ell_1$-regularized optimization problems using Nesterov's dual averaging algorithm. We establish that the error of our solution after $T$ iterations is at most $\\order((\\spindex \\log\\pdim)/T)$, with natural extensions to approximate sparsity. Our results apply to locally Lipschitz losses including the logistic, exponential, hinge and least-squares losses. By recourse to statistical minimax results, we show that our convergence rates are optimal up to multiplicative constant factors. The effectiveness of our approach is also confirmed in numerical simulations, in which we compare to several baselines on a least-squares regression problem.", "source": "arxiv/ml"}
{"id": "arxiv:2047", "title": "Protein Function Prediction Based on Kernel Logistic Regression with 2-order Graphic Neighbor Information", "text": "To enhance the accuracy of protein-protein interaction function prediction, a 2-order graphic neighbor information feature extraction method based on undirected simple graph is proposed in this paper, which extends the 1-order graphic neighbor featureextraction method. And the chi-square test statistical method is also involved in feature combination. To demonstrate the effectiveness of our 2-order graphic neighbor feature, four logistic regression models (logistic regression (abbrev. LR), diffusion kernel logistic regression (abbrev. DKLR), polynomial kernel logistic regression (abbrev. PKLR), and radial basis function (RBF) based kernel logistic regression (abbrev. RBF KLR)) are investigated on the two feature sets. The experimental results of protein function prediction of Yeast Proteome Database (YPD) using the the protein-protein interaction data of Munich Information Center for Protein Sequences (MIPS) show that 2-order graphic neighbor information of proteins can significantly improve the average overall percentage of protein function prediction especially with RBF KLR. And, with a new 5-top chi-square feature combination method, RBF KLR can achieve 99.05% average overall percentage on 2-order neighbor feature combination set.", "source": "arxiv/ml"}
{"id": "arxiv:2048", "title": "Local stability of Belief Propagation algorithm with multiple fixed points", "text": "A number of problems in statistical physics and computer science can be expressed as the computation of marginal probabilities over a Markov random field. Belief propagation, an iterative message-passing algorithm, computes exactly such marginals when the underlying graph is a tree. But it has gained its popularity as an efficient way to approximate them in the more general case, even if it can exhibits multiple fixed points and is not guaranteed to converge. In this paper, we express a new sufficient condition for local stability of a belief propagation fixed point in terms of the graph structure and the beliefs values at the fixed point. This gives credence to the usual understanding that Belief Propagation performs better on sparse graphs.", "source": "arxiv/ml"}
{"id": "arxiv:2049", "title": "Proceedings of the 29th International Conference on Machine Learning (ICML-12)", "text": "This is an index to the papers that appear in the Proceedings of the 29th International Conference on Machine Learning (ICML-12). The conference was held in Edinburgh, Scotland, June 27th - July 3rd, 2012.", "source": "arxiv/ml"}
{"id": "arxiv:2050", "title": "Block-Coordinate Frank-Wolfe Optimization for Structural SVMs", "text": "We propose a randomized block-coordinate variant of the classic Frank-Wolfe algorithm for convex optimization with block-separable constraints. Despite its lower iteration cost, we show that it achieves a similar convergence rate in duality gap as the full Frank-Wolfe algorithm. We also show that, when applied to the dual structural support vector machine (SVM) objective, this yields an online algorithm that has the same low iteration complexity as primal stochastic subgradient methods. However, unlike stochastic subgradient methods, the block-coordinate Frank-Wolfe algorithm allows us to compute the optimal step-size and yields a computable duality gap guarantee. Our experiments indicate that this simple algorithm outperforms competing structural SVM solvers.", "source": "arxiv/ml"}
{"id": "arxiv:2051", "title": "Hierarchical Clustering using Randomly Selected Similarities", "text": "The problem of hierarchical clustering items from pairwise similarities is found across various scientific disciplines, from biology to networking. Often, applications of clustering techniques are limited by the cost of obtaining similarities between pairs of items. While prior work has been developed to reconstruct clustering using a significantly reduced set of pairwise similarities via adaptive measurements, these techniques are only applicable when choice of similarities are available to the user. In this paper, we examine reconstructing hierarchical clustering under similarity observations at-random. We derive precise bounds which show that a significant fraction of the hierarchical clustering can be recovered using fewer than all the pairwise similarities. We find that the correct hierarchical clustering down to a constant fraction of the total number of items (i.e., clusters sized O(N)) can be found using only O(N log N) randomly selected pairwise similarities in expectation.", "source": "arxiv/ml"}
{"id": "arxiv:2052", "title": "Automorphism Groups of Graphical Models and Lifted Variational Inference", "text": "Using the theory of group action, we first introduce the concept of the automorphism group of an exponential family or a graphical model, thus formalizing the general notion of symmetry of a probabilistic model. This automorphism group provides a precise mathematical framework for lifted inference in the general exponential family. Its group action partitions the set of random variables and feature functions into equivalent classes (called orbits) having identical marginals and expectations. Then the inference problem is effectively reduced to that of computing marginals or expectations for each class, thus avoiding the need to deal with each individual variable or feature. We demonstrate the usefulness of this general framework in lifting two classes of variational approximation for MAP inference: local LP relaxation and local LP relaxation with cycle constraints; the latter yields the first lifted inference that operate on a bound tighter than local constraints. Initial experimental results demonstrate that lifted MAP inference with cycle constraints achieved the state of the art performance, obtaining much better objective function values than local approximation while remaining relatively efficient.", "source": "arxiv/ml"}
{"id": "arxiv:2053", "title": "Motion Planning Of an Autonomous Mobile Robot Using Artificial Neural Network", "text": "The paper presents the electronic design and motion planning of a robot based on decision making regarding its straight motion and precise turn using Artificial Neural Network (ANN). The ANN helps in learning of robot so that it performs motion autonomously. The weights calculated are implemented in microcontroller. The performance has been tested to be excellent.", "source": "arxiv/ml"}
{"id": "arxiv:2054", "title": "Fast nonparametric classification based on data depth", "text": "A new procedure, called DDa-procedure, is developed to solve the problem of classifying d-dimensional objects into q >= 2 classes. The procedure is completely nonparametric; it uses q-dimensional depth plots and a very efficient algorithm for discrimination analysis in the depth space [0,1]^q. Specifically, the depth is the zonoid depth, and the algorithm is the alpha-procedure. In case of more than two classes several binary classifications are performed and a majority rule is applied. Special treatments are discussed for 'outsiders', that is, data having zero depth vector. The DDa-classifier is applied to simulated as well as real data, and the results are compared with those of similar procedures that have been recently proposed. In most cases the new procedure has comparable error rates, but is much faster than other classification approaches, including the SVM.", "source": "arxiv/ml"}
{"id": "arxiv:2055", "title": "Learning Probabilistic Systems from Tree Samples", "text": "We consider the problem of learning a non-deterministic probabilistic system consistent with a given finite set of positive and negative tree samples. Consistency is defined with respect to strong simulation conformance. We propose learning algorithms that use traditional and a new \"stochastic\" state-space partitioning, the latter resulting in the minimum number of states. We then use them to solve the problem of \"active learning\", that uses a knowledgeable teacher to generate samples as counterexamples to simulation equivalence queries. We show that the problem is undecidable in general, but that it becomes decidable under a suitable condition on the teacher which comes naturally from the way samples are generated from failed simulation checks. The latter problem is shown to be undecidable if we impose an additional condition on the learner to always conjecture a \"minimum state\" hypothesis. We therefore propose a semi-algorithm using stochastic partitions. Finally, we apply the proposed (semi-) algorithms to infer intermediate assumptions in an automated assume-guarantee verification framework for probabilistic systems.", "source": "arxiv/ml"}
{"id": "arxiv:2056", "title": "Causal Inference on Time Series using Structural Equation Models", "text": "Causal inference uses observations to infer the causal structure of the data generating system. We study a class of functional models that we call Time Series Models with Independent Noise (TiMINo). These models require independent residual time series, whereas traditional methods like Granger causality exploit the variance of residuals. There are two main contributions: (1) Theoretical: By restricting the model class (e.g. to additive noise) we can provide a more general identifiability result than existing ones. This result incorporates lagged and instantaneous effects that can be nonlinear and do not need to be faithful, and non-instantaneous feedbacks between the time series. (2) Practical: If there are no feedback loops between time series, we propose an algorithm based on non-linear independence tests of time series. When the data are causally insufficient, or the data generating process does not satisfy the model assumptions, this algorithm may still give partial results, but mostly avoids incorrect answers. An extension to (non-instantaneous) feedbacks is possible, but not discussed. It outperforms existing methods on artificial and real data. Code can be provided upon request.", "source": "arxiv/ml"}
{"id": "arxiv:2057", "title": "Meta-Learning of Exploration/Exploitation Strategies: The Multi-Armed Bandit Case", "text": "The exploration/exploitation (E/E) dilemma arises naturally in many subfields of Science. Multi-armed bandit problems formalize this dilemma in its canonical form. Most current research in this field focuses on generic solutions that can be applied to a wide range of problems. However, in practice, it is often the case that a form of prior information is available about the specific class of target problems. Prior knowledge is rarely used in current solutions due to the lack of a systematic approach to incorporate it into the E/E strategy. To address a specific class of E/E problems, we propose to proceed in three steps: (i) model prior knowledge in the form of a probability distribution over the target class of E/E problems; (ii) choose a large hypothesis space of candidate E/E strategies; and (iii), solve an optimization problem to find a candidate E/E strategy of maximal average performance over a sample of problems drawn from the prior distribution. We illustrate this meta-learning approach with two different hypothesis spaces: one where E/E strategies are numerically parameterized and another where E/E strategies are represented as small symbolic formulas. We propose appropriate optimization algorithms for both cases. Our experiments, with two-armed Bernoulli bandit problems and various playing budgets, show that the meta-learnt E/E strategies outperform generic strategies of the literature (UCB1, UCB1-Tuned, UCB-v, KL-UCB and epsilon greedy); they also evaluate the robustness of the learnt E/E strategies, by tests carried out on arms whose rewards follow a truncated Gaussian distribution.", "source": "arxiv/ml"}
{"id": "arxiv:2058", "title": "Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality", "text": "We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and on the Good-Turing missing mass estimator. We prove two different regret bounds on the performance of this algorithm under weak assumptions on the probabilistic experts. Under more restrictive hypotheses, we also prove a macroscopic optimality result, comparing the algorithm both with an oracle strategy and with uniform sampling. Finally, we provide numerical experiments illustrating these theoretical findings.", "source": "arxiv/ml"}
{"id": "arxiv:2059", "title": "A Robust Signal Classification Scheme for Cognitive Radio", "text": "This paper presents a robust signal classification scheme for achieving comprehensive spectrum sensing of multiple coexisting wireless systems. It is built upon a group of feature-based signal detection algorithms enhanced by the proposed dimension cancelation (DIC) method for mitigating the noise uncertainty problem. The classification scheme is implemented on our testbed consisting real-world wireless devices. The simulation and experimental performances agree with each other well and shows the effectiveness and robustness of the proposed scheme.", "source": "arxiv/ml"}
{"id": "arxiv:2060", "title": "Generalization Bounds for Metric and Similarity Learning", "text": "Recently, metric learning and similarity learning have attracted a large amount of interest. Many models and optimisation algorithms have been proposed. However, there is relatively little work on the generalization analysis of such methods. In this paper, we derive novel generalization bounds of metric and similarity learning. In particular, we first show that the generalization analysis reduces to the estimation of the Rademacher average over \"sums-of-i.i.d.\" sample-blocks related to the specific matrix norm. Then, we derive generalization bounds for metric/similarity learning with different matrix-norm regularisers by estimating their specific Rademacher complexities. Our analysis indicates that sparse metric/similarity learning with $L^1$-norm regularisation could lead to significantly better bounds than those with Frobenius-norm regularisation. Our novel generalization analysis develops and refines the techniques of U-statistics and Rademacher complexity analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2061", "title": "MCTS Based on Simple Regret", "text": "UCT, a state-of-the art algorithm for Monte Carlo tree search (MCTS) in games and Markov decision processes, is based on UCB, a sampling policy for the Multi-armed Bandit problem (MAB) that minimizes the cumulative regret. However, search differs from MAB in that in MCTS it is usually only the final \"arm pull\" (the actual move selection) that collects a reward, rather than all \"arm pulls\". Therefore, it makes more sense to minimize the simple regret, as opposed to the cumulative regret. We begin by introducing policies for multi-armed bandits with lower finite-time and asymptotic simple regret than UCB, using it to develop a two-stage scheme (SR+CR) for MCTS which outperforms UCT empirically. Optimizing the sampling process is itself a metareasoning problem, a solution of which can use value of information (VOI) techniques. Although the theory of VOI for search exists, applying it to MCTS is non-trivial, as typical myopic assumptions fail. Lacking a complete working VOI theory for MCTS, we nevertheless propose a sampling scheme that is \"aware\" of VOI, achieving an algorithm that in empirical evaluation outperforms both UCT and the other proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2062", "title": "Bellman Error Based Feature Generation using Random Projections on Sparse Spaces", "text": "We address the problem of automatic generation of features for value function approximation. Bellman Error Basis Functions (BEBFs) have been shown to improve the error of policy evaluation with function approximation, with a convergence rate similar to that of value iteration. We propose a simple, fast and robust algorithm based on random projections to generate BEBFs for sparse feature spaces. We provide a finite sample analysis of the proposed method, and prove that projections logarithmic in the dimension of the original space are enough to guarantee contraction in the error. Empirical results demonstrate the strength of this method.", "source": "arxiv/ml"}
{"id": "arxiv:2063", "title": "VOI-aware MCTS", "text": "UCT, a state-of-the art algorithm for Monte Carlo tree search (MCTS) in games and Markov decision processes, is based on UCB1, a sampling policy for the Multi-armed Bandit problem (MAB) that minimizes the cumulative regret. However, search differs from MAB in that in MCTS it is usually only the final \"arm pull\" (the actual move selection) that collects a reward, rather than all \"arm pulls\". In this paper, an MCTS sampling policy based on Value of Information (VOI) estimates of rollouts is suggested. Empirical evaluation of the policy and comparison to UCB1 and UCT is performed on random MAB instances as well as on Computer Go.", "source": "arxiv/ml"}
{"id": "arxiv:2064", "title": "A New Training Algorithm for Kanerva's Sparse Distributed Memory", "text": "The Sparse Distributed Memory proposed by Pentii Kanerva (SDM in short) was thought to be a model of human long term memory. The architecture of the SDM permits to store binary patterns and to retrieve them using partially matching patterns. However Kanerva's model is especially efficient only in handling random data. The purpose of this article is to introduce a new approach of training Kanerva's SDM that can handle efficiently non-random data, and to provide it the capability to recognize inverted patterns. This approach uses a signal model which is different from the one proposed for different purposes by Hely, Willshaw and Hayes in [4]. This article additionally suggests a different way of creating hard locations in the memory despite the Kanerva's static model.", "source": "arxiv/ml"}
{"id": "arxiv:2065", "title": "Equivalence of distance-based and RKHS-based statistics in hypothesis testing", "text": "We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, maximum mean discrepancies (MMD), that is, distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning. In the case where the energy distance is computed with a semimetric of negative type, a positive definite kernel, termed distance kernel, may be defined such that the MMD corresponds exactly to the energy distance. Conversely, for any positive definite kernel, we can interpret the MMD as energy distance with respect to some negative-type semimetric. This equivalence readily extends to distance covariance using kernels on the product space. We determine the class of probability distributions for which the test statistics are consistent against all alternatives. Finally, we investigate the performance of the family of distance kernels in two-sample and independence tests: we show in particular that the energy distance most commonly employed in statistics is just one member of a parametric family of kernels, and that other choices from this family can yield more powerful tests.", "source": "arxiv/ml"}
{"id": "arxiv:2066", "title": "Determinantal point processes for machine learning", "text": "Determinantal point processes (DPPs) are elegant probabilistic models of repulsion that arise in quantum physics and random matrix theory. In contrast to traditional structured models like Markov random fields, which become intractable and hard to approximate in the presence of negative correlations, DPPs offer efficient and exact algorithms for sampling, marginalization, conditioning, and other inference tasks. We provide a gentle introduction to DPPs, focusing on the intuitions, algorithms, and extensions that are most relevant to the machine learning community, and show how DPPs can be applied to real-world applications like finding diverse sets of high-quality search results, building informative summaries by selecting diverse sentences from documents, modeling non-overlapping human poses in images or video, and automatically building timelines of important news stories.", "source": "arxiv/ml"}
{"id": "arxiv:2067", "title": "Touchalytics: On the Applicability of Touchscreen Input as a Behavioral Biometric for Continuous Authentication", "text": "We investigate whether a classifier can continuously authenticate users based on the way they interact with the touchscreen of a smart phone. We propose a set of 30 behavioral touch features that can be extracted from raw touchscreen logs and demonstrate that different users populate distinct subspaces of this feature space. In a systematic experiment designed to test how this behavioral pattern exhibits consistency over time, we collected touch data from users interacting with a smart phone using basic navigation maneuvers, i.e., up-down and left-right scrolling. We propose a classification framework that learns the touch behavior of a user during an enrollment phase and is able to accept or reject the current user by monitoring interaction with the touch screen. The classifier achieves a median equal error rate of 0% for intra-session authentication, 2%-3% for inter-session authentication and below 4% when the authentication test was carried out one week after the enrollment phase. While our experimental findings disqualify this method as a standalone authentication mechanism for long-term authentication, it could be implemented as a means to extend screen-lock time or as a part of a multi-modal biometric authentication system.", "source": "arxiv/ml"}
{"id": "arxiv:2068", "title": "On When and How to use SAT to Mine Frequent Itemsets", "text": "A new stream of research was born in the last decade with the goal of mining itemsets of interest using Constraint Programming (CP). This has promoted a natural way to combine complex constraints in a highly flexible manner. Although CP state-of-the-art solutions formulate the task using Boolean variables, the few attempts to adopt propositional Satisfiability (SAT) provided an unsatisfactory performance. This work deepens the study on when and how to use SAT for the frequent itemset mining (FIM) problem by defining different encodings with multiple task-driven enumeration options and search strategies. Although for the majority of the scenarios SAT-based solutions appear to be non-competitive with CP peers, results show a variety of interesting cases where SAT encodings are the best option.", "source": "arxiv/ml"}
{"id": "arxiv:2069", "title": "Identifying Users From Their Rating Patterns", "text": "This paper reports on our analysis of the 2011 CAMRa Challenge dataset (Track 2) for context-aware movie recommendation systems. The train dataset comprises 4,536,891 ratings provided by 171,670 users on 23,974$ movies, as well as the household groupings of a subset of the users. The test dataset comprises 5,450 ratings for which the user label is missing, but the household label is provided. The challenge required to identify the user labels for the ratings in the test set. Our main finding is that temporal information (time labels of the ratings) is significantly more useful for achieving this objective than the user preferences (the actual ratings). Using a model that leverages on this fact, we are able to identify users within a known household with an accuracy of approximately 96% (i.e. misclassification rate around 4%).", "source": "arxiv/ml"}
{"id": "arxiv:2070", "title": "Optimal Data Collection For Informative Rankings Expose Well-Connected Graphs", "text": "Given a graph where vertices represent alternatives and arcs represent pairwise comparison data, the statistical ranking problem is to find a potential function, defined on the vertices, such that the gradient of the potential function agrees with the pairwise comparisons. Our goal in this paper is to develop a method for collecting data for which the least squares estimator for the ranking problem has maximal Fisher information. Our approach, based on experimental design, is to view data collection as a bi-level optimization problem where the inner problem is the ranking problem and the outer problem is to identify data which maximizes the informativeness of the ranking. Under certain assumptions, the data collection problem decouples, reducing to a problem of finding multigraphs with large algebraic connectivity. This reduction of the data collection problem to graph-theoretic questions is one of the primary contributions of this work. As an application, we study the Yahoo! Movie user rating dataset and demonstrate that the addition of a small number of well-chosen pairwise comparisons can significantly increase the Fisher informativeness of the ranking. As another application, we study the 2011-12 NCAA football schedule and propose schedules with the same number of games which are significantly more informative. Using spectral clustering methods to identify highly-connected communities within the division, we argue that the NCAA could improve its notoriously poor rankings by simply scheduling more out-of-conference games.", "source": "arxiv/ml"}
{"id": "arxiv:2071", "title": "Gaussian process regression as a predictive model for Quality-of-Service in Web service systems", "text": "In this paper, we present the Gaussian process regression as the predictive model for Quality-of-Service (QoS) attributes in Web service systems. The goal is to predict performance of the execution system expressed as QoS attributes given existing execution system, service repository, and inputs, e.g., streams of requests. In order to evaluate the performance of Gaussian process regression the simulation environment was developed. Two quality indexes were used, namely, Mean Absolute Error and Mean Squared Error. The results obtained within the experiment show that the Gaussian process performed the best with linear kernel and statistically significantly better comparing to Classification and Regression Trees (CART) method.", "source": "arxiv/ml"}
{"id": "arxiv:2072", "title": "Supervised Laplacian Eigenmaps with Applications in Clinical Diagnostics for Pediatric Cardiology", "text": "Electronic health records contain rich textual data which possess critical predictive information for machine-learning based diagnostic aids. However many traditional machine learning methods fail to simultaneously integrate both vector space data and text. We present a supervised method using Laplacian eigenmaps to augment existing machine-learning methods with low-dimensional representations of textual predictors which preserve the local similarities. The proposed implementation performs alternating optimization using gradient descent. For the evaluation we applied our method to over 2,000 patient records from a large single-center pediatric cardiology practice to predict if patients were diagnosed with cardiac disease. Our method was compared with latent semantic indexing, latent Dirichlet allocation, and local Fisher discriminant analysis. The results were assessed using AUC, MCC, specificity, and sensitivity. Results indicate supervised Laplacian eigenmaps was the highest performing method in our study, achieving 0.782 and 0.374 for AUC and MCC respectively. SLE showed an increase in 8.16% in AUC and 20.6% in MCC over the baseline which excluded textual data and a 2.69% and 5.35% increase in AUC and MCC respectively over unsupervised Laplacian eigenmaps. This method allows many existing machine learning predictors to effectively and efficiently utilize the potential of textual predictors.", "source": "arxiv/ml"}
{"id": "arxiv:2073", "title": "Predicate Generation for Learning-Based Quantifier-Free Loop Invariant Inference", "text": "We address the predicate generation problem in the context of loop invariant inference. Motivated by the interpolation-based abstraction refinement technique, we apply the interpolation theorem to synthesize predicates implicitly implied by program texts. Our technique is able to improve the effectiveness and efficiency of the learning-based loop invariant inference algorithm in [14]. We report experiment results of examples from Linux, SPEC2000, and Tar utility.", "source": "arxiv/ml"}
{"id": "arxiv:2074", "title": "Learning a peptide-protein binding affinity predictor with kernel ridge regression", "text": "We propose a specialized string kernel for small bio-molecules, peptides and pseudo-sequences of binding interfaces. The kernel incorporates physico-chemical properties of amino acids and elegantly generalize eight kernels, such as the Oligo, the Weighted Degree, the Blended Spectrum, and the Radial Basis Function. We provide a low complexity dynamic programming algorithm for the exact computation of the kernel and a linear time algorithm for it's approximation. Combined with kernel ridge regression and SupCK, a novel binding pocket kernel, the proposed kernel yields biologically relevant and good prediction accuracy on the PepX database. For the first time, a machine learning predictor is capable of accurately predicting the binding affinity of any peptide to any protein. The method was also applied to both single-target and pan-specific Major Histocompatibility Complex class II benchmark datasets and three Quantitative Structure Affinity Model benchmark datasets. On all benchmarks, our method significantly (p-value < 0.057) outperforms the current state-of-the-art methods at predicting peptide-protein binding affinities. The proposed approach is flexible and can be applied to predict any quantitative biological activity. The method should be of value to a large segment of the research community with the potential to accelerate peptide-based drug and vaccine development.", "source": "arxiv/ml"}
{"id": "arxiv:2075", "title": "Oracle inequalities for computationally adaptive model selection", "text": "We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selection approaches do not consider computational aspects of performing model selection, we argue that any practical model selection procedure must not only trade off estimation and approximation error, but also the computational effort required to compute empirical minimizers for different function classes. We provide a framework for analyzing such problems, and we give algorithms for model selection under a computational budget. These algorithms satisfy oracle inequalities that show that the risk of the selected model is not much worse than if we had devoted all of our omputational budget to the optimal function class.", "source": "arxiv/ml"}
{"id": "arxiv:2076", "title": "Fast Planar Correlation Clustering for Image Segmentation", "text": "We describe a new optimization scheme for finding high-quality correlation clusterings in planar graphs that uses weighted perfect matching as a subroutine. Our method provides lower-bounds on the energy of the optimal correlation clustering that are typically fast to compute and tight in practice. We demonstrate our algorithm on the problem of image segmentation where this approach outperforms existing global optimization techniques in minimizing the objective and is competitive with the state of the art in producing high-quality segmentations.", "source": "arxiv/ml"}
{"id": "arxiv:2077", "title": "Multidimensional Membership Mixture Models", "text": "We present the multidimensional membership mixture (M3) models where every dimension of the membership represents an independent mixture model and each data point is generated from the selected mixture components jointly. This is helpful when the data has a certain shared structure. For example, three unique means and three unique variances can effectively form a Gaussian mixture model with nine components, while requiring only six parameters to fully describe it. In this paper, we present three instantiations of M3 models (together with the learning and inference algorithms): infinite, finite, and hybrid, depending on whether the number of mixtures is fixed or not. They are built upon Dirichlet process mixture models, latent Dirichlet allocation, and a combination respectively. We then consider two applications: topic modeling and learning 3D object arrangements. Our experiments show that our M3 models achieve better performance using fewer topics than many classic topic models. We also observe that topics from the different dimensions of M3 models are meaningful and orthogonal to each other.", "source": "arxiv/ml"}
{"id": "arxiv:2078", "title": "Efficient Point-to-Subspace Query in $\\ell^1$ with Application to Robust Object Instance Recognition", "text": "Motivated by vision tasks such as robust face and object recognition, we consider the following general problem: given a collection of low-dimensional linear subspaces in a high-dimensional ambient (image) space, and a query point (image), efficiently determine the nearest subspace to the query in $\\ell^1$ distance. In contrast to the naive exhaustive search which entails large-scale linear programs, we show that the computational burden can be cut down significantly by a simple two-stage algorithm: (1) projecting the query and data-base subspaces into lower-dimensional space by random Cauchy matrix, and solving small-scale distance evaluations (linear programs) in the projection space to locate candidate nearest; (2) with few candidates upon independent repetition of (1), getting back to the high-dimensional space and performing exhaustive search. To preserve the identity of the nearest subspace with nontrivial probability, the projection dimension typically is low-order polynomial of the subspace dimension multiplied by logarithm of number of the subspaces (Theorem 2.1). The reduced dimensionality and hence complexity renders the proposed algorithm particularly relevant to vision application such as robust face and object instance recognition that we investigate empirically.", "source": "arxiv/ml"}
{"id": "arxiv:2079", "title": "Detection of Deviations in Mobile Applications Network Behavior", "text": "In this paper a novel system for detecting meaningful deviations in a mobile application's network behavior is proposed. The main goal of the proposed system is to protect mobile device users and cellular infrastructure companies from malicious applications. The new system is capable of: (1) identifying malicious attacks or masquerading applications installed on a mobile device, and (2) identifying republishing of popular applications injected with a malicious code. The detection is performed based on the application's network traffic patterns only. For each application two types of models are learned. The first model, local, represents the personal traffic pattern for each user using an application and is learned on the device. The second model, collaborative, represents traffic patterns of numerous users using an application and is learned on the system server. Machine-learning methods are used for learning and detection purposes. This paper focuses on methods utilized for local (i.e., on mobile device) learning and detection of deviations from the normal application's behavior. These methods were implemented and evaluated on Android devices. The evaluation experiments demonstrate that: (1) various applications have specific network traffic patterns and certain application categories can be distinguishable by their network patterns, (2) different levels of deviations from normal behavior can be detected accurately, and (3) local learning is feasible and has a low performance overhead on mobile devices.", "source": "arxiv/ml"}
{"id": "arxiv:2080", "title": "On the Consistency of AUC Pairwise Optimization", "text": "AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all approaches work with surrogate loss functions. Thus, the consistency of AUC is crucial; however, it has been almost untouched before. In this paper, we provide a sufficient condition for the asymptotic consistency of learning approaches based on surrogate loss functions. Based on this result, we prove that exponential loss and logistic loss are consistent with AUC, but hinge loss is inconsistent. Then, we derive the $q$-norm hinge loss and general hinge loss that are consistent with AUC. We also derive the consistent bounds for exponential loss and logistic loss, and obtain the consistent bounds for many surrogate loss functions under the non-noise setting. Further, we disclose an equivalence between the exponential surrogate loss of AUC and exponential surrogate loss of accuracy, and one straightforward consequence of such finding is that AdaBoost and RankBoost are equivalent.", "source": "arxiv/ml"}
{"id": "arxiv:2081", "title": "Wisdom of the Crowd: Incorporating Social Influence in Recommendation Models", "text": "Recommendation systems have received considerable attention recently. However, most research has been focused on improving the performance of collaborative filtering (CF) techniques. Social networks, indispensably, provide us extra information on people's preferences, and should be considered and deployed to improve the quality of recommendations. In this paper, we propose two recommendation models, for individuals and for groups respectively, based on social contagion and social influence network theory. In the recommendation model for individuals, we improve the result of collaborative filtering prediction with social contagion outcome, which simulates the result of information cascade in the decision-making process. In the recommendation model for groups, we apply social influence network theory to take interpersonal influence into account to form a settled pattern of disagreement, and then aggregate opinions of group members. By introducing the concept of susceptibility and interpersonal influence, the settled rating results are flexible, and inclined to members whose ratings are \"essential\".", "source": "arxiv/ml"}
{"id": "arxiv:2082", "title": "A Random Walk Based Model Incorporating Social Information for Recommendations", "text": "Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system. In this paper, we propose a hybrid collaborative filtering model based on a Makovian random walk to address the data sparsity and cold start problems in recommendation systems. More precisely, we construct a directed graph whose nodes consist of items and users, together with item content, user profile and social network information. We incorporate user's ratings into edge settings in the graph model. The model provides personalized recommendations and predictions to individuals and groups. The proposed algorithms are evaluated on MovieLens and Epinions datasets. Experimental results show that the proposed methods perform well compared with other graph-based methods, especially in the cold start case.", "source": "arxiv/ml"}
{"id": "arxiv:2083", "title": "Cross-conformal predictors", "text": "This note introduces the method of cross-conformal prediction, which is a hybrid of the methods of inductive conformal prediction and cross-validation, and studies its validity and predictive efficiency empirically.", "source": "arxiv/ml"}
{"id": "arxiv:2084", "title": "Learning Theory Approach to Minimum Error Entropy Criterion", "text": "We consider the minimum error entropy (MEE) criterion and an empirical risk minimization learning algorithm in a regression setting. A learning theory approach is presented for this MEE algorithm and explicit error bounds are provided in terms of the approximation ability and capacity of the involved hypothesis space when the MEE scaling parameter is large. Novel asymptotic analysis is conducted for the generalization error associated with Renyi's entropy and a Parzen window function, to overcome technical difficulties arisen from the essential differences between the classical least squares problems and the MEE setting. A semi-norm and the involved symmetrized least squares error are introduced, which is related to some ranking algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2085", "title": "Statistical Results on Filtering and Epi-convergence for Learning-Based Model Predictive Control", "text": "Learning-based model predictive control (LBMPC) is a technique that provides deterministic guarantees on robustness, while statistical identification tools are used to identify richer models of the system in order to improve performance. This technical note provides proofs that elucidate the reasons for our choice of measurement model, as well as giving proofs concerning the stochastic convergence of LBMPC. The first part of this note discusses simultaneous state estimation and statistical identification (or learning) of unmodeled dynamics, for dynamical systems that can be described by ordinary differential equations (ODE's). The second part provides proofs concerning the epi-convergence of different statistical estimators that can be used with the learning-based model predictive control (LBMPC) technique. In particular, we prove results on the statistical properties of a nonparametric estimator that we have designed to have the correct deterministic and stochastic properties for numerical implementation when used in conjunction with LBMPC.", "source": "arxiv/ml"}
{"id": "arxiv:2086", "title": "Recklessly Approximate Sparse Coding", "text": "It has recently been observed that certain extremely simple feature encoding techniques are able to achieve state of the art performance on several standard image classification benchmarks including deep belief networks, convolutional nets, factored RBMs, mcRBMs, convolutional RBMs, sparse autoencoders and several others. Moreover, these \"triangle\" or \"soft threshold\" encodings are ex- tremely efficient to compute. Several intuitive arguments have been put forward to explain this remarkable performance, yet no mathematical justification has been offered. The main result of this report is to show that these features are realized as an approximate solution to the a non-negative sparse coding problem. Using this connection we describe several variants of the soft threshold features and demonstrate their effectiveness on two image classification benchmark tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2087", "title": "APRIL: Active Preference-learning based Reinforcement Learning", "text": "This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent demonstrations. Earlier work has presented an iterative preference-based RL framework: expert preferences are exploited to learn an approximate policy return, thus enabling the agent to achieve direct policy search. Iteratively, the agent selects a new candidate policy and demonstrates it; the expert ranks the new demonstration comparatively to the previous best one; the expert's ranking feedback enables the agent to refine the approximate policy return, and the process is iterated. In this paper, preference-based reinforcement learning is combined with active ranking in order to decrease the number of ranking queries to the expert needed to yield a satisfactory policy. Experiments on the mountain car and the cancer treatment testbeds witness that a couple of dozen rankings enable to learn a competent policy.", "source": "arxiv/ml"}
{"id": "arxiv:2088", "title": "Sequential Estimation Methods from Inclusion Principle", "text": "In this paper, we propose new sequential estimation methods based on inclusion principle. The main idea is to reformulate the estimation problems as constructing sequential random intervals and use confidence sequences to control the associated coverage probabilities. In contrast to existing asymptotic sequential methods, our estimation procedures rigorously guarantee the pre-specified levels of confidence.", "source": "arxiv/ml"}
{"id": "arxiv:2089", "title": "Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization", "text": "In this paper, we study the nonnegative matrix factorization problem under the separability assumption (that is, there exists a cone spanned by a small subset of the columns of the input nonnegative data matrix containing all columns), which is equivalent to the hyperspectral unmixing problem under the linear mixing model and the pure-pixel assumption. We present a family of fast recursive algorithms, and prove they are robust under any small perturbations of the input data matrix. This family generalizes several existing hyperspectral unmixing algorithms and hence provides for the first time a theoretical justification of their better practical performance.", "source": "arxiv/ml"}
{"id": "arxiv:2090", "title": "One Permutation Hashing for Efficient Search and Learning", "text": "Recently, the method of b-bit minwise hashing has been applied to large-scale linear learning and sublinear time near-neighbor search. The major drawback of minwise hashing is the expensive preprocessing cost, as the method requires applying (e.g.,) k=200 to 500 permutations on the data. The testing time can also be expensive if a new data point (e.g., a new document or image) has not been processed, which might be a significant issue in user-facing applications. We develop a very simple solution based on one permutation hashing. Conceptually, given a massive binary data matrix, we permute the columns only once and divide the permuted columns evenly into k bins; and we simply store, for each data vector, the smallest nonzero location in each bin. The interesting probability analysis (which is validated by experiments) reveals that our one permutation scheme should perform very similarly to the original (k-permutation) minwise hashing. In fact, the one permutation scheme can be even slightly more accurate, due to the \"sample-without-replacement\" effect. Our experiments with training linear SVM and logistic regression on the webspam dataset demonstrate that this one permutation hashing scheme can achieve the same (or even slightly better) accuracies compared to the original k-permutation scheme. To test the robustness of our method, we also experiment with the small news20 dataset which is very sparse and has merely on average 500 nonzeros in each data vector. Interestingly, our one permutation scheme noticeably outperforms the k-permutation scheme when k is not too small on the news20 dataset. In summary, our method can achieve at least the same accuracy as the original k-permutation scheme, at merely 1/k of the original preprocessing cost.", "source": "arxiv/ml"}
{"id": "arxiv:2091", "title": "Data Selection for Semi-Supervised Learning", "text": "The real challenge in pattern recognition task and machine learning process is to train a discriminator using labeled data and use it to distinguish between future data as accurate as possible. However, most of the problems in the real world have numerous data, which labeling them is a cumbersome or even an impossible matter. Semi-supervised learning is one approach to overcome these types of problems. It uses only a small set of labeled with the company of huge remain and unlabeled data to train the discriminator. In semi-supervised learning, it is very essential that which data is labeled and depend on position of data it effectiveness changes. In this paper, we proposed an evolutionary approach called Artificial Immune System (AIS) to determine which data is better to be labeled to get the high quality data. The experimental results represent the effectiveness of this algorithm in finding these data points.", "source": "arxiv/ml"}
{"id": "arxiv:2092", "title": "Guess Who Rated This Movie: Identifying Users Through Subspace Clustering", "text": "It is often the case that, within an online recommender system, multiple users share a common account. Can such shared accounts be identified solely on the basis of the user- provided ratings? Once a shared account is identified, can the different users sharing it be identified as well? Whenever such user identification is feasible, it opens the way to possible improvements in personalized recommendations, but also raises privacy concerns. We develop a model for composite accounts based on unions of linear subspaces, and use subspace clustering for carrying out the identification task. We show that a significant fraction of such accounts is identifiable in a reliable manner, and illustrate potential uses for personalized recommendation.", "source": "arxiv/ml"}
{"id": "arxiv:2093", "title": "Self-Organizing Time Map: An Abstraction of Temporal Multivariate Patterns", "text": "This paper adopts and adapts Kohonen's standard Self-Organizing Map (SOM) for exploratory temporal structure analysis. The Self-Organizing Time Map (SOTM) implements SOM-type learning to one-dimensional arrays for individual time units, preserves the orientation with short-term memory and arranges the arrays in an ascending order of time. The two-dimensional representation of the SOTM attempts thus twofold topology preservation, where the horizontal direction preserves time topology and the vertical direction data topology. This enables discovering the occurrence and exploring the properties of temporal structural changes in data. For representing qualities and properties of SOTMs, we adapt measures and visualizations from the standard SOM paradigm, as well as introduce a measure of temporal structural changes. The functioning of the SOTM, and its visualizations and quality and property measures, are illustrated on artificial toy data. The usefulness of the SOTM in a real-world setting is shown on poverty, welfare and development indicators.", "source": "arxiv/ml"}
{"id": "arxiv:2094", "title": "Metric Learning across Heterogeneous Domains by Respectively Aligning Both Priors and Posteriors", "text": "In this paper, we attempts to learn a single metric across two heterogeneous domains where source domain is fully labeled and has many samples while target domain has only a few labeled samples but abundant unlabeled samples. To the best of our knowledge, this task is seldom touched. The proposed learning model has a simple underlying motivation: all the samples in both the source and the target domains are mapped into a common space, where both their priors P(sample)s and their posteriors P(label|sample)s are forced to be respectively aligned as much as possible. We show that the two mappings, from both the source domain and the target domain to the common space, can be reparameterized into a single positive semi-definite(PSD) matrix. Then we develop an efficient Bregman Projection algorithm to optimize the PDS matrix over which a LogDet function is used to regularize. Furthermore, we also show that this model can be easily kernelized and verify its effectiveness in crosslanguage retrieval task and cross-domain object recognition task.", "source": "arxiv/ml"}
{"id": "arxiv:2095", "title": "Margin Distribution Controlled Boosting", "text": "Schapire's margin theory provides a theoretical explanation to the success of boosting-type methods and manifests that a good margin distribution (MD) of training samples is essential for generalization. However the statement that a MD is good is vague, consequently, many recently developed algorithms try to generate a MD in their goodness senses for boosting generalization. Unlike their indirect control over MD, in this paper, we propose an alternative boosting algorithm termed Margin distribution Controlled Boosting (MCBoost) which directly controls the MD by introducing and optimizing a key adjustable margin parameter. MCBoost's optimization implementation adopts the column generation technique to ensure fast convergence and small number of weak classifiers involved in the final MCBooster. We empirically demonstrate: 1) AdaBoost is actually also a MD controlled algorithm and its iteration number acts as a parameter controlling the distribution and 2) the generalization performance of MCBoost evaluated on UCI benchmark datasets is validated better than those of AdaBoost, L2Boost, LPBoost, AdaBoost-CG and MDBoost.", "source": "arxiv/ml"}
{"id": "arxiv:2096", "title": "Scaling Multiple-Source Entity Resolution using Statistically Efficient Transfer Learning", "text": "We consider a serious, previously-unexplored challenge facing almost all approaches to scaling up entity resolution (ER) to multiple data sources: the prohibitive cost of labeling training data for supervised learning of similarity scores for each pair of sources. While there exists a rich literature describing almost all aspects of pairwise ER, this new challenge is arising now due to the unprecedented ability to acquire and store data from online sources, features driven by ER such as enriched search verticals, and the uniqueness of noisy and missing data characteristics for each source. We show on real-world and synthetic data that for state-of-the-art techniques, the reality of heterogeneous sources means that the number of labeled training data must scale quadratically in the number of sources, just to maintain constant precision/recall. We address this challenge with a brand new transfer learning algorithm which requires far less training data (or equivalently, achieves superior accuracy with the same data) and is trained using fast convex optimization. The intuition behind our approach is to adaptively share structure learned about one scoring problem with all other scoring problems sharing a data source in common. We demonstrate that our theoretically motivated approach incurs no runtime cost while it can maintain constant precision/recall with the cost of labeling increasing only linearly with the number of sources.", "source": "arxiv/ml"}
{"id": "arxiv:2097", "title": "Sharp analysis of low-rank kernel matrix approximations", "text": "We consider supervised learning problems within the positive-definite kernel framework, such as kernel ridge regression, kernel logistic regression or the support vector machine. With kernels leading to infinite-dimensional feature spaces, a common practical limiting difficulty is the necessity of computing the kernel matrix, which most frequently leads to algorithms with running time at least quadratic in the number of observations n, i.e., O(n^2). Low-rank approximations of the kernel matrix are often considered as they allow the reduction of running time complexities to O(p^2 n), where p is the rank of the approximation. The practicality of such methods thus depends on the required rank p. In this paper, we show that in the context of kernel ridge regression, for approximations based on a random subset of columns of the original kernel matrix, the rank p may be chosen to be linear in the degrees of freedom associated with the problem, a quantity which is classically used in the statistical analysis of such methods, and is often seen as the implicit number of parameters of non-parametric estimators. This result enables simple algorithms that have sub-quadratic running time complexity, but provably exhibit the same predictive performance than existing algorithms, for any given problem instance, and not only for worst-case situations.", "source": "arxiv/ml"}
{"id": "arxiv:2098", "title": "Inverse Reinforcement Learning with Gaussian Process", "text": "We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework with the objective of maximum a posterior estimation. To deal with problems in large or even infinite state space, we propose a Gaussian process model and use preference graphs to represent observations of decision trajectories. Our method is distinguished from other approaches to IRL in that it makes no assumptions about the form of the reward function and yet it retains the promise of computationally manageable implementations for potential real-world applications. In comparison with an establish algorithm on small-scale numerical problems, our method demonstrated better accuracy in apprenticeship learning and a more robust dependence on the number of observations.", "source": "arxiv/ml"}
{"id": "arxiv:2099", "title": "Brain tumor MRI image classification with feature selection and extraction using linear discriminant analysis", "text": "Feature extraction is a method of capturing visual content of an image. The feature extraction is the process to represent raw image in its reduced form to facilitate decision making such as pattern classification. We have tried to address the problem of classification MRI brain images by creating a robust and more accurate classifier which can act as an expert assistant to medical practitioners. The objective of this paper is to present a novel method of feature selection and extraction. This approach combines the Intensity, Texture, shape based features and classifies the tumor as white matter, Gray matter, CSF, abnormal and normal area. The experiment is performed on 140 tumor contained brain MR images from the Internet Brain Segmentation Repository. The proposed technique has been carried out over a larger database as compare to any previous work and is more robust and effective. PCA and Linear Discriminant Analysis (LDA) were applied on the training sets. The Support Vector Machine (SVM) classifier served as a comparison of nonlinear techniques Vs linear ones. PCA and LDA methods are used to reduce the number of features used. The feature selection using the proposed technique is more beneficial as it analyses the data according to grouping class variable and gives reduced feature set with high classification accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2100", "title": "Learning pseudo-Boolean k-DNF and Submodular Functions", "text": "We prove that any submodular function f: {0,1}^n -> {0,1,...,k} can be represented as a pseudo-Boolean 2k-DNF formula. Pseudo-Boolean DNFs are a natural generalization of DNF representation for functions with integer range. Each term in such a formula has an associated integral constant. We show that an analog of Hastad's switching lemma holds for pseudo-Boolean k-DNFs if all constants associated with the terms of the formula are bounded. This allows us to generalize Mansour's PAC-learning algorithm for k-DNFs to pseudo-Boolean k-DNFs, and hence gives a PAC-learning algorithm with membership queries under the uniform distribution for submodular functions of the form f:{0,1}^n -> {0,1,...,k}. Our algorithm runs in time polynomial in n, k^{O(k \\log k / \\epsilon)}, 1/\\epsilon and log(1/\\delta) and works even in the agnostic setting. The line of previous work on learning submodular functions [Balcan, Harvey (STOC '11), Gupta, Hardt, Roth, Ullman (STOC '11), Cheraghchi, Klivans, Kothari, Lee (SODA '12)] implies only n^{O(k)} query complexity for learning submodular functions in this setting, for fixed epsilon and delta. Our learning algorithm implies a property tester for submodularity of functions f:{0,1}^n -> {0, ..., k} with query complexity polynomial in n for k=O((\\log n/ \\loglog n)^{1/2}) and constant proximity parameter \\epsilon.", "source": "arxiv/ml"}
{"id": "arxiv:2101", "title": "How to sample if you must: on optimal functional sampling", "text": "We examine a fundamental problem that models various active sampling setups, such as network tomography. We analyze sampling of a multivariate normal distribution with an unknown expectation that needs to be estimated: in our setup it is possible to sample the distribution from a given set of linear functionals, and the difficulty addressed is how to optimally select the combinations to achieve low estimation error. Although this problem is in the heart of the field of optimal design, no efficient solutions for the case with many functionals exist. We present some bounds and an efficient sub-optimal solution for this problem for more structured sets such as binary functionals that are induced by graph walks.", "source": "arxiv/ml"}
{"id": "arxiv:2102", "title": "Path Integral Control by Reproducing Kernel Hilbert Space Embedding", "text": "We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This formulation admits a decomposition of the problem into an invariant and task dependent component. Consequently, we make much more efficient use of the sample data compared to previous sample based approaches in this domain, e.g., by allowing sample re-use across tasks. Numerical examples on test problems, which illustrate the sample efficiency, are provided.", "source": "arxiv/ml"}
{"id": "arxiv:2103", "title": "Nonparametric sparsity and regularization", "text": "In this work we are interested in the problems of supervised learning and variable selection when the input-output dependence is described by a nonlinear function depending on a few variables. Our goal is to consider a sparse nonparametric model, hence avoiding linear or additive models. The key idea is to measure the importance of each variable in the model by making use of partial derivatives. Based on this intuition we propose a new notion of nonparametric sparsity and a corresponding least squares regularization scheme. Using concepts and results from the theory of reproducing kernel Hilbert spaces and proximal methods, we show that the proposed learning algorithm corresponds to a minimization problem which can be provably solved by an iterative procedure. The consistency properties of the obtained estimator are studied both in terms of prediction and selection performance. An extensive empirical analysis shows that the proposed method performs favorably with respect to the state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:2104", "title": "Analysis of a Statistical Hypothesis Based Learning Mechanism for Faster crawling", "text": "The growth of world-wide-web (WWW) spreads its wings from an intangible quantities of web-pages to a gigantic hub of web information which gradually increases the complexity of crawling process in a search engine. A search engine handles a lot of queries from various parts of this world, and the answers of it solely depend on the knowledge that it gathers by means of crawling. The information sharing becomes a most common habit of the society, and it is done by means of publishing structured, semi-structured and unstructured resources on the web. This social practice leads to an exponential growth of web-resource, and hence it became essential to crawl for continuous updating of web-knowledge and modification of several existing resources in any situation. In this paper one statistical hypothesis based learning mechanism is incorporated for learning the behavior of crawling speed in different environment of network, and for intelligently control of the speed of crawler. The scaling technique is used to compare the performance proposed method with the standard crawler. The high speed performance is observed after scaling, and the retrieval of relevant web-resource in such a high speed is analyzed.", "source": "arxiv/ml"}
{"id": "arxiv:2105", "title": "Detecting Events and Patterns in Large-Scale User Generated Textual Streams with Statistical Learning Methods", "text": "A vast amount of textual web streams is influenced by events or phenomena emerging in the real world. The social web forms an excellent modern paradigm, where unstructured user generated content is published on a regular basis and in most occasions is freely distributed. The present Ph.D. Thesis deals with the problem of inferring information - or patterns in general - about events emerging in real life based on the contents of this textual stream. We show that it is possible to extract valuable information about social phenomena, such as an epidemic or even rainfall rates, by automatic analysis of the content published in Social Media, and in particular Twitter, using Statistical Machine Learning methods. An important intermediate task regards the formation and identification of features which characterise a target event; we select and use those textual features in several linear, non-linear and hybrid inference approaches achieving a significantly good performance in terms of the applied loss function. By examining further this rich data set, we also propose methods for extracting various types of mood signals revealing how affective norms - at least within the social web's population - evolve during the day and how significant events emerging in the real world are influencing them. Lastly, we present some preliminary findings showing several spatiotemporal characteristics of this textual information as well as the potential of using it to tackle tasks such as the prediction of voting intentions.", "source": "arxiv/ml"}
{"id": "arxiv:2106", "title": "Using Program Synthesis for Social Recommendations", "text": "This paper presents a new approach to select events of interest to a user in a social media setting where events are generated by the activities of the user's friends through their mobile devices. We argue that given the unique requirements of the social media setting, the problem is best viewed as an inductive learning problem, where the goal is to first generalize from the users' expressed \"likes\" and \"dislikes\" of specific events, then to produce a program that can be manipulated by the system and distributed to the collection devices to collect only data of interest. The key contribution of this paper is a new algorithm that combines existing machine learning techniques with new program synthesis technology to learn users' preferences. We show that when compared with the more standard approaches, our new algorithm provides up to order-of-magnitude reductions in model training time, and significantly higher prediction accuracies for our target application. The approach also improves on standard machine learning techniques in that it produces clear programs that can be manipulated to optimize data collection and filtering.", "source": "arxiv/ml"}
{"id": "arxiv:2107", "title": "Asymptotic Generalization Bound of Fisher's Linear Discriminant Analysis", "text": "Fisher's linear discriminant analysis (FLDA) is an important dimension reduction method in statistical pattern recognition. It has been shown that FLDA is asymptotically Bayes optimal under the homoscedastic Gaussian assumption. However, this classical result has the following two major limitations: 1) it holds only for a fixed dimensionality $D$, and thus does not apply when $D$ and the training sample size $N$ are proportionally large; 2) it does not provide a quantitative description on how the generalization ability of FLDA is affected by $D$ and $N$. In this paper, we present an asymptotic generalization analysis of FLDA based on random matrix theory, in a setting where both $D$ and $N$ increase and $D/N\\longrightarrow\\gamma\\in[0,1)$. The obtained lower bound of the generalization discrimination power overcomes both limitations of the classical result, i.e., it is applicable when $D$ and $N$ are proportionally large and provides a quantitative description of the generalization ability of FLDA in terms of the ratio $\\gamma=D/N$ and the population discrimination power. Besides, the discrimination power bound also leads to an upper bound on the generalization error of binary-classification with FLDA.", "source": "arxiv/ml"}
{"id": "arxiv:2108", "title": "Metric distances derived from cosine similarity and Pearson and Spearman correlations", "text": "We investigate two classes of transformations of cosine similarity and Pearson and Spearman correlations into metric distances, utilising the simple tool of metric-preserving functions. The first class puts anti-correlated objects maximally far apart. Previously known transforms fall within this class. The second class collates correlated and anti-correlated objects. An example of such a transformation that yields a metric distance is the sine function when applied to centered data.", "source": "arxiv/ml"}
{"id": "arxiv:2109", "title": "Structured Prediction Cascades", "text": "Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference in the exponentially-sized output spaces such models require. We formulate and develop the Structured Prediction Cascade architecture: a sequence of increasingly complex models that progressively filter the space of possible outputs. The key principle of our approach is that each model in the cascade is optimized to accurately filter and refine the structured output state space of the next model, speeding up both learning and inference in the next layer of the cascade. We learn cascades by optimizing a novel convex loss function that controls the trade-off between the filtering efficiency and the accuracy of the cascade, and provide generalization bounds for both accuracy and efficiency. We also extend our approach to intractable models using tree-decomposition ensembles, and provide algorithms and theory for this setting. We evaluate our approach on several large-scale problems, achieving state-of-the-art performance in handwriting recognition and human pose recognition. We find that structured prediction cascades allow tremendous speedups and the use of previously intractable features and models in both settings.", "source": "arxiv/ml"}
{"id": "arxiv:2110", "title": "Distance Metric Learning for Kernel Machines", "text": "Recent work in metric learning has significantly improved the state-of-the-art in k-nearest neighbor classification. Support vector machines (SVM), particularly with RBF kernels, are amongst the most popular classification algorithms that uses distance metrics to compare examples. This paper provides an empirical analysis of the efficacy of three of the most popular Mahalanobis metric learning algorithms as pre-processing for SVM training. We show that none of these algorithms generate metrics that lead to particularly satisfying improvements for SVM-RBF classification. As a remedy we introduce support vector metric learning (SVML), a novel algorithm that seamlessly combines the learning of a Mahalanobis metric with the training of the RBF-SVM parameters. We demonstrate the capabilities of SVML on nine benchmark data sets of varying sizes and difficulties. In our study, SVML outperforms all alternative state-of-the-art metric learning algorithms in terms of accuracy and establishes itself as a serious alternative to the standard Euclidean metric with model selection by cross validation.", "source": "arxiv/ml"}
{"id": "arxiv:2111", "title": "Efficient Active Learning of Halfspaces: an Aggressive Approach", "text": "We study pool-based active learning of half-spaces. We revisit the aggressive approach for active learning in the realizable case, and show that it can be made efficient and practical, while also having theoretical guarantees under reasonable assumptions. We further show, both theoretically and experimentally, that it can be preferable to mellow approaches. Our efficient aggressive active learner of half-spaces has formal approximation guarantees that hold when the pool is separable with a margin. While our analysis is focused on the realizable setting, we show that a simple heuristic allows using the same algorithm successfully for pools with low error as well. We further compare the aggressive approach to the mellow approach, and prove that there are cases in which the aggressive approach results in significantly better label complexity compared to the mellow approach. We demonstrate experimentally that substantial improvements in label complexity can be achieved using the aggressive approach, for both realizable and low-error settings.", "source": "arxiv/ml"}
{"id": "arxiv:2112", "title": "An improvement direction for filter selection techniques using information theory measures and quadratic optimization", "text": "Filter selection techniques are known for their simplicity and efficiency. However this kind of methods doesn't take into consideration the features inter-redundancy. Consequently the un-removed redundant features remain in the final classification model, giving lower generalization performance. In this paper we propose to use a mathematical optimization method that reduces inter-features redundancy and maximize relevance between each feature and the target variable.", "source": "arxiv/ml"}
{"id": "arxiv:2113", "title": "Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms", "text": "Many different machine learning algorithms exist; taking into account each algorithm's hyperparameters, there is a staggeringly large number of possible alternatives overall. We consider the problem of simultaneously selecting a learning algorithm and setting its hyperparameters, going beyond previous work that addresses these issues in isolation. We show that this problem can be addressed by a fully automated approach, leveraging recent innovations in Bayesian optimization. Specifically, we consider a wide range of feature selection techniques (combining 3 search and 8 evaluator methods) and all classification approaches implemented in WEKA, spanning 2 ensemble methods, 10 meta-methods, 27 base classifiers, and hyperparameter settings for each classifier. On each of 21 popular datasets from the UCI repository, the KDD Cup 09, variants of the MNIST dataset and CIFAR-10, we show classification performance often much better than using standard selection/hyperparameter optimization methods. We hope that our approach will help non-expert users to more effectively identify machine learning algorithms and hyperparameter settings appropriate to their applications, and hence to achieve improved performance.", "source": "arxiv/ml"}
{"id": "arxiv:2114", "title": "Online Learning with Predictable Sequences", "text": "We present methods for online linear optimization that take advantage of benign (as opposed to worst-case) sequences. Specifically if the sequence encountered by the learner is described well by a known \"predictable process\", the algorithms presented enjoy tighter bounds as compared to the typical worst case bounds. Additionally, the methods achieve the usual worst-case regret bounds if the sequence is not benign. Our approach can be seen as a way of adding prior knowledge about the sequence within the paradigm of online learning. The setting is shown to encompass partial and side information. Variance and path-length bounds can be seen as particular examples of online learning with simple predictable sequences. We further extend our methods and results to include competing with a set of possible predictable processes (models), that is \"learning\" the predictable process itself concurrently with using it to obtain better regret guarantees. We show that such model selection is possible under various assumptions on the available feedback. Our results suggest a promising direction of further research with potential applications to stock market and time series prediction.", "source": "arxiv/ml"}
{"id": "arxiv:2115", "title": "Multiple graph regularized protein domain ranking", "text": "Background Protein domain ranking is a fundamental task in structural biology. Most protein domain ranking methods rely on the pairwise comparison of protein domains while neglecting the global manifold structure of the protein domain database. Recently, graph regularized ranking that exploits the global structure of the graph defined by the pairwise similarities has been proposed. However, the existing graph regularized ranking methods are very sensitive to the choice of the graph model and parameters, and this remains a difficult problem for most of the protein domain ranking methods. Results To tackle this problem, we have developed the Multiple Graph regularized Ranking algorithm, MultiG- Rank. Instead of using a single graph to regularize the ranking scores, MultiG-Rank approximates the intrinsic manifold of protein domain distribution by combining multiple initial graphs for the regularization. Graph weights are learned with ranking scores jointly and automatically, by alternately minimizing an ob- jective function in an iterative algorithm. Experimental results on a subset of the ASTRAL SCOP protein domain database demonstrate that MultiG-Rank achieves a better ranking performance than single graph regularized ranking methods and pairwise similarity based ranking methods. Conclusion The problem of graph model and parameter selection in graph regularized protein domain ranking can be solved effectively by combining multiple graphs. This aspect of generalization introduces a new frontier in applying multiple graphs to solving protein domain ranking applications.", "source": "arxiv/ml"}
{"id": "arxiv:2116", "title": "Discriminative Sparse Coding on Multi-Manifold for Data Representation and Classification", "text": "Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics, etc. However, the conventional sparse coding algorithms and its manifold regularized variants (graph sparse coding and Laplacian sparse coding), learn the codebook and codes in a unsupervised manner and neglect the class information available in the training set. To address this problem, in this paper we propose a novel discriminative sparse coding method based on multi-manifold, by learning discriminative class-conditional codebooks and sparse codes from both data feature space and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditional codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data point-manifold matching error based strategy to classify the unlabeled data point. Experimental results on somatic mutations identification and breast tumors classification in ultrasonic images tasks demonstrate the efficacy of the proposed data representation-classification approach.", "source": "arxiv/ml"}
{"id": "arxiv:2117", "title": "Adaptive Graph via Multiple Kernel Learning for Nonnegative Matrix Factorization", "text": "Nonnegative Matrix Factorization (NMF) has been continuously evolving in several areas like pattern recognition and information retrieval methods. It factorizes a matrix into a product of 2 low-rank non-negative matrices that will define parts-based, and linear representation of nonnegative data. Recently, Graph regularized NMF (GrNMF) is proposed to find a compact representation,which uncovers the hidden semantics and simultaneously respects the intrinsic geometric structure. In GNMF, an affinity graph is constructed from the original data space to encode the geometrical information. In this paper, we propose a novel idea which engages a Multiple Kernel Learning approach into refining the graph structure that reflects the factorization of the matrix and the new data space. The GrNMF is improved by utilizing the graph refined by the kernel learning, and then a novel kernel learning method is introduced under the GrNMF framework. Our approach shows encouraging results of the proposed algorithm in comparison to the state-of-the-art clustering algorithms like NMF, GrNMF, SVD etc.", "source": "arxiv/ml"}
{"id": "arxiv:2118", "title": "Performance Tuning Of J48 Algorithm For Prediction Of Soil Fertility", "text": "Data mining involves the systematic analysis of large data sets, and data mining in agricultural soil datasets is exciting and modern research area. The productive capacity of a soil depends on soil fertility. Achieving and maintaining appropriate levels of soil fertility, is of utmost importance if agricultural land is to remain capable of nourishing crop production. In this research, Steps for building a predictive model of soil fertility have been explained. This paper aims at predicting soil fertility class using decision tree algorithms in data mining . Further, it focuses on performance tuning of J48 decision tree algorithm with the help of meta-techniques such as attribute selection and boosting.", "source": "arxiv/ml"}
{"id": "arxiv:2119", "title": "Semi-supervised Clustering Ensemble by Voting", "text": "Clustering ensemble is one of the most recent advances in unsupervised learning. It aims to combine the clustering results obtained using different algorithms or from different runs of the same clustering algorithm for the same data set, this is accomplished using on a consensus function, the efficiency and accuracy of this method has been proven in many works in literature. In the first part of this paper we make a comparison among current approaches to clustering ensemble in literature. All of these approaches consist of two main steps: the ensemble generation and consensus function. In the second part of the paper, we suggest engaging supervision in the clustering ensemble procedure to get more enhancements on the clustering results. Supervision can be applied in two places: either by using semi-supervised algorithms in the clustering ensemble generation step or in the form of a feedback used by the consensus function stage. Also, we introduce a flexible two parameter weighting mechanism, the first parameter describes the compatibility between the datasets under study and the semi-supervised clustering algorithms used to generate the base partitions, the second parameter is used to provide the user feedback on the these partitions. The two parameters are engaged in a \"relabeling and voting\" based consensus function to produce the final clustering.", "source": "arxiv/ml"}
{"id": "arxiv:2120", "title": "Generating ordered list of Recommended Items: a Hybrid Recommender System of Microblog", "text": "Precise recommendation of followers helps in improving the user experience and maintaining the prosperity of twitter and microblog platforms. In this paper, we design a hybrid recommender system of microblog as a solution of KDD Cup 2012, track 1 task, which requires predicting users a user might follow in Tencent Microblog. We describe the background of the problem and present the algorithm consisting of keyword analysis, user taxonomy, (potential)interests extraction and item recommendation. Experimental result shows the high performance of our algorithm. Some possible improvements are discussed, which leads to further study.", "source": "arxiv/ml"}
{"id": "arxiv:2121", "title": "A Learning Theoretic Approach to Energy Harvesting Communication System Optimization", "text": "A point-to-point wireless communication system in which the transmitter is equipped with an energy harvesting device and a rechargeable battery, is studied. Both the energy and the data arrivals at the transmitter are modeled as Markov processes. Delay-limited communication is considered assuming that the underlying channel is block fading with memory, and the instantaneous channel state information is available at both the transmitter and the receiver. The expected total transmitted data during the transmitter's activation time is maximized under three different sets of assumptions regarding the information available at the transmitter about the underlying stochastic processes. A learning theoretic approach is introduced, which does not assume any a priori information on the Markov processes governing the communication system. In addition, online and offline optimization problems are studied for the same setting. Full statistical knowledge and causal information on the realizations of the underlying stochastic processes are assumed in the online optimization problem, while the offline optimization problem assumes non-causal knowledge of the realizations in advance. Comparing the optimal solutions in all three frameworks, the performance loss due to the lack of the transmitter's information regarding the behaviors of the underlying Markov processes is quantified.", "source": "arxiv/ml"}
{"id": "arxiv:2122", "title": "Optimized Look-Ahead Tree Policies: A Bridge Between Look-Ahead Tree Policies and Direct Policy Search", "text": "Direct policy search (DPS) and look-ahead tree (LT) policies are two widely used classes of techniques to produce high performance policies for sequential decision-making problems. To make DPS approaches work well, one crucial issue is to select an appropriate space of parameterized policies with respect to the targeted problem. A fundamental issue in LT approaches is that, to take good decisions, such policies must develop very large look-ahead trees which may require excessive online computational resources. In this paper, we propose a new hybrid policy learning scheme that lies at the intersection of DPS and LT, in which the policy is an algorithm that develops a small look-ahead tree in a directed way, guided by a node scoring function that is learned through DPS. The LT-based representation is shown to be a versatile way of representing policies in a DPS scheme, while at the same time, DPS enables to significantly reduce the size of the look-ahead trees that are required to take high-quality decisions. We experimentally compare our method with two other state-of-the-art DPS techniques and four common LT policies on four benchmark domains and show that it combines the advantages of the two techniques from which it originates. In particular, we show that our method: (1) produces overall better performing policies than both pure DPS and pure LT policies, (2) requires a substantially smaller number of policy evaluations than other DPS techniques, (3) is easy to tune and (4) results in policies that are quite robust with respect to perturbations of the initial conditions.", "source": "arxiv/ml"}
{"id": "arxiv:2123", "title": "Identification of Probabilities of Languages", "text": "We consider the problem of inferring the probability distribution associated with a language, given data consisting of an infinite sequence of elements of the languge. We do this under two assumptions on the algorithms concerned: (i) like a real-life algorothm it has round-off errors, and (ii) it has no round-off errors. Assuming (i) we (a) consider a probability mass function of the elements of the language if the data are drawn independent identically distributed (i.i.d.), provided the probability mass function is computable and has a finite expectation. We give an effective procedure to almost surely identify in the limit the target probability mass function using the Strong Law of Large Numbers. Second (b) we treat the case of possibly incomputable probabilistic mass functions in the above setting. In this case we can only pointswize converge to the target probability mass function almost surely. Third (c) we consider the case where the data are dependent assuming they are typical for at least one computable measure and the language is finite. There is an effective procedure to identify by infinite recurrence a nonempty subset of the computable measures according to which the data is typical. Here we use the theory of Kolmogorov complexity. Assuming (ii) we obtain the weaker result for (a) that the target distribution is identified by infinite recurrence almost surely; (b) stays the same as under assumption (i). We consider the associated predictions.", "source": "arxiv/ml"}
{"id": "arxiv:2124", "title": "Changepoint detection for high-dimensional time series with missing data", "text": "This paper describes a novel approach to change-point detection when the observed high-dimensional data may have missing elements. The performance of classical methods for change-point detection typically scales poorly with the dimensionality of the data, so that a large number of observations are collected after the true change-point before it can be reliably detected. Furthermore, missing components in the observed data handicap conventional approaches. The proposed method addresses these challenges by modeling the dynamic distribution underlying the data as lying close to a time-varying low-dimensional submanifold embedded within the ambient observation space. Specifically, streaming data is used to track a submanifold approximation, measure deviations from this approximation, and calculate a series of statistics of the deviations for detecting when the underlying manifold has changed in a sharp or unexpected manner. The approach described in this paper leverages several recent results in the field of high-dimensional data analysis, including subspace tracking with missing data, multiscale analysis techniques for point clouds, online optimization, and change-point detection performance analysis. Simulations and experiments highlight the robustness and efficacy of the proposed approach in detecting an abrupt change in an otherwise slowly varying low-dimensional manifold.", "source": "arxiv/ml"}
{"id": "arxiv:2125", "title": "Vector Field k-Means: Clustering Trajectories by Fitting Multiple Vector Fields", "text": "Scientists study trajectory data to understand trends in movement patterns, such as human mobility for traffic analysis and urban planning. There is a pressing need for scalable and efficient techniques for analyzing this data and discovering the underlying patterns. In this paper, we introduce a novel technique which we call vector-field $k$-means. The central idea of our approach is to use vector fields to induce a similarity notion between trajectories. Other clustering algorithms seek a representative trajectory that best describes each cluster, much like $k$-means identifies a representative \"center\" for each cluster. Vector-field $k$-means, on the other hand, recognizes that in all but the simplest examples, no single trajectory adequately describes a cluster. Our approach is based on the premise that movement trends in trajectory data can be modeled as flows within multiple vector fields, and the vector field itself is what defines each of the clusters. We also show how vector-field $k$-means connects techniques for scalar field design on meshes and $k$-means clustering. We present an algorithm that finds a locally optimal clustering of trajectories into vector fields, and demonstrate how vector-field $k$-means can be used to mine patterns from trajectory data. We present experimental evidence of its effectiveness and efficiency using several datasets, including historical hurricane data, GPS tracks of people and vehicles, and anonymous call records from a large phone company. We compare our results to previous trajectory clustering techniques, and find that our algorithm performs faster in practice than the current state-of-the-art in trajectory clustering, in some examples by a large margin.", "source": "arxiv/ml"}
{"id": "arxiv:2126", "title": "Link Prediction via Generalized Coupled Tensor Factorisation", "text": "This study deals with the missing link prediction problem: the problem of predicting the existence of missing connections between entities of interest. We address link prediction using coupled analysis of relational datasets represented as heterogeneous data, i.e., datasets in the form of matrices and higher-order tensors. We propose to use an approach based on probabilistic interpretation of tensor factorisation models, i.e., Generalised Coupled Tensor Factorisation, which can simultaneously fit a large class of tensor models to higher-order tensors/matrices with com- mon latent factors using different loss functions. Numerical experiments demonstrate that joint analysis of data from multiple sources via coupled factorisation improves the link prediction performance and the selection of right loss function and tensor model is crucial for accurately predicting missing links.", "source": "arxiv/ml"}
{"id": "arxiv:2127", "title": "Automated Marble Plate Classification System Based On Different Neural Network Input Training Sets and PLC Implementation", "text": "The process of sorting marble plates according to their surface texture is an important task in the automated marble plate production. Nowadays some inspection systems in marble industry that automate the classification tasks are too expensive and are compatible only with specific technological equipment in the plant. In this paper a new approach to the design of an Automated Marble Plate Classification System (AMPCS),based on different neural network input training sets is proposed, aiming at high classification accuracy using simple processing and application of only standard devices. It is based on training a classification MLP neural network with three different input training sets: extracted texture histograms, Discrete Cosine and Wavelet Transform over the histograms. The algorithm is implemented in a PLC for real-time operation. The performance of the system is assessed with each one of the input training sets. The experimental test results regarding classification accuracy and quick operation are represented and discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2128", "title": "Comparative Study and Optimization of Feature-Extraction Techniques for Content based Image Retrieval", "text": "The aim of a Content-Based Image Retrieval (CBIR) system, also known as Query by Image Content (QBIC), is to help users to retrieve relevant images based on their contents. CBIR technologies provide a method to find images in large databases by using unique descriptors from a trained image. The image descriptors include texture, color, intensity and shape of the object inside an image. Several feature-extraction techniques viz., Average RGB, Color Moments, Co-occurrence, Local Color Histogram, Global Color Histogram and Geometric Moment have been critically compared in this paper. However, individually these techniques result in poor performance. So, combinations of these techniques have also been evaluated and results for the most efficient combination of techniques have been presented and optimized for each class of image query. We also propose an improvement in image retrieval performance by introducing the idea of Query modification through image cropping. It enables the user to identify a region of interest and modify the initial query to refine and personalize the image retrieval results.", "source": "arxiv/ml"}
{"id": "arxiv:2129", "title": "A Widely Applicable Bayesian Information Criterion", "text": "A statistical model or a learning machine is called regular if the map taking a parameter to a probability distribution is one-to-one and if its Fisher information matrix is always positive definite. If otherwise, it is called singular. In regular statistical models, the Bayes free energy, which is defined by the minus logarithm of Bayes marginal likelihood, can be asymptotically approximated by the Schwarz Bayes information criterion (BIC), whereas in singular models such approximation does not hold. Recently, it was proved that the Bayes free energy of a singular model is asymptotically given by a generalized formula using a birational invariant, the real log canonical threshold (RLCT), instead of half the number of parameters in BIC. Theoretical values of RLCTs in several statistical models are now being discovered based on algebraic geometrical methodology. However, it has been difficult to estimate the Bayes free energy using only training samples, because an RLCT depends on an unknown true distribution. In the present paper, we define a widely applicable Bayesian information criterion (WBIC) by the average log likelihood function over the posterior distribution with the inverse temperature $1/\\log n$, where $n$ is the number of training samples. We mathematically prove that WBIC has the same asymptotic expansion as the Bayes free energy, even if a statistical model is singular for and unrealizable by a statistical model. Since WBIC can be numerically calculated without any information about a true distribution, it is a generalized version of BIC onto singular statistical models.", "source": "arxiv/ml"}
{"id": "arxiv:2130", "title": "An Improved Bound for the Nystrom Method for Large Eigengap", "text": "We develop an improved bound for the approximation error of the Nystr\\\"{o}m method under the assumption that there is a large eigengap in the spectrum of kernel matrix. This is based on the empirical observation that the eigengap has a significant impact on the approximation error of the Nystr\\\"{o}m method. Our approach is based on the concentration inequality of integral operator and the theory of matrix perturbation. Our analysis shows that when there is a large eigengap, we can improve the approximation error of the Nystr\\\"{o}m method from $O(N/m^{1/4})$ to $O(N/m^{1/2})$ when measured in Frobenius norm, where $N$ is the size of the kernel matrix, and $m$ is the number of sampled columns.", "source": "arxiv/ml"}
{"id": "arxiv:2131", "title": "Statistically adaptive learning for a general class of cost functions (SA L-BFGS)", "text": "We present a system that enables rapid model experimentation for tera-scale machine learning with trillions of non-zero features, billions of training examples, and millions of parameters. Our contribution to the literature is a new method (SA L-BFGS) for changing batch L-BFGS to perform in near real-time by using statistical tools to balance the contributions of previous weights, old training examples, and new training examples to achieve fast convergence with few iterations. The result is, to our knowledge, the most scalable and flexible linear learning system reported in the literature, beating standard practice with the current best system (Vowpal Wabbit and AllReduce). Using the KDD Cup 2012 data set from Tencent, Inc. we provide experimental results to verify the performance of this method.", "source": "arxiv/ml"}
{"id": "arxiv:2132", "title": "Learning implicitly in reasoning in PAC-Semantics", "text": "We consider the problem of answering queries about formulas of propositional logic based on background knowledge partially represented explicitly as other formulas, and partially represented as partially obscured examples independently drawn from a fixed probability distribution, where the queries are answered with respect to a weaker semantics than usual -- PAC-Semantics, introduced by Valiant (2000) -- that is defined using the distribution of examples. We describe a fairly general, efficient reduction to limited versions of the decision problem for a proof system (e.g., bounded space treelike resolution, bounded degree polynomial calculus, etc.) from corresponding versions of the reasoning problem where some of the background knowledge is not explicitly given as formulas, only learnable from the examples. Crucially, we do not generate an explicit representation of the knowledge extracted from the examples, and so the \"learning\" of the background knowledge is only done implicitly. As a consequence, this approach can utilize formulas as background knowledge that are not perfectly valid over the distribution---essentially the analogue of agnostic learning here.", "source": "arxiv/ml"}
{"id": "arxiv:2133", "title": "Estimating the historical and future probabilities of large terrorist events", "text": "Quantities with right-skewed distributions are ubiquitous in complex social systems, including political conflict, economics and social networks, and these systems sometimes produce extremely large events. For instance, the 9/11 terrorist events produced nearly 3000 fatalities, nearly six times more than the next largest event. But, was this enormous loss of life statistically unlikely given modern terrorism's historical record? Accurately estimating the probability of such an event is complicated by the large fluctuations in the empirical distribution's upper tail. We present a generic statistical algorithm for making such estimates, which combines semi-parametric models of tail behavior and a nonparametric bootstrap. Applied to a global database of terrorist events, we estimate the worldwide historical probability of observing at least one 9/11-sized or larger event since 1968 to be 11-35%. These results are robust to conditioning on global variations in economic development, domestic versus international events, the type of weapon used and a truncated history that stops at 1998. We then use this procedure to make a data-driven statistical forecast of at least one similar event over the next decade.", "source": "arxiv/ml"}
{"id": "arxiv:2134", "title": "A History of Cluster Analysis Using the Classification Society's Bibliography Over Four Decades", "text": "The Classification Literature Automated Search Service, an annual bibliography based on citation of one or more of a set of around 80 book or journal publications, ran from 1972 to 2012. We analyze here the years 1994 to 2011. The Classification Society's Service, as it was termed, has been produced by the Classification Society. In earlier decades it was distributed as a diskette or CD with the Journal of Classification. Among our findings are the following: an enormous increase in scholarly production post approximately 2000; a very major increase in quantity, coupled with work in different disciplines, from approximately 2004; and a major shift also from cluster analysis in earlier times having mathematics and psychology as disciplines of the journals published in, and affiliations of authors, contrasted with, in more recent times, a \"centre of gravity\" in management and engineering.", "source": "arxiv/ml"}
{"id": "arxiv:2135", "title": "Autoregressive short-term prediction of turning points using support vector regression", "text": "This work is concerned with autoregressive prediction of turning points in financial price sequences. Such turning points are critical local extrema points along a series, which mark the start of new swings. Predicting the future time of such turning points or even their early or late identification slightly before or after the fact has useful applications in economics and finance. Building on recently proposed neural network model for turning point prediction, we propose and study a new autoregressive model for predicting turning points of small swings. Our method relies on a known turning point indicator, a Fourier enriched representation of price histories, and support vector regression. We empirically examine the performance of the proposed method over a long history of the Dow Jones Industrial average. Our study shows that the proposed method is superior to the previous neural network model, in terms of trading performance of a simple trading application and also exhibits a quantifiable advantage over the buy-and-hold benchmark.", "source": "arxiv/ml"}
{"id": "arxiv:2136", "title": "Proximal methods for the latent group lasso penalty", "text": "We consider a regularized least squares problem, with regularization by structured sparsity-inducing norms, which extend the usual $\\ell_1$ and the group lasso penalty, by allowing the subsets to overlap. Such regularizations lead to nonsmooth problems that are difficult to optimize, and we propose in this paper a suitable version of an accelerated proximal method to solve them. We prove convergence of a nested procedure, obtained composing an accelerated proximal method with an inner algorithm for computing the proximity operator. By exploiting the geometrical properties of the penalty, we devise a new active set strategy, thanks to which the inner iteration is relatively fast, thus guaranteeing good computational performances of the overall algorithm. Our approach allows to deal with high dimensional problems without pre-processing for dimensionality reduction, leading to better computational and prediction performances with respect to the state-of-the art methods, as shown empirically both on toy and real data.", "source": "arxiv/ml"}
{"id": "arxiv:2137", "title": "Fixed-rank matrix factorizations and Riemannian low-rank optimization", "text": "Motivated by the problem of learning a linear regression model whose parameter is a large fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function defined on the set of fixed-rank matrices. We adopt the geometric framework of optimization on Riemannian quotient manifolds. We study the underlying geometries of several well-known fixed-rank matrix factorizations and then exploit the Riemannian quotient geometry of the search space in the design of a class of gradient descent and trust-region algorithms. The proposed algorithms generalize our previous results on fixed-rank symmetric positive semidefinite matrices, apply to a broad range of applications, scale to high-dimensional problems and confer a geometric basis to recent contributions on the learning of fixed-rank non-symmetric matrices. We make connections with existing algorithms in the context of low-rank matrix completion and discuss relative usefulness of the proposed framework. Numerical experiments suggest that the proposed algorithms compete with the state-of-the-art and that manifold optimization offers an effective and versatile framework for the design of machine learning algorithms that learn a fixed-rank matrix.", "source": "arxiv/ml"}
{"id": "arxiv:2138", "title": "Efficient EM Training of Gaussian Mixtures with Missing Data", "text": "In data-mining applications, we are frequently faced with a large fraction of missing entries in the data matrix, which is problematic for most discriminant machine learning algorithms. A solution that we explore in this paper is the use of a generative model (a mixture of Gaussians) to compute the conditional expectation of the missing variables given the observed variables. Since training a Gaussian mixture with many different patterns of missing values can be computationally very expensive, we introduce a spanning-tree based algorithm that significantly speeds up training in these conditions. We also observe that good results can be obtained by using the generative model to fill-in the missing values for a separate discriminant learning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2139", "title": "Sparse coding for multitask and transfer learning", "text": "We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear combinations of the atoms of a dictionary on a high or infinite dimensional space. This assumption, together with the large quantity of available data in the multitask and transfer learning settings, allows a principled choice of the dictionary. We provide bounds on the generalization error of this approach, for both settings. Numerical experiments on one synthetic and two real datasets show the advantage of our method over single task learning, a previous method based on orthogonal and dense representation of the tasks and a related method learning task grouping.", "source": "arxiv/ml"}
{"id": "arxiv:2140", "title": "Improving the K-means algorithm using improved downhill simplex search", "text": "The k-means algorithm is one of the well-known and most popular clustering algorithms. K-means seeks an optimal partition of the data by minimizing the sum of squared error with an iterative optimization procedure, which belongs to the category of hill climbing algorithms. As we know hill climbing searches are famous for converging to local optimums. Since k-means can converge to a local optimum, different initial points generally lead to different convergence cancroids, which makes it important to start with a reasonable initial partition in order to achieve high quality clustering solutions. However, in theory, there exist no efficient and universal methods for determining such initial partitions. In this paper we tried to find an optimum initial partitioning for k-means algorithm. To achieve this goal we proposed a new improved version of downhill simplex search, and then we used it in order to find an optimal result for clustering approach and then compare this algorithm with Genetic Algorithm base (GA), Genetic K-Means (GKM), Improved Genetic K-Means (IGKM) and k-means algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2141", "title": "Structuring Relevant Feature Sets with Multiple Model Learning", "text": "Feature selection is one of the most prominent learning tasks, especially in high-dimensional datasets in which the goal is to understand the mechanisms that underly the learning dataset. However most of them typically deliver just a flat set of relevant features and provide no further information on what kind of structures, e.g. feature groupings, might underly the set of relevant features. In this paper we propose a new learning paradigm in which our goal is to uncover the structures that underly the set of relevant features for a given learning problem. We uncover two types of features sets, non-replaceable features that contain important information about the target variable and cannot be replaced by other features, and functionally similar features sets that can be used interchangeably in learned models, given the presence of the non-replaceable features, with no change in the predictive performance. To do so we propose a new learning algorithm that learns a number of disjoint models using a model disjointness regularization constraint together with a constraint on the predictive agreement of the disjoint models. We explore the behavior of our approach on a number of high-dimensional datasets, and show that, as expected by their construction, these satisfy a number of properties. Namely, model disjointness, a high predictive agreement, and a similar predictive performance to models learned on the full set of relevant features. The ability to structure the set of relevant features in such a manner can become a valuable tool in different applications of scientific knowledge discovery.", "source": "arxiv/ml"}
{"id": "arxiv:2142", "title": "The Annealing Sparse Bayesian Learning Algorithm", "text": "In this paper we propose a two-level hierarchical Bayesian model and an annealing schedule to re-enable the noise variance learning capability of the fast marginalized Sparse Bayesian Learning Algorithms. The performance such as NMSE and F-measure can be greatly improved due to the annealing technique. This algorithm tends to produce the most sparse solution under moderate SNR scenarios and can outperform most concurrent SBL algorithms while pertains small computational load.", "source": "arxiv/ml"}
{"id": "arxiv:2143", "title": "Learning Probability Measures with respect to Optimal Transport Metrics", "text": "We study the problem of estimating, in the sense of optimal transport metrics, a measure which is assumed supported on a manifold embedded in a Hilbert space. By establishing a precise connection between optimal transport metrics, optimal quantization, and learning theory, we derive new probabilistic bounds for the performance of a classic algorithm in unsupervised learning (k-means), when used to produce a probability measure derived from the data. In the course of the analysis, we arrive at new lower bounds, as well as probabilistic upper bounds on the convergence rate of the empirical law of large numbers, which, unlike existing bounds, are applicable to a wide class of measures.", "source": "arxiv/ml"}
{"id": "arxiv:2144", "title": "Robustness and Generalization for Metric Learning", "text": "Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied. In this paper, we introduce an adaptation of the notion of algorithmic robustness (previously introduced by Xu and Mannor) that can be used to derive generalization bounds for metric learning. We further show that a weak notion of robustness is in fact a necessary and sufficient condition for a metric learning algorithm to generalize. To illustrate the applicability of the proposed framework, we derive generalization results for a large family of existing metric learning algorithms, including some sparse formulations that are not covered by previous results.", "source": "arxiv/ml"}
{"id": "arxiv:2145", "title": "Learning Manifolds with K-Means and K-Flats", "text": "We study the problem of estimating a manifold from random samples. In particular, we consider piecewise constant and piecewise linear estimators induced by k-means and k-flats, and analyze their performance. We extend previous results for k-means in two separate directions. First, we provide new results for k-means reconstruction on manifolds and, secondly, we prove reconstruction bounds for higher-order approximation (k-flats), for which no known results were previously available. While the results for k-means are novel, some of the technical tools are well-established in the literature. In the case of k-flats, both the results and the mathematical tools are new.", "source": "arxiv/ml"}
{"id": "arxiv:2146", "title": "Multiclass Learning with Simplex Coding", "text": "In this paper we discuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows to generalize to multiple classes a relaxation approach commonly used in binary classification. In this framework, a relaxation error analysis can be developed avoiding constraints on the considered hypotheses class. Moreover, we show that in this setting it is possible to derive the first provably consistent regularized method with training/tuning complexity which is independent to the number of classes. Tools from convex analysis are introduced that can be used beyond the scope of this paper.", "source": "arxiv/ml"}
{"id": "arxiv:2147", "title": "On spatial selectivity and prediction across conditions with fMRI", "text": "Researchers in functional neuroimaging mostly use activation coordinates to formulate their hypotheses. Instead, we propose to use the full statistical images to define regions of interest (ROIs). This paper presents two machine learning approaches, transfer learning and selection transfer, that are compared upon their ability to identify the common patterns between brain activation maps related to two functional tasks. We provide some preliminary quantification of these similarities, and show that selection transfer makes it possible to set a spatial scale yielding ROIs that are more specific to the context of interest than with transfer learning. In particular, selection transfer outlines well known regions such as the Visual Word Form Area when discriminating between different visual tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2148", "title": "Learning Model-Based Sparsity via Projected Gradient Descent", "text": "Several convex formulation methods have been proposed previously for statistical estimation with structured sparsity as the prior. These methods often require a carefully tuned regularization parameter, often a cumbersome or heuristic exercise. Furthermore, the estimate that these methods produce might not belong to the desired sparsity model, albeit accurately approximating the true parameter. Therefore, greedy-type algorithms could often be more desirable in estimating structured-sparse parameters. So far, these greedy methods have mostly focused on linear statistical models. In this paper we study the projected gradient descent with non-convex structured-sparse parameter model as the constraint set. Should the cost function have a Stable Model-Restricted Hessian the algorithm produces an approximation for the desired minimizer. As an example we elaborate on application of the main results to estimation in Generalized Linear Model.", "source": "arxiv/ml"}
{"id": "arxiv:2149", "title": "Rank Centrality: Ranking from Pair-wise Comparisons", "text": "The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating social opinions, or deciding which product to sell based on transactions. In most settings, in addition to obtaining a ranking, finding `scores' for each object (e.g. player's rating) is of interest for understanding the intensity of the preferences. In this paper, we propose Rank Centrality, an iterative rank aggregation algorithm for discovering scores for objects (or items) from pair-wise comparisons. The algorithm has a natural random walk interpretation over the graph of objects with an edge present between a pair of objects if they are compared; the score, which we call Rank Centrality, of an object turns out to be its stationary probability under this random walk. To study the efficacy of the algorithm, we consider the popular Bradley-Terry-Luce (BTL) model (equivalent to the Multinomial Logit (MNL) for pair-wise comparisons) in which each object has an associated score which determines the probabilistic outcomes of pair-wise comparisons between objects. In terms of the pair-wise marginal probabilities, which is the main subject of this paper, the MNL model and the BTL model are identical. We bound the finite sample error rates between the scores assumed by the BTL model and those estimated by our algorithm. In particular, the number of samples required to learn the score well with high probability depends on the structure of the comparison graph. When the Laplacian of the comparison graph has a strictly positive spectral gap, e.g. each item is compared to a subset of randomly chosen items, this leads to dependence on the number of samples that is nearly order-optimal.", "source": "arxiv/ml"}
{"id": "arxiv:2150", "title": "Bandits with heavy tail", "text": "The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+\\epsilon, for some $\\epsilon \\in (0,1]$. Surprisingly, moments of order 2 (i.e., finite variance) are sufficient to obtain regret bounds of the same order as under sub-Gaussian reward distributions. In order to achieve such regret, we define sampling strategies based on refined estimators of the mean such as the truncated empirical mean, Catoni's M-estimator, and the median-of-means estimator. We also derive matching lower bounds that also show that the best achievable regret deteriorates when \\epsilon <1.", "source": "arxiv/ml"}
{"id": "arxiv:2151", "title": "Design of Spectrum Sensing Policy for Multi-user Multi-band Cognitive Radio Network", "text": "Finding an optimal sensing policy for a particular access policy and sensing scheme is a laborious combinatorial problem that requires the system model parameters to be known. In practise the parameters or the model itself may not be completely known making reinforcement learning methods appealing. In this paper a non-parametric reinforcement learning-based method is developed for sensing and accessing multi-band radio spectrum in multi-user cognitive radio networks. A suboptimal sensing policy search algorithm is proposed for a particular multi-user multi-band access policy and the randomized Chair-Varshney rule. The randomized Chair-Varshney rule is used to reduce the probability of false alarms under a constraint on the probability of detection that protects the primary user. The simulation results show that the proposed method achieves a sum profit (e.g. data rate) close to the optimal sensing policy while achieving the desired probability of detection.", "source": "arxiv/ml"}
{"id": "arxiv:2152", "title": "Securing Your Transactions: Detecting Anomalous Patterns In XML Documents", "text": "XML transactions are used in many information systems to store data and interact with other systems. Abnormal transactions, the result of either an on-going cyber attack or the actions of a benign user, can potentially harm the interacting systems and therefore they are regarded as a threat. In this paper we address the problem of anomaly detection and localization in XML transactions using machine learning techniques. We present a new XML anomaly detection framework, XML-AD. Within this framework, an automatic method for extracting features from XML transactions was developed as well as a practical method for transforming XML features into vectors of fixed dimensionality. With these two methods in place, the XML-AD framework makes it possible to utilize general learning algorithms for anomaly detection. Central to the functioning of the framework is a novel multi-univariate anomaly detection algorithm, ADIFA. The framework was evaluated on four XML transactions datasets, captured from real information systems, in which it achieved over 89% true positive detection rate with less than a 0.2% false positive rate.", "source": "arxiv/ml"}
{"id": "arxiv:2153", "title": "An Empirical Study of MAUC in Multi-class Problems with Uncertain Cost Matrices", "text": "Cost-sensitive learning relies on the availability of a known and fixed cost matrix. However, in some scenarios, the cost matrix is uncertain during training, and re-train a classifier after the cost matrix is specified would not be an option. For binary classification, this issue can be successfully addressed by methods maximizing the Area Under the ROC Curve (AUC) metric. Since the AUC can measure performance of base classifiers independent of cost during training, and a larger AUC is more likely to lead to a smaller total cost in testing using the threshold moving method. As an extension of AUC to multi-class problems, MAUC has attracted lots of attentions and been widely used. Although MAUC also measures performance of base classifiers independent of cost, it is unclear whether a larger MAUC of classifiers is more likely to lead to a smaller total cost. In fact, it is also unclear what kinds of post-processing methods should be used in multi-class problems to convert base classifiers into discrete classifiers such that the total cost is as small as possible. In the paper, we empirically explore the relationship between MAUC and the total cost of classifiers by applying two categories of post-processing methods. Our results suggest that a larger MAUC is also beneficial. Interestingly, simple calibration methods that convert the output matrix into posterior probabilities perform better than existing sophisticated post re-optimization methods.", "source": "arxiv/ml"}
{"id": "arxiv:2154", "title": "Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization", "text": "Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closely related Dual Coordinate Ascent (DCA) method has been implemented in various software packages, it has so far lacked good convergence analysis. This paper presents a new analysis of Stochastic Dual Coordinate Ascent (SDCA) showing that this class of methods enjoy strong theoretical guarantees that are comparable or better than SGD. This analysis justifies the effectiveness of SDCA for practical applications.", "source": "arxiv/ml"}
{"id": "arxiv:2155", "title": "A Comparative Study of Efficient Initialization Methods for the K-Means Clustering Algorithm", "text": "K-means is undoubtedly the most widely used partitional clustering algorithm. Unfortunately, due to its gradient descent nature, this algorithm is highly sensitive to the initial placement of the cluster centers. Numerous initialization methods have been proposed to address this problem. In this paper, we first present an overview of these methods with an emphasis on their computational efficiency. We then compare eight commonly used linear time complexity initialization methods on a large and diverse collection of data sets using various performance criteria. Finally, we analyze the experimental results using non-parametric statistical tests and provide recommendations for practitioners. We demonstrate that popular initialization methods often perform poorly and that there are in fact strong alternatives to these methods.", "source": "arxiv/ml"}
{"id": "arxiv:2156", "title": "Fused Multiple Graphical Lasso", "text": "In this paper, we consider the problem of estimating multiple graphical models simultaneously using the fused lasso penalty, which encourages adjacent graphs to share similar structures. A motivating example is the analysis of brain networks of Alzheimer's disease using neuroimaging data. Specifically, we may wish to estimate a brain network for the normal controls (NC), a brain network for the patients with mild cognitive impairment (MCI), and a brain network for Alzheimer's patients (AD). We expect the two brain networks for NC and MCI to share common structures but not to be identical to each other; similarly for the two brain networks for MCI and AD. The proposed formulation can be solved using a second-order method. Our key technical contribution is to establish the necessary and sufficient condition for the graphs to be decomposable. Based on this key property, a simple screening rule is presented, which decomposes the large graphs into small subgraphs and allows an efficient estimation of multiple independent (small) subgraphs, dramatically reducing the computational cost. We perform experiments on both synthetic and real data; our results demonstrate the effectiveness and efficiency of the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:2157", "title": "Cooperative learning in multi-agent systems from intermittent measurements", "text": "Motivated by the problem of tracking a direction in a decentralized way, we consider the general problem of cooperative learning in multi-agent systems with time-varying connectivity and intermittent measurements. We propose a distributed learning protocol capable of learning an unknown vector $\\mu$ from noisy measurements made independently by autonomous nodes. Our protocol is completely distributed and able to cope with the time-varying, unpredictable, and noisy nature of inter-agent communication, and intermittent noisy measurements of $\\mu$. Our main result bounds the learning speed of our protocol in terms of the size and combinatorial features of the (time-varying) networks connecting the nodes.", "source": "arxiv/ml"}
{"id": "arxiv:2158", "title": "Counterfactual Reasoning and Learning Systems", "text": "This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select changes that improve both the short-term and long-term performance of such systems. This work is illustrated by experiments carried out on the ad placement system associated with the Bing search engine.", "source": "arxiv/ml"}
{"id": "arxiv:2159", "title": "On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization", "text": "The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and performance upper bounds. However, much less is known about the inherent complexity of these problems, and there are few lower bounds in the literature, especially for nonlinear functions. In this paper, we investigate the attainable error/regret in the bandit and derivative-free settings, as a function of the dimension d and the available number of queries T. We provide a precise characterization of the attainable performance for strongly-convex and smooth functions, which also imply a non-trivial lower bound for more general problems. Moreover, we prove that in both the bandit and derivative-free setting, the required number of queries must scale at least quadratically with the dimension. Finally, we show that on the natural class of quadratic functions, it is possible to obtain a \"fast\" O(1/T) error rate in terms of T, under mild assumptions, even without having access to gradients. To the best of our knowledge, this is the first such rate in a derivative-free stochastic setting, and holds despite previous results which seem to imply the contrary.", "source": "arxiv/ml"}
{"id": "arxiv:2160", "title": "Query Complexity of Derivative-Free Optimization", "text": "This paper provides lower bounds on the convergence rate of Derivative Free Optimization (DFO) with noisy function evaluations, exposing a fundamental and unavoidable gap between the performance of algorithms with access to gradients and those with access to only function evaluations. However, there are situations in which DFO is unavoidable, and for such situations we propose a new DFO algorithm that is proved to be near optimal for the class of strongly convex objective functions. A distinctive feature of the algorithm is that it uses only Boolean-valued function comparisons, rather than function evaluations. This makes the algorithm useful in an even wider range of applications, such as optimization based on paired comparisons from human subjects, for example. We also show that regardless of whether DFO is based on noisy function evaluations or Boolean-valued function comparisons, the convergence rate is the same.", "source": "arxiv/ml"}
{"id": "arxiv:2161", "title": "Performance Evaluation of Predictive Classifiers For Knowledge Discovery From Engineering Materials Data Sets", "text": "In this paper, naive Bayesian and C4.5 Decision Tree Classifiers(DTC) are successively applied on materials informatics to classify the engineering materials into different classes for the selection of materials that suit the input design specifications. Here, the classifiers are analyzed individually and their performance evaluation is analyzed with confusion matrix predictive parameters and standard measures, the classification results are analyzed on different class of materials. Comparison of classifiers has found that naive Bayesian classifier is more accurate and better than the C4.5 DTC. The knowledge discovered by the naive bayesian classifier can be employed for decision making in materials selection in manufacturing industries.", "source": "arxiv/ml"}
{"id": "arxiv:2162", "title": "Probabilities on Sentences in an Expressive Logic", "text": "Automated reasoning about uncertain knowledge has many applications. One difficulty when developing such systems is the lack of a completely satisfactory integration of logic and probability. We address this problem directly. Expressive languages like higher-order logic are ideally suited for representing and reasoning about structured knowledge. Uncertain knowledge can be modeled by using graded probabilities rather than binary truth-values. The main technical problem studied in this paper is the following: Given a set of sentences, each having some probability of being true, what probability should be ascribed to other (query) sentences? A natural wish-list, among others, is that the probability distribution (i) is consistent with the knowledge base, (ii) allows for a consistent inference procedure and in particular (iii) reduces to deductive logic in the limit of probabilities being 0 and 1, (iv) allows (Bayesian) inductive reasoning and (v) learning in the limit and in particular (vi) allows confirmation of universally quantified hypotheses/sentences. We translate this wish-list into technical requirements for a prior probability and show that probabilities satisfying all our criteria exist. We also give explicit constructions and several general characterizations of probabilities that satisfy some or all of the criteria and various (counter) examples. We also derive necessary and sufficient conditions for extending beliefs about finitely many sentences to suitable probabilities over all sentences, and in particular least dogmatic or least biased ones. We conclude with a brief outlook on how the developed theory might be used and approximated in autonomous reasoning agents. Our theory is a step towards a globally consistent and empirically satisfactory unification of probability and logic.", "source": "arxiv/ml"}
{"id": "arxiv:2163", "title": "Conditional validity of inductive conformal predictors", "text": "Conformal predictors are set predictors that are automatically valid in the sense of having coverage probability equal to or exceeding a given confidence level. Inductive conformal predictors are a computationally efficient version of conformal predictors satisfying the same property of validity. However, inductive conformal predictors have been only known to control unconditional coverage probability. This paper explores various versions of conditional validity and various ways to achieve them using inductive conformal predictors and their modifications.", "source": "arxiv/ml"}
{"id": "arxiv:2164", "title": "Regret Bounds for Restless Markov Bandits", "text": "We consider the restless Markov bandit problem, in which the state of each arm evolves according to a Markov process independently of the learner's actions. We suggest an algorithm that after $T$ steps achieves $\\tilde{O}(\\sqrt{T})$ regret with respect to the best policy that knows the distributions of all arms. No assumptions on the Markov chains are made except that they are irreducible. In addition, we show that index-based policies are necessarily suboptimal for the considered problem.", "source": "arxiv/ml"}
{"id": "arxiv:2165", "title": "Multi-track Map Matching", "text": "We study algorithms for matching user tracks, consisting of time-ordered location points, to paths in the road network. Previous work has focused on the scenario where the location data is linearly ordered and consists of fairly dense and regular samples. In this work, we consider the \\emph{multi-track map matching}, where the location data comes from different trips on the same route, each with very sparse samples. This captures the realistic scenario where users repeatedly travel on regular routes and samples are sparsely collected, either due to energy consumption constraints or because samples are only collected when the user actively uses a service. In the multi-track problem, the total set of combined locations is only partially ordered, rather than globally ordered as required by previous map-matching algorithms. We propose two methods, the iterative projection scheme and the graph Laplacian scheme, to solve the multi-track problem by using a single-track map-matching subroutine. We also propose a boosting technique which may be applied to either approach to improve the accuracy of the estimated paths. In addition, in order to deal with variable sampling rates in single-track map matching, we propose a method based on a particular regularized cost function that can be adapted for different sampling rates and measurement errors. We evaluate the effectiveness of our techniques for reconstructing tracks under several different configurations of sampling error and sampling rate.", "source": "arxiv/ml"}
{"id": "arxiv:2166", "title": "Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL", "text": "Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation that minimizes the maximum of the tasks' empirical risks. Via a certain relaxation of minimax MTL, we obtain a continuum of MTL formulations spanning minimax MTL and classical MTL. The full paradigm itself is loss-compositional, operating on the vector of empirical risks. It incorporates minimax MTL, its relaxations, and many new MTL formulations as special cases. We show theoretically that minimax MTL tends to avoid worst case outcomes on newly drawn test tasks in the learning to learn (LTL) test setting. The results of several MTL formulations on synthetic and real problems in the MTL and LTL test settings are encouraging.", "source": "arxiv/ml"}
{"id": "arxiv:2167", "title": "Improving Energy Efficiency in Femtocell Networks: A Hierarchical Reinforcement Learning Framework", "text": "This paper investigates energy efficiency for two-tier femtocell networks through combining game theory and stochastic learning. With the Stackelberg game formulation, a hierarchical reinforcement learning framework is applied to study the joint average utility maximization of macrocells and femtocells subject to the minimum signal-to-interference-plus-noise-ratio requirements. The macrocells behave as the leaders and the femtocells are followers during the learning procedure. At each time step, the leaders commit to dynamic strategies based on the best responses of the followers, while the followers compete against each other with no further information but the leaders' strategy information. In this paper, we propose two learning algorithms to schedule each cell's stochastic power levels, leading by the macrocells. Numerical experiments are presented to validate the proposed studies and show that the two learning algorithms substantially improve the energy efficiency of the femtocell networks.", "source": "arxiv/ml"}
{"id": "arxiv:2168", "title": "Community Detection in the Labelled Stochastic Block Model", "text": "We consider the problem of community detection from observed interactions between individuals, in the context where multiple types of interaction are possible. We use labelled stochastic block models to represent the observed data, where labels correspond to interaction types. Focusing on a two-community scenario, we conjecture a threshold for the problem of reconstructing the hidden communities in a way that is correlated with the true partition. To substantiate the conjecture, we prove that the given threshold correctly identifies a transition on the behaviour of belief propagation from insensitive to sensitive. We further prove that the same threshold corresponds to the transition in a related inference problem on a tree model from infeasible to feasible. Finally, numerical results using belief propagation for community detection give further support to the conjecture.", "source": "arxiv/ml"}
{"id": "arxiv:2169", "title": "Parametric Local Metric Learning for Nearest Neighbor Classification", "text": "We study the problem of learning local metrics for nearest neighbor classification. Most previous works on local metric learning learn a number of local unrelated metrics. While this \"independence\" approach delivers an increased flexibility its downside is the considerable risk of overfitting. We present a new parametric local metric learning method in which we learn a smooth metric matrix function over the data manifold. Using an approximation error bound of the metric matrix function we learn local metrics as linear combinations of basis metrics defined on anchor points over different regions of the instance space. We constrain the metric matrix function by imposing on the linear combinations manifold regularization which makes the learned metric matrix function vary smoothly along the geodesics of the data manifold. Our metric learning method has excellent performance both in terms of predictive power and scalability. We experimented with several large-scale classification problems, tens of thousands of instances, and compared it with several state of the art metric learning methods, both global and local, as well as to SVM with automatic kernel selection, all of which it outperforms in a significant manner.", "source": "arxiv/ml"}
{"id": "arxiv:2170", "title": "Analog readout for optical reservoir computers", "text": "Reservoir computing is a new, powerful and flexible machine learning technique that is easily implemented in hardware. Recently, by using a time-multiplexed architecture, hardware reservoir computers have reached performance comparable to digital implementations. Operating speeds allowing for real time information operation have been reached using optoelectronic systems. At present the main performance bottleneck is the readout layer which uses slow, digital postprocessing. We have designed an analog readout suitable for time-multiplexed optoelectronic reservoir computers, capable of working in real time. The readout has been built and tested experimentally on a standard benchmark task. Its performance is better than non-reservoir methods, with ample room for further improvement. The present work thereby overcomes one of the major limitations for the future development of hardware reservoir computers.", "source": "arxiv/ml"}
{"id": "arxiv:2171", "title": "Thompson Sampling for Contextual Bandits with Linear Payoffs", "text": "Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better empirical performance compared to the state-of-the-art methods. However, many questions regarding its theoretical performance remained open. In this paper, we design and analyze a generalization of Thompson Sampling algorithm for the stochastic contextual multi-armed bandit problem with linear payoff functions, when the contexts are provided by an adaptive adversary. This is among the most important and widely studied versions of the contextual bandits problem. We provide the first theoretical guarantees for the contextual version of Thompson Sampling. We prove a high probability regret bound of $\\tilde{O}(d^{3/2}\\sqrt{T})$ (or $\\tilde{O}(d\\sqrt{T \\log(N)})$), which is the best regret bound achieved by any computationally efficient algorithm available for this problem in the current literature, and is within a factor of $\\sqrt{d}$ (or $\\sqrt{\\log(N)}$) of the information-theoretic lower bound for this problem.", "source": "arxiv/ml"}
{"id": "arxiv:2172", "title": "Further Optimal Regret Bounds for Thompson Sampling", "text": "Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better empirical performance compared to the state of the art methods. In this paper, we provide a novel regret analysis for Thompson Sampling that simultaneously proves both the optimal problem-dependent bound of $(1+\\epsilon)\\sum_i \\frac{\\ln T}{\\Delta_i}+O(\\frac{N}{\\epsilon^2})$ and the first near-optimal problem-independent bound of $O(\\sqrt{NT\\ln T})$ on the expected regret of this algorithm. Our near-optimal problem-independent bound solves a COLT 2012 open problem of Chapelle and Li. The optimal problem-dependent regret bound for this problem was first proven recently by Kaufmann et al. [ALT 2012]. Our novel martingale-based analysis techniques are conceptually simple, easily extend to distributions other than the Beta distribution, and also extend to the more general contextual bandits setting [Manuscript, Agrawal and Goyal, 2012].", "source": "arxiv/ml"}
{"id": "arxiv:2173", "title": "A Hajj And Umrah Location Classification System For Video Crowded Scenes", "text": "In this paper, a new automatic system for classifying ritual locations in diverse Hajj and Umrah video scenes is investigated. This challenging subject has mostly been ignored in the past due to several problems one of which is the lack of realistic annotated video datasets. HUER Dataset is defined to model six different Hajj and Umrah ritual locations[26]. The proposed Hajj and Umrah ritual location classifying system consists of four main phases: Preprocessing, segmentation, feature extraction, and location classification phases. The shot boundary detection and background/foregroud segmentation algorithms are applied to prepare the input video scenes into the KNN, ANN, and SVM classifiers. The system improves the state of art results on Hajj and Umrah location classifications, and successfully recognizes the six Hajj rituals with more than 90% accuracy. The various demonstrated experiments show the promising results.", "source": "arxiv/ml"}
{"id": "arxiv:2174", "title": "Active Learning for Crowd-Sourced Databases", "text": "Crowd-sourcing has become a popular means of acquiring labeled data for a wide variety of tasks where humans are more accurate than computers, e.g., labeling images, matching objects, or analyzing sentiment. However, relying solely on the crowd is often impractical even for data sets with thousands of items, due to time and cost constraints of acquiring human input (which cost pennies and minutes per label). In this paper, we propose algorithms for integrating machine learning into crowd-sourced databases, with the goal of allowing crowd-sourcing applications to scale, i.e., to handle larger datasets at lower costs. The key observation is that, in many of the above tasks, humans and machine learning algorithms can be complementary, as humans are often more accurate but slow and expensive, while algorithms are usually less accurate, but faster and cheaper. Based on this observation, we present two new active learning algorithms to combine humans and algorithms together in a crowd-sourced database. Our algorithms are based on the theory of non-parametric bootstrap, which makes our results applicable to a broad class of machine learning models. Our results, on three real-life datasets collected with Amazon's Mechanical Turk, and on 15 well-known UCI data sets, show that our methods on average ask humans to label one to two orders of magnitude fewer items to achieve the same accuracy as a baseline that labels random images, and two to eight times fewer questions than previous active learning schemes.", "source": "arxiv/ml"}
{"id": "arxiv:2175", "title": "Submodularity in Batch Active Learning and Survey Problems on Gaussian Random Fields", "text": "Many real-world datasets can be represented in the form of a graph whose edge weights designate similarities between instances. A discrete Gaussian random field (GRF) model is a finite-dimensional Gaussian process (GP) whose prior covariance is the inverse of a graph Laplacian. Minimizing the trace of the predictive covariance Sigma (V-optimality) on GRFs has proven successful in batch active learning classification problems with budget constraints. However, its worst-case bound has been missing. We show that the V-optimality on GRFs as a function of the batch query set is submodular and hence its greedy selection algorithm guarantees an (1-1/e) approximation ratio. Moreover, GRF models have the absence-of-suppressor (AofS) condition. For active survey problems, we propose a similar survey criterion which minimizes 1'(Sigma)1. In practice, V-optimality criterion performs better than GPs with mutual information gain criteria and allows nonuniform costs for different nodes.", "source": "arxiv/ml"}
{"id": "arxiv:2176", "title": "Generalized Canonical Correlation Analysis for Disparate Data Fusion", "text": "Manifold matching works to identify embeddings of multiple disparate data spaces into the same low-dimensional space, where joint inference can be pursued. It is an enabling methodology for fusion and inference from multiple and massive disparate data sources. In this paper we focus on a method called Canonical Correlation Analysis (CCA) and its generalization Generalized Canonical Correlation Analysis (GCCA), which belong to the more general Reduced Rank Regression (RRR) framework. We present an efficiency investigation of CCA and GCCA under different training conditions for a particular text document classification task.", "source": "arxiv/ml"}
{"id": "arxiv:2177", "title": "Evolution and the structure of learning agents", "text": "This paper presents the thesis that all learning agents of finite information size are limited by their informational structure in what goals they can efficiently learn to achieve in a complex environment. Evolutionary change is critical for creating the required structure for all learning agents in any complex environment. The thesis implies that there is no efficient universal learning algorithm. An agent can go past the learning limits imposed by its structure only by slow evolutionary change or blind search which in a very complex environment can only give an agent an inefficient universal learning capability that can work only in evolutionary timescales or improbable luck.", "source": "arxiv/ml"}
{"id": "arxiv:2178", "title": "Transferring Subspaces Between Subjects in Brain-Computer Interfacing", "text": "Compensating changes between a subjects' training and testing session in Brain Computer Interfacing (BCI) is challenging but of great importance for a robust BCI operation. We show that such changes are very similar between subjects, thus can be reliably estimated using data from other users and utilized to construct an invariant feature space. This novel approach to learning from other subjects aims to reduce the adverse effects of common non-stationarities, but does not transfer discriminative information. This is an important conceptual difference to standard multi-subject methods that e.g. improve the covariance matrix estimation by shrinking it towards the average of other users or construct a global feature space. These methods do not reduces the shift between training and test data and may produce poor results when subjects have very different signal characteristics. In this paper we compare our approach to two state-of-the-art multi-subject methods on toy data and two data sets of EEG recordings from subjects performing motor imagery. We show that it can not only achieve a significant increase in performance, but also that the extracted change patterns allow for a neurophysiologically meaningful interpretation.", "source": "arxiv/ml"}
{"id": "arxiv:2179", "title": "Comunication-Efficient Algorithms for Statistical Optimization", "text": "We analyze two communication-efficient algorithms for distributed statistical optimization on large-scale data sets. The first algorithm is a standard averaging method that distributes the $N$ data samples evenly to $\\nummac$ machines, performs separate minimization on each subset, and then averages the estimates. We provide a sharp analysis of this average mixture algorithm, showing that under a reasonable set of conditions, the combined parameter achieves mean-squared error that decays as $\\order(N^{-1}+(N/m)^{-2})$. Whenever $m \\le \\sqrt{N}$, this guarantee matches the best possible rate achievable by a centralized algorithm having access to all $\\totalnumobs$ samples. The second algorithm is a novel method, based on an appropriate form of bootstrap subsampling. Requiring only a single round of communication, it has mean-squared error that decays as $\\order(N^{-1} + (N/m)^{-3})$, and so is more robust to the amount of parallelization. In addition, we show that a stochastic gradient-based method attains mean-squared error decaying as $O(N^{-1} + (N/ m)^{-3/2})$, easing computation at the expense of penalties in the rate of convergence. We also provide experimental evaluation of our methods, investigating their performance both on simulated data and on a large-scale regression problem from the internet search domain. In particular, we show that our methods can be used to efficiently solve an advertisement prediction problem from the Chinese SoSo Search Engine, which involves logistic regression with $N \\approx 2.4 \\times 10^8$ samples and $d \\approx 740,000$ covariates.", "source": "arxiv/ml"}
{"id": "arxiv:2180", "title": "Efficient Regularized Least-Squares Algorithms for Conditional Ranking on Relational Data", "text": "In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel framework for learning conditional rankings from various types of relational data, where rankings can be conditioned on unseen data objects. We propose efficient algorithms for conditional ranking by optimizing squared regression and ranking loss functions. We show theoretically, that learning with the ranking loss is likely to generalize better than with the regression loss. Further, we prove that symmetry or reciprocity properties of relations can be efficiently enforced in the learned models. Experiments on synthetic and real-world data illustrate that the proposed methods deliver state-of-the-art performance in terms of predictive power and computational efficiency. Moreover, we also show empirically that incorporating symmetry or reciprocity properties can improve the generalization performance.", "source": "arxiv/ml"}
{"id": "arxiv:2181", "title": "On the Sensitivity of Shape Fitting Problems", "text": "In this article, we study shape fitting problems, $\\epsilon$-coresets, and total sensitivity. We focus on the $(j,k)$-projective clustering problems, including $k$-median/$k$-means, $k$-line clustering, $j$-subspace approximation, and the integer $(j,k)$-projective clustering problem. We derive upper bounds of total sensitivities for these problems, and obtain $\\epsilon$-coresets using these upper bounds. Using a dimension-reduction type argument, we are able to greatly simplify earlier results on total sensitivity for the $k$-median/$k$-means clustering problems, and obtain positively-weighted $\\epsilon$-coresets for several variants of the $(j,k)$-projective clustering problem. We also extend an earlier result on $\\epsilon$-coresets for the integer $(j,k)$-projective clustering problem in fixed dimension to the case of high dimension.", "source": "arxiv/ml"}
{"id": "arxiv:2182", "title": "An efficient model-free estimation of multiclass conditional probability", "text": "Conventional multiclass conditional probability estimation methods, such as Fisher's discriminate analysis and logistic regression, often require restrictive distributional model assumption. In this paper, a model-free estimation method is proposed to estimate multiclass conditional probability through a series of conditional quantile regression functions. Specifically, the conditional class probability is formulated as difference of corresponding cumulative distribution functions, where the cumulative distribution functions can be converted from the estimated conditional quantile regression functions. The proposed estimation method is also efficient as its computation cost does not increase exponentially with the number of classes. The theoretical and numerical studies demonstrate that the proposed estimation method is highly competitive against the existing competitors, especially when the number of classes is relatively large.", "source": "arxiv/ml"}
{"id": "arxiv:2183", "title": "A Bayesian Nonparametric Approach to Image Super-resolution", "text": "Super-resolution methods form high-resolution images from low-resolution images. In this paper, we develop a new Bayesian nonparametric model for super-resolution. Our method uses a beta-Bernoulli process to learn a set of recurring visual patterns, called dictionary elements, from the data. Because it is nonparametric, the number of elements found is also determined from the data. We test the results on both benchmark and natural images, comparing with several other models from the research literature. We perform large-scale human evaluation experiments to assess the visual quality of the results. In a first implementation, we use Gibbs sampling to approximate the posterior. However, this algorithm is not feasible for large-scale data. To circumvent this, we then develop an online variational Bayes (VB) algorithm. This algorithm finds high quality dictionaries in a fraction of the time needed by the Gibbs sampler.", "source": "arxiv/ml"}
{"id": "arxiv:2184", "title": "Fast Randomized Model Generation for Shapelet-Based Time Series Classification", "text": "Time series classification is a field which has drawn much attention over the past decade. A new approach for classification of time series uses classification trees based on shapelets. A shapelet is a subsequence extracted from one of the time series in the dataset. A disadvantage of this approach is the time required for building the shapelet-based classification tree. The search for the best shapelet requires examining all subsequences of all lengths from all time series in the training set. A key goal of this work was to find an evaluation order of the shapelets space which enables fast convergence to an accurate model. The comparative analysis we conducted clearly indicates that a random evaluation order yields the best results. Our empirical analysis of the distribution of high-quality shapelets within the shapelets space provides insights into why randomized shapelets sampling is superior to alternative evaluation orders. We present an algorithm for randomized model generation for shapelet-based classification that converges extremely quickly to a model with surprisingly high accuracy after evaluating only an exceedingly small fraction of the shapelets space.", "source": "arxiv/ml"}
{"id": "arxiv:2185", "title": "On Move Pattern Trends in a Large Go Games Corpus", "text": "We process a large corpus of game records of the board game of Go and propose a way of extracting summary information on played moves. We then apply several basic data-mining methods on the summary information to identify the most differentiating features within the summary information, and discuss their correspondence with traditional Go knowledge. We show statistically significant mappings of the features to player attributes such as playing strength or informally perceived \"playing style\" (e.g. territoriality or aggressivity), describe accurate classifiers for these attributes, and propose applications including seeding real-work ranks of internet players, aiding in Go study and tuning of Go-playing programs, or contribution to Go-theoretical discussion on the scope of \"playing style\".", "source": "arxiv/ml"}
{"id": "arxiv:2186", "title": "Towards Ultrahigh Dimensional Feature Selection for Big Data", "text": "In this paper, we present a new adaptive feature scaling scheme for ultrahigh-dimensional feature selection on Big Data. To solve this problem effectively, we first reformulate it as a convex semi-infinite programming (SIP) problem and then propose an efficient \\emph{feature generating paradigm}. In contrast with traditional gradient-based approaches that conduct optimization on all input features, the proposed method iteratively activates a group of features and solves a sequence of multiple kernel learning (MKL) subproblems of much reduced scale. To further speed up the training, we propose to solve the MKL subproblems in their primal forms through a modified accelerated proximal gradient approach. Due to such an optimization scheme, some efficient cache techniques are also developed. The feature generating paradigm can guarantee that the solution converges globally under mild conditions and achieve lower feature selection bias. Moreover, the proposed method can tackle two challenging tasks in feature selection: 1) group-based feature selection with complex structures and 2) nonlinear feature selection with explicit feature mappings. Comprehensive experiments on a wide range of synthetic and real-world datasets containing tens of million data points with $O(10^{14})$ features demonstrate the competitive performance of the proposed method over state-of-the-art feature selection methods in terms of generalization performance and training efficiency.", "source": "arxiv/ml"}
{"id": "arxiv:2187", "title": "BPRS: Belief Propagation Based Iterative Recommender System", "text": "In this paper we introduce the first application of the Belief Propagation (BP) algorithm in the design of recommender systems. We formulate the recommendation problem as an inference problem and aim to compute the marginal probability distributions of the variables which represent the ratings to be predicted. However, computing these marginal probability functions is computationally prohibitive for large-scale systems. Therefore, we utilize the BP algorithm to efficiently compute these functions. Recommendations for each active user are then iteratively computed by probabilistic message passing. As opposed to the previous recommender algorithms, BPRS does not require solving the recommendation problem for all the users if it wishes to update the recommendations for only a single active. Further, BPRS computes the recommendations for each user with linear complexity and without requiring a training period. Via computer simulations (using the 100K MovieLens dataset), we verify that BPRS iteratively reduces the error in the predicted ratings of the users until it converges. Finally, we confirm that BPRS is comparable to the state of art methods such as Correlation-based neighborhood model (CorNgbr) and Singular Value Decomposition (SVD) in terms of rating and precision accuracy. Therefore, we believe that the BP-based recommendation algorithm is a new promising approach which offers a significant advantage on scalability while providing competitive accuracy for the recommender systems.", "source": "arxiv/ml"}
{"id": "arxiv:2188", "title": "Learning Topic Models and Latent Bayesian Networks Under Expansion Constraints", "text": "Unsupervised estimation of latent variable models is a fundamental problem central to numerous applications of machine learning and statistics. This work presents a principled approach for estimating broad classes of such models, including probabilistic topic models and latent linear Bayesian networks, using only second-order observed moments. The sufficient conditions for identifiability of these models are primarily based on weak expansion constraints on the topic-word matrix, for topic models, and on the directed acyclic graph, for Bayesian networks. Because no assumptions are made on the distribution among the latent variables, the approach can handle arbitrary correlations among the topics or latent factors. In addition, a tractable learning method via $\\ell_1$ optimization is proposed and studied in numerical experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2189", "title": "Minimizing inter-subject variability in fNIRS based Brain Computer Interfaces via multiple-kernel support vector learning", "text": "Brain signal variability in the measurements obtained from different subjects during different sessions significantly deteriorates the accuracy of most brain-computer interface (BCI) systems. Moreover these variabilities, also known as inter-subject or inter-session variabilities, require lengthy calibration sessions before the BCI system can be used. Furthermore, the calibration session has to be repeated for each subject independently and before use of the BCI due to the inter-session variability. In this study, we present an algorithm in order to minimize the above-mentioned variabilities and to overcome the time-consuming and usually error-prone calibration time. Our algorithm is based on linear programming support-vector machines and their extensions to a multiple kernel learning framework. We tackle the inter-subject or -session variability in the feature spaces of the classifiers. This is done by incorporating each subject- or session-specific feature spaces into much richer feature spaces with a set of optimal decision boundaries. Each decision boundary represents the subject- or a session specific spatio-temporal variabilities of neural signals. Consequently, a single classifier with multiple feature spaces will generalize well to new unseen test patterns even without the calibration steps. We demonstrate that classifiers maintain good performances even under the presence of a large degree of BCI variability. The present study analyzes BCI variability related to oxy-hemoglobin neural signals measured using a functional near-infrared spectroscopy.", "source": "arxiv/ml"}
{"id": "arxiv:2190", "title": "Optimal Weighting of Multi-View Data with Low Dimensional Hidden States", "text": "In Natural Language Processing (NLP) tasks, data often has the following two properties: First, data can be chopped into multi-views which has been successfully used for dimension reduction purposes. For example, in topic classification, every paper can be chopped into the title, the main text and the references. However, it is common that some of the views are less noisier than other views for supervised learning problems. Second, unlabeled data are easy to obtain while labeled data are relatively rare. For example, articles occurred on New York Times in recent 10 years are easy to grab but having them classified as 'Politics', 'Finance' or 'Sports' need human labor. Hence less noisy features are preferred before running supervised learning methods. In this paper we propose an unsupervised algorithm which optimally weights features from different views when these views are generated from a low dimensional hidden state, which occurs in widely used models like Mixture Gaussian Model, Hidden Markov Model (HMM) and Latent Dirichlet Allocation (LDA).", "source": "arxiv/ml"}
{"id": "arxiv:2191", "title": "Towards a learning-theoretic analysis of spike-timing dependent plasticity", "text": "This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to theoretical analysis. We show that the selectron encodes reward estimates into spikes and that an error bound on spikes is controlled by a spiking margin and the sum of synaptic weights. Moreover, the efficacy of spikes (their usefulness to other reward maximizing selectrons) also depends on total synaptic strength. Finally, based on our analysis, we propose a regularized version of STDP, and show the regularization improves the robustness of neuronal learning when faced with multiple stimuli.", "source": "arxiv/ml"}
{"id": "arxiv:2192", "title": "Supervised Blockmodelling", "text": "Collective classification models attempt to improve classification performance by taking into account the class labels of related instances. However, they tend not to learn patterns of interactions between classes and/or make the assumption that instances of the same class link to each other (assortativity assumption). Blockmodels provide a solution to these issues, being capable of modelling assortative and disassortative interactions, and learning the pattern of interactions in the form of a summary network. The Supervised Blockmodel provides good classification performance using link structure alone, whilst simultaneously providing an interpretable summary of network interactions to allow a better understanding of the data. This work explores three variants of supervised blockmodels of varying complexity and tests them on four structurally different real world networks.", "source": "arxiv/ml"}
{"id": "arxiv:2193", "title": "Feature selection with test cost constraint", "text": "Feature selection is an important preprocessing step in machine learning and data mining. In real-world applications, costs, including money, time and other resources, are required to acquire the features. In some cases, there is a test cost constraint due to limited resources. We shall deliberately select an informative and cheap feature subset for classification. This paper proposes the feature selection with test cost constraint problem for this issue. The new problem has a simple form while described as a constraint satisfaction problem (CSP). Backtracking is a general algorithm for CSP, and it is efficient in solving the new problem on medium-sized data. As the backtracking algorithm is not scalable to large datasets, a heuristic algorithm is also developed. Experimental results show that the heuristic algorithm can find the optimal solution in most cases. We also redefine some existing feature selection problems in rough sets, especially in decision-theoretic rough sets, from the viewpoint of CSP. These new definitions provide insight to some new research directions.", "source": "arxiv/ml"}
{"id": "arxiv:2194", "title": "Locality-Sensitive Hashing with Margin Based Feature Selection", "text": "We propose a learning method with feature selection for Locality-Sensitive Hashing. Locality-Sensitive Hashing converts feature vectors into bit arrays. These bit arrays can be used to perform similarity searches and personal authentication. The proposed method uses bit arrays longer than those used in the end for similarity and other searches and by learning selects the bits that will be used. We demonstrated this method can effectively perform optimization for cases such as fingerprint images with a large number of labels and extremely few data that share the same labels, as well as verifying that it is also effective for natural images, handwritten digits, and speech features.", "source": "arxiv/ml"}
{"id": "arxiv:2195", "title": "Subset Selection for Gaussian Markov Random Fields", "text": "Given a Gaussian Markov random field, we consider the problem of selecting a subset of variables to observe which minimizes the total expected squared prediction error of the unobserved variables. We first show that finding an exact solution is NP-hard even for a restricted class of Gaussian Markov random fields, called Gaussian free fields, which arise in semi-supervised learning and computer vision. We then give a simple greedy approximation algorithm for Gaussian free fields on arbitrary graphs. Finally, we give a message passing algorithm for general Gaussian Markov random fields on bounded tree-width graphs.", "source": "arxiv/ml"}
{"id": "arxiv:2196", "title": "Bayesian Mixture Models for Frequent Itemset Discovery", "text": "In binary-transaction data-mining, traditional frequent itemset mining often produces results which are not straightforward to interpret. To overcome this problem, probability models are often used to produce more compact and conclusive results, albeit with some loss of accuracy. Bayesian statistics have been widely used in the development of probability models in machine learning in recent years and these methods have many advantages, including their abilities to avoid overfitting. In this paper, we develop two Bayesian mixture models with the Dirichlet distribution prior and the Dirichlet process (DP) prior to improve the previous non-Bayesian mixture model developed for transaction dataset mining. We implement the inference of both mixture models using two methods: a collapsed Gibbs sampling scheme and a variational approximation algorithm. Experiments in several benchmark problems have shown that both mixture models achieve better performance than a non-Bayesian mixture model. The variational algorithm is the faster of the two approaches while the Gibbs sampling method achieves a more accurate results. The Dirichlet process mixture model can automatically grow to a proper complexity for a better approximation. Once the model is built, it can be very fast to query and run analysis on (typically 10 times faster than Eclat, as we will show in the experiment section). However, these approaches also show that mixture models underestimate the probabilities of frequent itemsets. Consequently, these models have a higher sensitivity but a lower specificity.", "source": "arxiv/ml"}
{"id": "arxiv:2197", "title": "The Issue-Adjusted Ideal Point Model", "text": "We develop a model of issue-specific voting behavior. This model can be used to explore lawmakers' personal voting patterns of voting by issue area, providing an exploratory window into how the language of the law is correlated with political support. We derive approximate posterior inference algorithms based on variational methods. Across 12 years of legislative data, we demonstrate both improvement in heldout prediction performance and the model's utility in interpreting an inherently multi-dimensional space.", "source": "arxiv/ml"}
{"id": "arxiv:2198", "title": "Movie Popularity Classification based on Inherent Movie Attributes using C4.5,PART and Correlation Coefficient", "text": "Abundance of movie data across the internet makes it an obvious candidate for machine learning and knowledge discovery. But most researches are directed towards bi-polar classification of movie or generation of a movie recommendation system based on reviews given by viewers on various internet sites. Classification of movie popularity based solely on attributes of a movie i.e. actor, actress, director rating, language, country and budget etc. has been less highlighted due to large number of attributes that are associated with each movie and their differences in dimensions. In this paper, we propose classification scheme of pre-release movie popularity based on inherent attributes using C4.5 and PART classifier algorithm and define the relation between attributes of post release movies using correlation coefficient.", "source": "arxiv/ml"}
{"id": "arxiv:2199", "title": "More Is Better: Large Scale Partially-supervised Sentiment Classification - Appendix", "text": "We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our experiments cover semi-supervised learning, domain adaptation and weakly supervised learning. In some cases our methods were able to reduce test error by more than half using such large amount of data. NOTICE: This is only the supplementary material.", "source": "arxiv/ml"}
{"id": "arxiv:2200", "title": "Sparse Ising Models with Covariates", "text": "There has been a lot of work fitting Ising models to multivariate binary data in order to understand the conditional dependency relationships between the variables. However, additional covariates are frequently recorded together with the binary data, and may influence the dependence relationships. Motivated by such a dataset on genomic instability collected from tumor samples of several types, we propose a sparse covariate dependent Ising model to study both the conditional dependency within the binary data and its relationship with the additional covariates. This results in subject-specific Ising models, where the subject's covariates influence the strength of association between the genes. As in all exploratory data analysis, interpretability of results is important, and we use L1 penalties to induce sparsity in the fitted graphs and in the number of selected covariates. Two algorithms to fit the model are proposed and compared on a set of simulated data, and asymptotic results are established. The results on the tumor dataset and their biological significance are discussed in detail.", "source": "arxiv/ml"}
{"id": "arxiv:2201", "title": "Learning Robust Low-Rank Representations", "text": "In this paper we present a comprehensive framework for learning robust low-rank representations by combining and extending recent ideas for learning fast sparse coding regressors with structured non-convex optimization techniques. This approach connects robust principal component analysis (RPCA) with dictionary learning techniques and allows its approximation via trainable encoders. We propose an efficient feed-forward architecture derived from an optimization algorithm designed to exactly solve robust low dimensional projections. This architecture, in combination with different training objective functions, allows the regressors to be used as online approximants of the exact offline RPCA problem or as RPCA-based neural networks. Simple modifications of these encoders can handle challenging extensions, such as the inclusion of geometric data transformations. We present several examples with real data from image, audio, and video processing. When used to approximate RPCA, our basic implementation shows several orders of magnitude speedup compared to the exact solvers with almost no performance degradation. We show the strength of the inclusion of learning to the RPCA approach on a music source separation application, where the encoders outperform the exact RPCA algorithms, which are already reported to produce state-of-the-art results on a benchmark database. Our preliminary implementation on an iPad shows faster-than-real-time performance with minimal latency.", "source": "arxiv/ml"}
{"id": "arxiv:2202", "title": "A Deterministic Analysis of an Online Convex Mixture of Expert Algorithms", "text": "We analyze an online learning algorithm that adaptively combines outputs of two constituent algorithms (or the experts) running in parallel to model an unknown desired signal. This online learning algorithm is shown to achieve (and in some cases outperform) the mean-square error (MSE) performance of the best constituent algorithm in the mixture in the steady-state. However, the MSE analysis of this algorithm in the literature uses approximations and relies on statistical models on the underlying signals and systems. Hence, such an analysis may not be useful or valid for signals generated by various real life systems that show high degrees of nonstationarity, limit cycles and, in many cases, that are even chaotic. In this paper, we produce results in an individual sequence manner. In particular, we relate the time-accumulated squared estimation error of this online algorithm at any time over any interval to the time accumulated squared estimation error of the optimal convex mixture of the constituent algorithms directly tuned to the underlying signal in a deterministic sense without any statistical assumptions. In this sense, our analysis provides the transient, steady-state and tracking behavior of this algorithm in a strong sense without any approximations in the derivations or statistical assumptions on the underlying signals such that our results are guaranteed to hold. We illustrate the introduced results through examples.", "source": "arxiv/ml"}
{"id": "arxiv:2203", "title": "Partial Gaussian Graphical Model Estimation", "text": "This paper studies the partial estimation of Gaussian graphical models from high-dimensional empirical observations. We derive a convex formulation for this problem using $\\ell_1$-regularized maximum-likelihood estimation, which can be solved via a block coordinate descent algorithm. Statistical estimation performance can be established for our method. The proposed approach has competitive empirical performance compared to existing methods, as demonstrated by various experiments on synthetic and real datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2204", "title": "Gene selection with guided regularized random forest", "text": "The regularized random forest (RRF) was recently proposed for feature selection by building only one ensemble. In RRF the features are evaluated on a part of the training data at each tree node. We derive an upper bound for the number of distinct Gini information gain values in a node, and show that many features can share the same information gain at a node with a small number of instances and a large number of features. Therefore, in a node with a small number of instances, RRF is likely to select a feature not strongly relevant. Here an enhanced RRF, referred to as the guided RRF (GRRF), is proposed. In GRRF, the importance scores from an ordinary random forest (RF) are used to guide the feature selection process in RRF. Experiments on 10 gene data sets show that the accuracy performance of GRRF is, in general, more robust than RRF when their parameters change. GRRF is computationally efficient, can select compact feature subsets, and has competitive accuracy performance, compared to RRF, varSelRF and LASSO logistic regression (with evaluations from an RF classifier). Also, RF applied to the features selected by RRF with the minimal regularization outperforms RF applied to all the features for most of the data sets considered here. Therefore, if accuracy is considered more important than the size of the feature subset, RRF with the minimal regularization may be considered. We use the accuracy performance of RF, a strong classifier, to evaluate feature selection methods, and illustrate that weak classifiers are less capable of capturing the information contained in a feature subset. Both RRF and GRRF were implemented in the \"RRF\" R package available at CRAN, the official R package archive.", "source": "arxiv/ml"}
{"id": "arxiv:2205", "title": "A Complete System for Candidate Polyps Detection in Virtual Colonoscopy", "text": "Computer tomographic colonography, combined with computer-aided detection, is a promising emerging technique for colonic polyp analysis. We present a complete pipeline for polyp detection, starting with a simple colon segmentation technique that enhances polyps, followed by an adaptive-scale candidate polyp delineation and classification based on new texture and geometric features that consider both the information in the candidate polyp location and its immediate surrounding area. The proposed system is tested with ground truth data, including flat and small polyps which are hard to detect even with optical colonoscopy. For polyps larger than 6mm in size we achieve 100% sensitivity with just 0.9 false positives per case, and for polyps larger than 3mm in size we achieve 93% sensitivity with 2.8 false positives per case.", "source": "arxiv/ml"}
{"id": "arxiv:2206", "title": "Scoring and Searching over Bayesian Networks with Causal and Associative Priors", "text": "A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such beliefs correspond to knowledge about the possible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addition, a novel search-operator is proposed to take advantage of such prior knowledge. Experiments show that, using path beliefs improves the learning of the skeleton, as well as the edge directions in the network.", "source": "arxiv/ml"}
{"id": "arxiv:2207", "title": "Iterative Reweighted Minimization Methods for $l_p$ Regularized Unconstrained Nonlinear Programming", "text": "In this paper we study general $l_p$ regularized unconstrained minimization problems. In particular, we derive lower bounds for nonzero entries of first- and second-order stationary points, and hence also of local minimizers of the $l_p$ minimization problems. We extend some existing iterative reweighted $l_1$ (IRL1) and $l_2$ (IRL2) minimization methods to solve these problems and proposed new variants for them in which each subproblem has a closed form solution. Also, we provide a unified convergence analysis for these methods. In addition, we propose a novel Lipschitz continuous $\\epsilon$-approximation to $\\|x\\|^p_p$. Using this result, we develop new IRL1 methods for the $l_p$ minimization problems and showed that any accumulation point of the sequence generated by these methods is a first-order stationary point, provided that the approximation parameter $\\epsilon$ is below a computable threshold value. This is a remarkable result since all existing iterative reweighted minimization methods require that $\\epsilon$ be dynamically updated and approach zero. Our computational results demonstrate that the new IRL1 method is generally more stable than the existing IRL1 methods [21,18] in terms of objective function value and CPU time.", "source": "arxiv/ml"}
{"id": "arxiv:2208", "title": "Optimistic Agents are Asymptotically Optimal", "text": "We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.", "source": "arxiv/ml"}
{"id": "arxiv:2209", "title": "Memory Constraint Online Multitask Classification", "text": "We investigate online kernel algorithms which simultaneously process multiple classification tasks while a fixed constraint is imposed on the size of their active sets. We focus in particular on the design of algorithms that can efficiently deal with problems where the number of tasks is extremely high and the task data are large scale. Two new projection-based algorithms are introduced to efficiently tackle those issues while presenting different trade offs on how the available memory is managed with respect to the prior information about the learning tasks. Theoretically sound budget algorithms are devised by coupling the Randomized Budget Perceptron and the Forgetron algorithms with the multitask kernel. We show how the two seemingly contrasting properties of learning from multiple tasks and keeping a constant memory footprint can be balanced, and how the sharing of the available space among different tasks is automatically taken care of. We propose and discuss new insights on the multitask kernel. Experiments show that online kernel multitask algorithms running on a budget can efficiently tackle real world learning problems involving multiple tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2210", "title": "Inference algorithms for pattern-based CRFs on sequence data", "text": "We consider Conditional Random Fields (CRFs) with pattern-based potentials defined on a chain. In this model the energy of a string (labeling) $x_1...x_n$ is the sum of terms over intervals $[i,j]$ where each term is non-zero only if the substring $x_i...x_j$ equals a prespecified pattern $\\alpha$. Such CRFs can be naturally applied to many sequence tagging problems. We present efficient algorithms for the three standard inference tasks in a CRF, namely computing (i) the partition function, (ii) marginals, and (iii) computing the MAP. Their complexities are respectively $O(n L)$, $O(n L \\ell_{max})$ and $O(n L \\min\\{|D|,\\log (\\ell_{max}+1)\\})$ where $L$ is the combined length of input patterns, $\\ell_{max}$ is the maximum length of a pattern, and $D$ is the input alphabet. This improves on the previous algorithms of (Ye et al., 2009) whose complexities are respectively $O(n L |D|)$, $O(n |\\Gamma| L^2 \\ell_{max}^2)$ and $O(n L |D|)$, where $|\\Gamma|$ is the number of input patterns. In addition, we give an efficient algorithm for sampling. Finally, we consider the case of non-positive weights. (Komodakis & Paragios, 2009) gave an $O(n L)$ algorithm for computing the MAP. We present a modification that has the same worst-case complexity but can beat it in the best case.", "source": "arxiv/ml"}
{"id": "arxiv:2211", "title": "Sparse LMS via Online Linearized Bregman Iteration", "text": "We propose a version of least-mean-square (LMS) algorithm for sparse system identification. Our algorithm called online linearized Bregman iteration (OLBI) is derived from minimizing the cumulative prediction error squared along with an l1-l2 norm regularizer. By systematically treating the non-differentiable regularizer we arrive at a simple two-step iteration. We demonstrate that OLBI is bias free and compare its operation with existing sparse LMS algorithms by rederiving them in the online convex optimization framework. We perform convergence analysis of OLBI for white input signals and derive theoretical expressions for both the steady state and instantaneous mean square deviations (MSD). We demonstrate numerically that OLBI improves the performance of LMS type algorithms for signals generated from sparse tap weights.", "source": "arxiv/ml"}
{"id": "arxiv:2212", "title": "Nonparametric Unsupervised Classification", "text": "Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised classification methods obtain appealing results by the classifiers learned in an unsupervised manner. However, existing methods do not consider the misclassification error of the unsupervised classifiers except unsupervised SVM, so the performance of the unsupervised classifiers is not fully evaluated. In this work, we study the misclassification error of two popular classifiers, i.e. the nearest neighbor classifier (NN) and the plug-in classifier, in the setting of unsupervised classification.", "source": "arxiv/ml"}
{"id": "arxiv:2213", "title": "Local stability and robustness of sparse dictionary learning in the presence of noise", "text": "A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and show that, with high probability, sparse coding admits a local minimum around the reference dictionary generating the signals. Our study takes into account the case of over-complete dictionaries and noisy signals, thus extending previous work limited to noiseless settings and/or under-complete dictionaries. The analysis we conduct is non-asymptotic and makes it possible to understand how the key quantities of the problem, such as the coherence or the level of noise, can scale with respect to the dimension of the signals, the number of atoms, the sparsity and the number of observations.", "source": "arxiv/ml"}
{"id": "arxiv:2214", "title": "Revisiting the Training of Logic Models of Protein Signaling Networks with a Formal Approach based on Answer Set Programming", "text": "A fundamental question in systems biology is the construction and training to data of mathematical models. Logic formalisms have become very popular to model signaling networks because their simplicity allows us to model large systems encompassing hundreds of proteins. An approach to train (Boolean) logic models to high-throughput phospho-proteomics data was recently introduced and solved using optimization heuristics based on stochastic methods. Here we demonstrate how this problem can be solved using Answer Set Programming (ASP), a declarative problem solving paradigm, in which a problem is encoded as a logical program such that its answer sets represent solutions to the problem. ASP has significant improvements over heuristic methods in terms of efficiency and scalability, it guarantees global optimality of solutions as well as provides a complete set of solutions. We illustrate the application of ASP with in silico cases based on realistic networks and data.", "source": "arxiv/ml"}
{"id": "arxiv:2215", "title": "TV-SVM: Total Variation Support Vector Machine for Semi-Supervised Data Classification", "text": "We introduce semi-supervised data classification algorithms based on total variation (TV), Reproducing Kernel Hilbert Space (RKHS), support vector machine (SVM), Cheeger cut, labeled and unlabeled data points. We design binary and multi-class semi-supervised classification algorithms. We compare the TV-based classification algorithms with the related Laplacian-based algorithms, and show that TV classification perform significantly better when the number of labeled data is small.", "source": "arxiv/ml"}
{"id": "arxiv:2216", "title": "Evaluation of linear classifiers on articles containing pharmacokinetic evidence of drug-drug interactions", "text": "Background. Drug-drug interaction (DDI) is a major cause of morbidity and mortality. [...] Biomedical literature mining can aid DDI research by extracting relevant DDI signals from either the published literature or large clinical databases. However, though drug interaction is an ideal area for translational research, the inclusion of literature mining methodologies in DDI workflows is still very preliminary. One area that can benefit from literature mining is the automatic identification of a large number of potential DDIs, whose pharmacological mechanisms and clinical significance can then be studied via in vitro pharmacology and in populo pharmaco-epidemiology. Experiments. We implemented a set of classifiers for identifying published articles relevant to experimental pharmacokinetic DDI evidence. These documents are important for identifying causal mechanisms behind putative drug-drug interactions, an important step in the extraction of large numbers of potential DDIs. We evaluate performance of several linear classifiers on PubMed abstracts, under different feature transformation and dimensionality reduction methods. In addition, we investigate the performance benefits of including various publicly-available named entity recognition features, as well as a set of internally-developed pharmacokinetic dictionaries. Results. We found that several classifiers performed well in distinguishing relevant and irrelevant abstracts. We found that the combination of unigram and bigram textual features gave better performance than unigram features alone, and also that normalization transforms that adjusted for feature frequency and document length improved classification. For some classifiers, such as linear discriminant analysis (LDA), proper dimensionality reduction had a large impact on performance. Finally, the inclusion of NER features and dictionaries was found not to help classification.", "source": "arxiv/ml"}
{"id": "arxiv:2217", "title": "A fast compression-based similarity measure with applications to content-based image retrieval", "text": "Compression-based similarity measures are effectively employed in applications on diverse data types with a basically parameter-free approach. Nevertheless, there are problems in applying these techniques to medium-to-large datasets which have been seldom addressed. This paper proposes a similarity measure based on compression with dictionaries, the Fast Compression Distance (FCD), which reduces the complexity of these methods, without degradations in performance. On its basis a content-based color image retrieval system is defined, which can be compared to state-of-the-art methods based on invariant color features. Through the FCD a better understanding of compression-based techniques is achieved, by performing experiments on datasets which are larger than the ones analyzed so far in literature.", "source": "arxiv/ml"}
{"id": "arxiv:2218", "title": "Graph-Based Approaches to Clustering Network-Constrained Trajectory Data", "text": "Even though clustering trajectory data attracted considerable attention in the last few years, most of prior work assumed that moving objects can move freely in an euclidean space and did not consider the eventual presence of an underlying road network and its influence on evaluating the similarity between trajectories. In this paper, we present two approaches to clustering network-constrained trajectory data. The first approach discovers clusters of trajectories that traveled along the same parts of the road network. The second approach is segment-oriented and aims to group together road segments based on trajectories that they have in common. Both approaches use a graph model to depict the interactions between observations w.r.t. their similarity and cluster this similarity graph using a community detection algorithm. We also present experimental results obtained on synthetic data to showcase our propositions.", "source": "arxiv/ml"}
{"id": "arxiv:2219", "title": "Distributed High Dimensional Information Theoretical Image Registration via Random Projections", "text": "Information theoretical measures, such as entropy, mutual information, and various divergences, exhibit robust characteristics in image registration applications. However, the estimation of these quantities is computationally intensive in high dimensions. On the other hand, consistent estimation from pairwise distances of the sample points is possible, which suits random projection (RP) based low dimensional embeddings. We adapt the RP technique to this task by means of a simple ensemble method. To the best of our knowledge, this is the first distributed, RP based information theoretical image registration approach. The efficiency of the method is demonstrated through numerical examples.", "source": "arxiv/ml"}
{"id": "arxiv:2220", "title": "Learning mixtures of structured distributions over discrete domains", "text": "Let $\\mathfrak{C}$ be a class of probability distributions over the discrete domain $[n] = \\{1,...,n\\}.$ We show that if $\\mathfrak{C}$ satisfies a rather general condition -- essentially, that each distribution in $\\mathfrak{C}$ can be well-approximated by a variable-width histogram with few bins -- then there is a highly efficient (both in terms of running time and sample complexity) algorithm that can learn any mixture of $k$ unknown distributions from $\\mathfrak{C}.$ We analyze several natural types of distributions over $[n]$, including log-concave, monotone hazard rate and unimodal distributions, and show that they have the required structural property of being well-approximated by a histogram with few bins. Applying our general algorithm, we obtain near-optimally efficient algorithms for all these mixture learning problems.", "source": "arxiv/ml"}
{"id": "arxiv:2221", "title": "Learning from Collective Intelligence in Groups", "text": "Collective intelligence, which aggregates the shared information from large crowds, is often negatively impacted by unreliable information sources with the low quality data. This becomes a barrier to the effective use of collective intelligence in a variety of applications. In order to address this issue, we propose a probabilistic model to jointly assess the reliability of sources and find the true data. We observe that different sources are often not independent of each other. Instead, sources are prone to be mutually influenced, which makes them dependent when sharing information with each other. High dependency between sources makes collective intelligence vulnerable to the overuse of redundant (and possibly incorrect) information from the dependent sources. Thus, we reveal the latent group structure among dependent sources, and aggregate the information at the group level rather than from individual sources directly. This can prevent the collective intelligence from being inappropriately dominated by dependent sources. We will also explicitly reveal the reliability of groups, and minimize the negative impacts of unreliable groups. Experimental results on real-world data sets show the effectiveness of the proposed approach with respect to existing algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2222", "title": "Sensory Anticipation of Optical Flow in Mobile Robotics", "text": "In order to anticipate dangerous events, like a collision, an agent needs to make long-term predictions. However, those are challenging due to uncertainties in internal and external variables and environment dynamics. A sensorimotor model is acquired online by the mobile robot using a state-of-the-art method that learns the optical flow distribution in images, both in space and time. The learnt model is used to anticipate the optical flow up to a given time horizon and to predict an imminent collision by using reinforcement learning. We demonstrate that multi-modal predictions reduce to simpler distributions once actions are taken into account.", "source": "arxiv/ml"}
{"id": "arxiv:2223", "title": "Smooth Sparse Coding via Marginal Regression for Learning Sparse Representations", "text": "We propose and analyze a novel framework for learning sparse representations, based on two statistical techniques: kernel smoothing and marginal regression. The proposed approach provides a flexible framework for incorporating feature similarity or temporal information present in data sets, via non-parametric kernel smoothing. We provide generalization bounds for dictionary learning using smooth sparse coding and show how the sample complexity depends on the L1 norm of kernel function used. Furthermore, we propose using marginal regression for obtaining sparse codes, which significantly improves the speed and allows one to scale to large dictionary sizes easily. We demonstrate the advantages of the proposed approach, both in terms of accuracy and speed by extensive experimentation on several real data sets. In addition, we demonstrate how the proposed approach could be used for improving semi-supervised sparse coding.", "source": "arxiv/ml"}
{"id": "arxiv:2224", "title": "Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization", "text": "The separability assumption (Donoho & Stodden, 2003; Arora et al., 2012) turns non-negative matrix factorization (NMF) into a tractable problem. Recently, a new class of provably-correct NMF algorithms have emerged under this assumption. In this paper, we reformulate the separable NMF problem as that of finding the extreme rays of the conical hull of a finite set of vectors. From this geometric perspective, we derive new separable NMF algorithms that are highly scalable and empirically noise robust, and have several other favorable properties in relation to existing methods. A parallel implementation of our algorithm demonstrates high scalability on shared- and distributed-memory machines.", "source": "arxiv/ml"}
{"id": "arxiv:2225", "title": "Unfolding Latent Tree Structures using 4th Order Tensors", "text": "Discovering the latent structure from many observed variables is an important yet challenging learning task. Existing approaches for discovering latent structures often require the unknown number of hidden states as an input. In this paper, we propose a quartet based approach which is \\emph{agnostic} to this number. The key contribution is a novel rank characterization of the tensor associated with the marginal distribution of a quartet. This characterization allows us to design a \\emph{nuclear norm} based test for resolving quartet relations. We then use the quartet test as a subroutine in a divide-and-conquer algorithm for recovering the latent tree structure. Under mild conditions, the algorithm is consistent and its error probability decays exponentially with increasing sample size. We demonstrate that the proposed approach compares favorably to alternatives. In a real world stock dataset, it also discovers meaningful groupings of variables, and produces a model that fits the data better.", "source": "arxiv/ml"}
{"id": "arxiv:2226", "title": "Learning Heterogeneous Similarity Measures for Hybrid-Recommendations in Meta-Mining", "text": "The notion of meta-mining has appeared recently and extends the traditional meta-learning in two ways. First it does not learn meta-models that provide support only for the learning algorithm selection task but ones that support the whole data-mining process. In addition it abandons the so called black-box approach to algorithm description followed in meta-learning. Now in addition to the datasets, algorithms also have descriptors, workflows as well. For the latter two these descriptions are semantic, describing properties of the algorithms. With the availability of descriptors both for datasets and data mining workflows the traditional modelling techniques followed in meta-learning, typically based on classification and regression algorithms, are no longer appropriate. Instead we are faced with a problem the nature of which is much more similar to the problems that appear in recommendation systems. The most important meta-mining requirements are that suggestions should use only datasets and workflows descriptors and the cold-start problem, e.g. providing workflow suggestions for new datasets. In this paper we take a different view on the meta-mining modelling problem and treat it as a recommender problem. In order to account for the meta-mining specificities we derive a novel metric-based-learning recommender approach. Our method learns two homogeneous metrics, one in the dataset and one in the workflow space, and a heterogeneous one in the dataset-workflow space. All learned metrics reflect similarities established from the dataset-workflow preference matrix. We demonstrate our method on meta-mining over biological (microarray datasets) problems. The application of our method is not limited to the meta-mining problem, its formulations is general enough so that it can be applied on problems with similar requirements.", "source": "arxiv/ml"}
{"id": "arxiv:2227", "title": "A Scalable CUR Matrix Decomposition Algorithm: Lower Time Complexity and Tighter Bound", "text": "The CUR matrix decomposition is an important extension of Nystr\\\"{o}m approximation to a general matrix. It approximates any data matrix in terms of a small number of its columns and rows. In this paper we propose a novel randomized CUR algorithm with an expected relative-error bound. The proposed algorithm has the advantages over the existing relative-error CUR algorithms that it possesses tighter theoretical bound and lower time complexity, and that it can avoid maintaining the whole data matrix in main memory. Finally, experiments on several real-world datasets demonstrate significant improvement over the existing relative-error algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2228", "title": "Bayesian Inference with Posterior Regularization and applications to Infinite Latent SVMs", "text": "Existing Bayesian models, especially nonparametric Bayesian methods, rely on specially conceived priors to incorporate domain knowledge for discovering improved latent representations. While priors can affect posterior distributions through Bayes' rule, imposing posterior regularization is arguably more direct and in some cases more natural and general. In this paper, we present regularized Bayesian inference (RegBayes), a novel computational framework that performs posterior inference with a regularization term on the desired post-data posterior distribution under an information theoretical formulation. RegBayes is more flexible than the procedure that elicits expert knowledge via priors, and it covers both directed Bayesian networks and undirected Markov networks whose Bayesian formulation results in hybrid chain graph models. When the regularization is induced from a linear operator on the posterior distributions, such as the expectation operator, we present a general convex-analysis theorem to characterize the solution of RegBayes. Furthermore, we present two concrete examples of RegBayes, infinite latent support vector machines (iLSVM) and multi-task infinite latent support vector machines (MT-iLSVM), which explore the large-margin idea in combination with a nonparametric Bayesian model for discovering predictive latent features for classification and multi-task learning, respectively. We present efficient inference methods and report empirical studies on several benchmark datasets, which appear to demonstrate the merits inherited from both large-margin learning and Bayesian nonparametrics. Such results were not available until now, and contribute to push forward the interface between these two important subfields, which have been largely treated as isolated in the community.", "source": "arxiv/ml"}
{"id": "arxiv:2229", "title": "Information fusion in multi-task Gaussian processes", "text": "This paper evaluates heterogeneous information fusion using multi-task Gaussian processes in the context of geological resource modeling. Specifically, it empirically demonstrates that information integration across heterogeneous information sources leads to superior estimates of all the quantities being modeled, compared to modeling them individually. Multi-task Gaussian processes provide a powerful approach for simultaneous modeling of multiple quantities of interest while taking correlations between these quantities into consideration. Experiments are performed on large scale real sensor data.", "source": "arxiv/ml"}
{"id": "arxiv:2230", "title": "Feature Selection via L1-Penalized Squared-Loss Mutual Information", "text": "Feature selection is a technique to screen out less important features. Many existing supervised feature selection algorithms use redundancy and relevancy as the main criteria to select features. However, feature interaction, potentially a key characteristic in real-world problems, has not received much attention. As an attempt to take feature interaction into account, we propose L1-LSMI, an L1-regularization based algorithm that maximizes a squared-loss variant of mutual information between selected features and outputs. Numerical results show that L1-LSMI performs well in handling redundancy, detecting non-linear dependency, and considering feature interaction.", "source": "arxiv/ml"}
{"id": "arxiv:2231", "title": "Anomalous Vacillatory Learning", "text": "In 1986, Osherson, Stob and Weinstein asked whether two variants of anomalous vacillatory learning, TxtFex^*_* and TxtFext^*_*, could be distinguished. In both, a machine is permitted to vacillate between a finite number of hypotheses and to make a finite number of errors. TxtFext^*_*-learning requires that hypotheses output infinitely often must describe the same finite variant of the correct set, while TxtFex^*_*-learning permits the learner to vacillate between finitely many different finite variants of the correct set. In this paper we show that TxtFex^*_* \\neq TxtFext^*_*, thereby answering the question posed by Osherson, \\textit{et al}. We prove this in a strong way by exhibiting a family in TxtFex^*_2 \\setminus {TxtFext}^*_*.", "source": "arxiv/ml"}
{"id": "arxiv:2232", "title": "Privacy Aware Learning", "text": "We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as measured by convergence rate, of any statistical estimator or learning procedure.", "source": "arxiv/ml"}
{"id": "arxiv:2233", "title": "Semisupervised Classifier Evaluation and Recalibration", "text": "How many labeled examples are needed to estimate a classifier's performance on a new dataset? We study the case where data is plentiful, but labels are expensive. We show that by making a few reasonable assumptions on the structure of the data, it is possible to estimate performance curves, with confidence bounds, using a small number of ground truth labels. Our approach, which we call Semisupervised Performance Evaluation (SPE), is based on a generative model for the classifier's confidence scores. In addition to estimating the performance of classifiers on new datasets, SPE can be used to recalibrate a classifier by re-estimating the class-conditional confidence distributions.", "source": "arxiv/ml"}
{"id": "arxiv:2234", "title": "ET-LDA: Joint Topic Modeling For Aligning, Analyzing and Sensemaking of Public Events and Their Twitter Feeds", "text": "Social media channels such as Twitter have emerged as popular platforms for crowds to respond to public events such as speeches, sports and debates. While this promises tremendous opportunities to understand and make sense of the reception of an event from the social media, the promises come entwined with significant technical challenges. In particular, given an event and an associated large scale collection of tweets, we need approaches to effectively align tweets and the parts of the event they refer to. This in turn raises questions about how to segment the event into smaller yet meaningful parts, and how to figure out whether a tweet is a general one about the entire event or specific one aimed at a particular segment of the event. In this work, we present ET-LDA, an effective method for aligning an event and its tweets through joint statistical modeling of topical influences from the events and their associated tweets. The model enables the automatic segmentation of the events and the characterization of tweets into two categories: (1) episodic tweets that respond specifically to the content in the segments of the events, and (2) steady tweets that respond generally about the events. We present an efficient inference method for this model, and a comprehensive evaluation of its effectiveness over existing methods. In particular, through a user study, we demonstrate that users find the topics, the segments, the alignment, and the episodic tweets discovered by ET-LDA to be of higher quality and more interesting as compared to the state-of-the-art, with improvements in the range of 18-41%.", "source": "arxiv/ml"}
{"id": "arxiv:2235", "title": "Fast Online EM for Big Topic Modeling", "text": "The expectation-maximization (EM) algorithm can compute the maximum-likelihood (ML) or maximum a posterior (MAP) point estimate of the mixture models or latent variable models such as latent Dirichlet allocation (LDA), which has been one of the most popular probabilistic topic modeling methods in the past decade. However, batch EM has high time and space complexities to learn big LDA models from big data streams. In this paper, we present a fast online EM (FOEM) algorithm that infers the topic distribution from the previously unseen documents incrementally with constant memory requirements. Within the stochastic approximation framework, we show that FOEM can converge to the local stationary point of the LDA's likelihood function. By dynamic scheduling for the fast speed and parameter streaming for the low memory usage, FOEM is more efficient for some lifelong topic modeling tasks than the state-of-the-art online LDA algorithms to handle both big data and big models (aka, big topic modeling) on just a PC.", "source": "arxiv/ml"}
{"id": "arxiv:2236", "title": "A Fast Distributed Proximal-Gradient Method", "text": "We present a distributed proximal-gradient method for optimizing the average of convex functions, each of which is the private local objective of an agent in a network with time-varying topology. The local objectives have distinct differentiable components, but they share a common nondifferentiable component, which has a favorable structure suitable for effective computation of the proximal operator. In our method, each agent iteratively updates its estimate of the global minimum by optimizing its local objective function, and exchanging estimates with others via communication in the network. Using Nesterov-type acceleration techniques and multiple communication steps per iteration, we show that this method converges at the rate 1/k (where k is the number of communication rounds between the agents), which is faster than the convergence rate of the existing distributed methods for solving this problem. The superior convergence rate of our method is also verified by numerical experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2237", "title": "Blending Learning and Inference in Structured Prediction", "text": "In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional approaches, such as conditional random fields and structured support vector machines. For this purpose we utilize the structures of the predictors to describe a low dimensional structured prediction task which encourages local consistencies within the different structures while learning the parameters of the model. Convexity of the learning task provides the means to enforce the consistencies between the different parts. The inference-learning blending algorithm that we propose is guaranteed to converge to the optimum of the low dimensional primal and dual programs. Unlike many of the existing approaches, the inference-learning blending allows us to learn efficiently high-order graphical models, over regions of any size, and very large number of parameters. We demonstrate the effectiveness of our approach, while presenting state-of-the-art results in stereo estimation, semantic segmentation, shape reconstruction, and indoor scene understanding.", "source": "arxiv/ml"}
{"id": "arxiv:2238", "title": "The Power of Linear Reconstruction Attacks", "text": "We consider the power of linear reconstruction attacks in statistical data privacy, showing that they can be applied to a much wider range of settings than previously understood. Linear attacks have been studied before (Dinur and Nissim PODS'03, Dwork, McSherry and Talwar STOC'07, Kasiviswanathan, Rudelson, Smith and Ullman STOC'10, De TCC'12, Muthukrishnan and Nikolov STOC'12) but have so far been applied only in settings with releases that are obviously linear. Consider a database curator who manages a database of sensitive information but wants to release statistics about how a sensitive attribute (say, disease) in the database relates to some nonsensitive attributes (e.g., postal code, age, gender, etc). We show one can mount linear reconstruction attacks based on any release that gives: a) the fraction of records that satisfy a given non-degenerate boolean function. Such releases include contingency tables (previously studied by Kasiviswanathan et al., STOC'10) as well as more complex outputs like the error rate of classifiers such as decision trees; b) any one of a large class of M-estimators (that is, the output of empirical risk minimization algorithms), including the standard estimators for linear and logistic regression. We make two contributions: first, we show how these types of releases can be transformed into a linear format, making them amenable to existing polynomial-time reconstruction algorithms. This is already perhaps surprising, since many of the above releases (like M-estimators) are obtained by solving highly nonlinear formulations. Second, we show how to analyze the resulting attacks under various distributional assumptions on the data. Specifically, we consider a setting in which the same statistic (either a) or b) above) is released about how the sensitive attribute relates to all subsets of size k (out of a total of d) nonsensitive boolean attributes.", "source": "arxiv/ml"}
{"id": "arxiv:2239", "title": "Measuring the Influence of Observations in HMMs through the Kullback-Leibler Distance", "text": "We measure the influence of individual observations on the sequence of the hidden states of the Hidden Markov Model (HMM) by means of the Kullback-Leibler distance (KLD). Namely, we consider the KLD between the conditional distribution of the hidden states' chain given the complete sequence of observations and the conditional distribution of the hidden chain given all the observations but the one under consideration. We introduce a linear complexity algorithm for computing the influence of all the observations. As an illustration, we investigate the application of our algorithm to the problem of detecting outliers in HMM data series.", "source": "arxiv/ml"}
{"id": "arxiv:2240", "title": "Multi-view constrained clustering with an incomplete mapping between views", "text": "Multi-view learning algorithms typically assume a complete bipartite mapping between the different views in order to exchange information during the learning process. However, many applications provide only a partial mapping between the views, creating a challenge for current methods. To address this problem, we propose a multi-view algorithm based on constrained clustering that can operate with an incomplete mapping. Given a set of pairwise constraints in each view, our approach propagates these constraints using a local similarity measure to those instances that can be mapped to the other views, allowing the propagated constraints to be transferred across views via the partial mapping. It uses co-EM to iteratively estimate the propagation within each view based on the current clustering model, transfer the constraints across views, and then update the clustering model. By alternating the learning process between views, this approach produces a unified clustering model that is consistent with all views. We show that this approach significantly improves clustering performance over several other methods for transferring constraints and allows multi-view clustering to be reliably applied when given a limited mapping between the views. Our evaluation reveals that the propagated constraints have high precision with respect to the true clusters in the data, explaining their benefit to clustering performance in both single- and multi-view learning scenarios.", "source": "arxiv/ml"}
{"id": "arxiv:2241", "title": "Cost-Sensitive Tree of Classifiers", "text": "Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e.g. search engines and email spam filters). Here, the CPU cost during test time must be budgeted and accounted for. In this paper, we address the challenge of balancing the test-time cost and the classifier accuracy in a principled fashion. The test-time cost of a classifier is often dominated by the computation required for feature extraction-which can vary drastically across eatures. We decrease this extraction time by constructing a tree of classifiers, through which test inputs traverse along individual paths. Each path extracts different features and is optimized for a specific sub-partition of the input space. By only computing features for inputs that benefit from them the most, our cost sensitive tree of classifiers can match the high accuracies of the current state-of-the-art at a small fraction of the computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:2242", "title": "Learning Onto-Relational Rules with Inductive Logic Programming", "text": "Rules complement and extend ontologies on the Semantic Web. We refer to these rules as onto-relational since they combine DL-based ontology languages and Knowledge Representation formalisms supporting the relational data model within the tradition of Logic Programming and Deductive Databases. Rule authoring is a very demanding Knowledge Engineering task which can be automated though partially by applying Machine Learning algorithms. In this chapter we show how Inductive Logic Programming (ILP), born at the intersection of Machine Learning and Logic Programming and considered as a major approach to Relational Learning, can be adapted to Onto-Relational Learning. For the sake of illustration, we provide details of a specific Onto-Relational Learning solution to the problem of learning rule-based definitions of DL concepts and roles with ILP.", "source": "arxiv/ml"}
{"id": "arxiv:2243", "title": "A Benchmark to Select Data Mining Based Classification Algorithms For Business Intelligence And Decision Support Systems", "text": "DSS serve the management, operations, and planning levels of an organization and help to make decisions, which may be rapidly changing and not easily specified in advance. Data mining has a vital role to extract important information to help in decision making of a decision support system. Integration of data mining and decision support systems (DSS) can lead to the improved performance and can enable the tackling of new types of problems. Artificial Intelligence methods are improving the quality of decision support, and have become embedded in many applications ranges from ant locking automobile brakes to these days interactive search engines. It provides various machine learning techniques to support data mining. The classification is one of the main and valuable tasks of data mining. Several types of classification algorithms have been suggested, tested and compared to determine the future trends based on unseen data. There has been no single algorithm found to be superior over all others for all data sets. The objective of this paper is to compare various classification algorithms that have been frequently used in data mining for decision support systems. Three decision trees based algorithms, one artificial neural network, one statistical, one support vector machines with and without ada boost and one clustering algorithm are tested and compared on four data sets from different domains in terms of predictive accuracy, error rate, classification index, comprehensibility and training time. Experimental results demonstrate that Genetic Algorithm (GA) and support vector machines based algorithms are better in terms of predictive accuracy. SVM without adaboost shall be the first choice in context of speed and predictive accuracy. Adaboost improves the accuracy of SVM but on the cost of large training time.", "source": "arxiv/ml"}
{"id": "arxiv:2244", "title": "Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures", "text": "This paper proposes a technique for the unsupervised detection and tracking of arbitrary objects in videos. It is intended to reduce the need for detection and localization methods tailored to specific object types and serve as a general framework applicable to videos with varied objects, backgrounds, and image qualities. The technique uses a dependent Dirichlet process mixture (DDPM) known as the Generalized Polya Urn (GPUDDPM) to model image pixel data that can be easily and efficiently extracted from the regions in a video that represent objects. This paper describes a specific implementation of the model using spatial and color pixel data extracted via frame differencing and gives two algorithms for performing inference in the model to accomplish detection and tracking. This technique is demonstrated on multiple synthetic and benchmark video datasets that illustrate its ability to, without modification, detect and track objects with diverse physical characteristics moving over non-uniform backgrounds and through occlusion.", "source": "arxiv/ml"}
{"id": "arxiv:2245", "title": "Inferring clonal evolution of tumors from single nucleotide somatic mutations", "text": "High-throughput sequencing allows the detection and quantification of frequencies of somatic single nucleotide variants (SNV) in heterogeneous tumor cell populations. In some cases, the evolutionary history and population frequency of the subclonal lineages of tumor cells present in the sample can be reconstructed from these SNV frequency measurements. However, automated methods to do this reconstruction are not available and the conditions under which reconstruction is possible have not been described. We describe the conditions under which the evolutionary history can be uniquely reconstructed from SNV frequencies from single or multiple samples from the tumor population and we introduce a new statistical model, PhyloSub, that infers the phylogeny and genotype of the major subclonal lineages represented in the population of cancer cells. It uses a Bayesian nonparametric prior over trees that groups SNVs into major subclonal lineages and automatically estimates the number of lineages and their ancestry. We sample from the joint posterior distribution over trees to identify evolutionary histories and cell population frequencies that have the highest probability of generating the observed SNV frequency data. When multiple phylogenies are consistent with a given set of SNV frequencies, PhyloSub represents the uncertainty in the tumor phylogeny using a partial order plot. Experiments on a simulated dataset and two real datasets comprising tumor samples from acute myeloid leukemia and chronic lymphocytic leukemia patients demonstrate that PhyloSub can infer both linear (or chain) and branching lineages and its inferences are in good agreement with ground truth, where it is available.", "source": "arxiv/ml"}
{"id": "arxiv:2246", "title": "Bayesian Analysis for miRNA and mRNA Interactions Using Expression Data", "text": "MicroRNAs (miRNAs) are small RNA molecules composed of 19-22 nt, which play important regulatory roles in post-transcriptional gene regulation by inhibiting the translation of the mRNA into proteins or otherwise cleaving the target mRNA. Inferring miRNA targets provides useful information for understanding the roles of miRNA in biological processes that are potentially involved in complex diseases. Statistical methodologies for point estimation, such as the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm, have been proposed to identify the interactions of miRNA and mRNA based on sequence and expression data. In this paper, we propose using the Bayesian LASSO (BLASSO) and the non-negative Bayesian LASSO (nBLASSO) to analyse the interactions between miRNA and mRNA using expression data. The proposed Bayesian methods explore the posterior distributions for those parameters required to model the miRNA-mRNA interactions. These approaches can be used to observe the inferred effects of the miRNAs on the targets by plotting the posterior distributions of those parameters. For comparison purposes, the Least Squares Regression (LSR), Ridge Regression (RR), LASSO, non-negative LASSO (nLASSO), and the proposed Bayesian approaches were applied to four public datasets. We concluded that nLASSO and nBLASSO perform best in terms of sensitivity and specificity. Compared to the point estimate algorithms, which only provide single estimates for those parameters, the Bayesian methods are more meaningful and provide credible intervals, which take into account the uncertainty of the inferred interactions of the miRNA and mRNA. Furthermore, Bayesian methods naturally provide statistical significance to select convincing inferred interactions, while point estimate algorithms require a manually chosen threshold, which is less meaningful, to choose the possible interactions.", "source": "arxiv/ml"}
{"id": "arxiv:2247", "title": "Learning Attitudes and Attributes from Multi-Aspect Reviews", "text": "The majority of online reviews consist of plain-text feedback together with a single numeric score. However, there are multiple dimensions to products and opinions, and understanding the `aspects' that contribute to users' ratings may help us to better understand their individual preferences. For example, a user's impression of an audiobook presumably depends on aspects such as the story and the narrator, and knowing their opinions on these aspects may help us to recommend better products. In this paper, we build models for rating systems in which such dimensions are explicit, in the sense that users leave separate ratings for each aspect of a product. By introducing new corpora consisting of five million reviews, rated with between three and six aspects, we evaluate our models on three prediction tasks: First, we use our model to uncover which parts of a review discuss which of the rated aspects. Second, we use our model to summarize reviews, which for us means finding the sentences that best explain a user's rating. Finally, since aspect ratings are optional in many of the datasets we consider, we use our model to recover those ratings that are missing from a user's evaluation. Our model matches state-of-the-art approaches on existing small-scale datasets, while scaling to the real-world datasets we introduce. Moreover, our model is able to `disentangle' content and sentiment words: we automatically learn content words that are indicative of a particular aspect as well as the aspect-specific sentiment words that are indicative of a particular rating.", "source": "arxiv/ml"}
{"id": "arxiv:2248", "title": "The Perturbed Variation", "text": "We introduce a new discrepancy score between two distributions that gives an indication on their similarity. While much research has been done to determine if two samples come from exactly the same distribution, much less research considered the problem of determining if two finite samples come from similar distributions. The new score gives an intuitive interpretation of similarity; it optimally perturbs the distributions so that they best fit each other. The score is defined between distributions, and can be efficiently estimated from samples. We provide convergence bounds of the estimated score, and develop hypothesis testing procedures that test if two data sets come from similar distributions. The statistical power of this procedures is presented in simulations. We also compare the score's capacity to detect similarity with that of other known measures on real data.", "source": "arxiv/ml"}
{"id": "arxiv:2249", "title": "Getting Feasible Variable Estimates From Infeasible Ones: MRF Local Polytope Study", "text": "This paper proposes a method for construction of approximate feasible primal solutions from dual ones for large-scale optimization problems possessing certain separability properties. Whereas infeasible primal estimates can typically be produced from (sub-)gradients of the dual function, it is often not easy to project them to the primal feasible set, since the projection itself has a complexity comparable to the complexity of the initial problem. We propose an alternative efficient method to obtain feasibility and show that its properties influencing the convergence to the optimum are similar to the properties of the Euclidean projection. We apply our method to the local polytope relaxation of inference problems for Markov Random Fields and demonstrate its superiority over existing methods.", "source": "arxiv/ml"}
{"id": "arxiv:2250", "title": "The Kernel Pitman-Yor Process", "text": "In this work, we propose the kernel Pitman-Yor process (KPYP) for nonparametric clustering of data with general spatial or temporal interdependencies. The KPYP is constructed by first introducing an infinite sequence of random locations. Then, based on the stick-breaking construction of the Pitman-Yor process, we define a predictor-dependent random probability measure by considering that the discount hyperparameters of the Beta-distributed random weights (stick variables) of the process are not uniform among the weights, but controlled by a kernel function expressing the proximity between the location assigned to each weight and the given predictors.", "source": "arxiv/ml"}
{"id": "arxiv:2251", "title": "Semi-Supervised Classification Through the Bag-of-Paths Group Betweenness", "text": "This paper introduces a novel, well-founded, betweenness measure, called the Bag-of-Paths (BoP) betweenness, as well as its extension, the BoP group betweenness, to tackle semisupervised classification problems on weighted directed graphs. The objective of semi-supervised classification is to assign a label to unlabeled nodes using the whole topology of the graph and the labeled nodes at our disposal. The BoP betweenness relies on a bag-of-paths framework assigning a Boltzmann distribution on the set of all possible paths through the network such that long (high-cost) paths have a low probability of being picked from the bag, while short (low-cost) paths have a high probability of being picked. Within that context, the BoP betweenness of node j is defined as the sum of the a posteriori probabilities that node j lies in-between two arbitrary nodes i, k, when picking a path starting in i and ending in k. Intuitively, a node typically receives a high betweenness if it has a large probability of appearing on paths connecting two arbitrary nodes of the network. This quantity can be computed in closed form by inverting a n x n matrix where n is the number of nodes. For the group betweenness, the paths are constrained to start and end in nodes within the same class, therefore defining a group betweenness for each class. Unlabeled nodes are then classified according to the class showing the highest group betweenness. Experiments on various real-world data sets show that BoP group betweenness outperforms all the tested state of-the-art methods. The benefit of the BoP betweenness is particularly noticeable when only a few labeled nodes are available.", "source": "arxiv/ml"}
{"id": "arxiv:2252", "title": "Hilbert Space Embedding for Dirichlet Process Mixtures", "text": "This paper proposes a Hilbert space embedding for Dirichlet Process mixture models via a stick-breaking construction of Sethuraman. Although Bayesian nonparametrics offers a powerful approach to construct a prior that avoids the need to specify the model size/complexity explicitly, an exact inference is often intractable. On the other hand, frequentist approaches such as kernel machines, which suffer from the model selection/comparison problems, often benefit from efficient learning algorithms. This paper discusses the possibility to combine the best of both worlds by using the Dirichlet Process mixture model as a case study.", "source": "arxiv/ml"}
{"id": "arxiv:2253", "title": "Fast SVM-based Feature Elimination Utilizing Data Radius, Hard-Margin, Soft-Margin", "text": "Margin maximization in the hard-margin sense, proposed as feature elimination criterion by the MFE-LO method, is combined here with data radius utilization to further aim to lower generalization error, as several published bounds and bound-related formulations pertaining to lowering misclassification risk (or error) pertain to radius e.g. product of squared radius and weight vector squared norm. Additionally, we propose additional novel feature elimination criteria that, while instead being in the soft-margin sense, too can utilize data radius, utilizing previously published bound-related formulations for approaching radius for the soft-margin sense, whereby e.g. a focus was on the principle stated therein as \"finding a bound whose minima are in a region with small leave-one-out values may be more important than its tightness\". These additional criteria we propose combine radius utilization with a novel and computationally low-cost soft-margin light classifier retraining approach we devise named QP1; QP1 is the soft-margin alternative to the hard-margin LO. We correct an error in the MFE-LO description, find MFE-LO achieves the highest generalization accuracy among the previously published margin-based feature elimination (MFE) methods, discuss some limitations of MFE-LO, and find our novel methods herein outperform MFE-LO, attain lower test set classification error rate. On several datasets that each both have a large number of features and fall into the `large features few samples' dataset category, and on datasets with lower (low-to-intermediate) number of features, our novel methods give promising results. Especially, among our methods the tunable ones, that do not employ (the non-tunable) LO approach, can be tuned more aggressively in the future than herein, to aim to demonstrate for them even higher performance than herein.", "source": "arxiv/ml"}
{"id": "arxiv:2254", "title": "Epitome for Automatic Image Colorization", "text": "Image colorization adds color to grayscale images. It not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous method in our experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2255", "title": "A Direct Approach to Multi-class Boosting and Extensions", "text": "Boosting methods combine a set of moderately accurate weaklearners to form a highly accurate predictor. Despite the practical importance of multi-class boosting, it has received far less attention than its binary counterpart. In this work, we propose a fully-corrective multi-class boosting formulation which directly solves the multi-class problem without dividing it into multiple binary classification problems. In contrast, most previous multi-class boosting algorithms decompose a multi-boost problem into multiple binary boosting problems. By explicitly deriving the Lagrange dual of the primal optimization problem, we are able to construct a column generation-based fully-corrective approach to boosting which directly optimizes multi-class classification performance. The new approach not only updates all weak learners' coefficients at every iteration, but does so in a manner flexible enough to accommodate various loss functions and regularizations. For example, it enables us to introduce structural sparsity through mixed-norm regularization to promote group sparsity and feature sharing. Boosting with shared features is particularly beneficial in complex prediction problems where features can be expensive to compute. Our experiments on various data sets demonstrate that our direct multi-class boosting generalizes as well as, or better than, a range of competing multi-class boosting methods. The end result is a highly effective and compact ensemble classifier which can be trained in a distributed fashion.", "source": "arxiv/ml"}
{"id": "arxiv:2256", "title": "Mean-Field Learning: a Survey", "text": "In this paper we study iterative procedures for stationary equilibria in games with large number of players. Most of learning algorithms for games with continuous action spaces are limited to strict contraction best reply maps in which the Banach-Picard iteration converges with geometrical convergence rate. When the best reply map is not a contraction, Ishikawa-based learning is proposed. The algorithm is shown to behave well for Lipschitz continuous and pseudo-contractive maps. However, the convergence rate is still unsatisfactory. Several acceleration techniques are presented. We explain how cognitive users can improve the convergence rate based only on few number of measurements. The methodology provides nice properties in mean field games where the payoff function depends only on own-action and the mean of the mean-field (first moment mean-field games). A learning framework that exploits the structure of such games, called, mean-field learning, is proposed. The proposed mean-field learning framework is suitable not only for games but also for non-convex global optimization problems. Then, we introduce mean-field learning without feedback and examine the convergence to equilibria in beauty contest games, which have interesting applications in financial markets. Finally, we provide a fully distributed mean-field learning and its speedup versions for satisfactory solution in wireless networks. We illustrate the convergence rate improvement with numerical examples.", "source": "arxiv/ml"}
{"id": "arxiv:2257", "title": "Regulating the information in spikes: a useful bias", "text": "The bias/variance tradeoff is fundamental to learning: increasing a model's complexity can improve its fit on training data, but potentially worsens performance on future samples. Remarkably, however, the human brain effortlessly handles a wide-range of complex pattern recognition tasks. On the basis of these conflicting observations, it has been argued that useful biases in the form of \"generic mechanisms for representation\" must be hardwired into cortex (Geman et al). This note describes a useful bias that encourages cooperative learning which is both biologically plausible and rigorously justified.", "source": "arxiv/ml"}
{"id": "arxiv:2258", "title": "Scalable Matrix-valued Kernel Learning for High-dimensional Nonlinear Multivariate Regression and Granger Causality", "text": "We propose a general matrix-valued multiple kernel learning framework for high-dimensional nonlinear multivariate regression problems. This framework allows a broad class of mixed norm regularizers, including those that induce sparsity, to be imposed on a dictionary of vector-valued Reproducing Kernel Hilbert Spaces. We develop a highly scalable and eigendecomposition-free algorithm that orchestrates two inexact solvers for simultaneously learning both the input and output components of separable matrix-valued kernels. As a key application enabled by our framework, we show how high-dimensional causal inference tasks can be naturally cast as sparse function estimation problems, leading to novel nonlinear extensions of a class of Graphical Granger Causality techniques. Our algorithmic developments and extensive empirical studies are complemented by theoretical analyses in terms of Rademacher generalization bounds.", "source": "arxiv/ml"}
{"id": "arxiv:2259", "title": "Leveraging Side Observations in Stochastic Bandits", "text": "This paper considers stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms. In this setting, after pulling an arm i, the decision maker also observes the rewards for some other actions related to i. We will see that this model is suited to content recommendation in social networks, where users' reactions may be endorsed or not by their friends. We provide efficient algorithms based on upper confidence bounds (UCBs) to leverage this additional information and derive new bounds improving on standard regret guarantees. We also evaluate these policies in the context of movie recommendation in social networks: experiments on real datasets show substantial learning rate speedups ranging from 2.2x to 14x on dense networks.", "source": "arxiv/ml"}
{"id": "arxiv:2260", "title": "An Efficient Message-Passing Algorithm for the M-Best MAP Problem", "text": "Much effort has been directed at algorithms for obtaining the highest probability configuration in a probabilistic random field model known as the maximum a posteriori (MAP) inference problem. In many situations, one could benefit from having not just a single solution, but the top M most probable solutions known as the M-Best MAP problem. In this paper, we propose an efficient message-passing based algorithm for solving the M-Best MAP problem. Specifically, our algorithm solves the recently proposed Linear Programming (LP) formulation of M-Best MAP [7], while being orders of magnitude faster than a generic LP-solver. Our approach relies on studying a particular partial Lagrangian relaxation of the M-Best MAP LP which exposes a natural combinatorial structure of the problem that we exploit.", "source": "arxiv/ml"}
{"id": "arxiv:2261", "title": "Deterministic MDPs with Adversarial Rewards and Bandit Feedback", "text": "We consider a Markov decision process with deterministic state transition dynamics, adversarially generated rewards that change arbitrarily from round to round, and a bandit feedback model in which the decision maker only observes the rewards it receives. In this setting, we present a novel and efficient online decision making algorithm named MarcoPolo. Under mild assumptions on the structure of the transition dynamics, we prove that MarcoPolo enjoys a regret of O(T^(3/4)sqrt(log(T))) against the best deterministic policy in hindsight. Specifically, our analysis does not rely on the stringent unichain assumption, which dominates much of the previous work on this topic.", "source": "arxiv/ml"}
{"id": "arxiv:2262", "title": "Variational Dual-Tree Framework for Large-Scale Transition Matrix Approximation", "text": "In recent years, non-parametric methods utilizing random walks on graphs have been used to solve a wide range of machine learning problems, but in their simplest form they do not scale well due to the quadratic complexity. In this paper, a new dual-tree based variational approach for approximating the transition matrix and efficiently performing the random walk is proposed. The approach exploits a connection between kernel density estimation, mixture modeling, and random walk on graphs in an optimization of the transition matrix for the data graph that ties together edge transitions probabilities that are similar. Compared to the de facto standard approximation method based on k-nearestneighbors, we demonstrate order of magnitudes speedup without sacrificing accuracy for Label Propagation tasks on benchmark data sets in semi-supervised learning.", "source": "arxiv/ml"}
{"id": "arxiv:2263", "title": "Markov Determinantal Point Processes", "text": "A determinantal point process (DPP) is a random process useful for modeling the combinatorial problem of subset selection. In particular, DPPs encourage a random subset Y to contain a diverse set of items selected from a base set Y. For example, we might use a DPP to display a set of news headlines that are relevant to a user's interests while covering a variety of topics. Suppose, however, that we are asked to sequentially select multiple diverse sets of items, for example, displaying new headlines day-by-day. We might want these sets to be diverse not just individually but also through time, offering headlines today that are unlike the ones shown yesterday. In this paper, we construct a Markov DPP (M-DPP) that models a sequence of random sets {Yt}. The proposed M-DPP defines a stationary process that maintains DPP margins. Crucially, the induced union process Zt = Yt u Yt-1 is also marginally DPP-distributed. Jointly, these properties imply that the sequence of random sets are encouraged to be diverse both at a given time step as well as across time steps. We describe an exact, efficient sampling procedure, and a method for incrementally learning a quality measure over items in the base set Y based on external preferences. We apply the M-DPP to the task of sequentially displaying diverse and relevant news articles to a user with topic preferences.", "source": "arxiv/ml"}
{"id": "arxiv:2264", "title": "Learning to Rank With Bregman Divergences and Monotone Retargeting", "text": "This paper introduces a novel approach for learning to rank (LETOR) based on the notion of monotone retargeting. It involves minimizing a divergence between all monotonic increasing transformations of the training scores and a parameterized prediction function. The minimization is both over the transformations as well as over the parameters. It is applied to Bregman divergences, a large class of \"distance like\" functions that were recently shown to be the unique class that is statistically consistent with the normalized discounted gain (NDCG) criterion [19]. The algorithm uses alternating projection style updates, in which one set of simultaneous projections can be computed independent of the Bregman divergence and the other reduces to parameter estimation of a generalized linear model. This results in easily implemented, efficiently parallelizable algorithm for the LETOR task that enjoys global optimum guarantees under mild conditions. We present empirical results on benchmark datasets showing that this approach can outperform the state of the art NDCG consistent techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2265", "title": "A Slice Sampler for Restricted Hierarchical Beta Process with Applications to Shared Subspace Learning", "text": "Hierarchical beta process has found interesting applications in recent years. In this paper we present a modified hierarchical beta process prior with applications to hierarchical modeling of multiple data sources. The novel use of the prior over a hierarchical factor model allows factors to be shared across different sources. We derive a slice sampler for this model, enabling tractable inference even when the likelihood and the prior over parameters are non-conjugate. This allows the application of the model in much wider contexts without restrictions. We present two different data generative models a linear GaussianGaussian model for real valued data and a linear Poisson-gamma model for count data. Encouraging transfer learning results are shown for two real world applications text modeling and content based image retrieval.", "source": "arxiv/ml"}
{"id": "arxiv:2266", "title": "Exploiting compositionality to explore a large space of model structures", "text": "The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can express a variety of widely used models from unsupervised learning. To enable model selection, we organize these models into a context-free grammar which generates a wide variety of structures through the compositional application of a few simple rules. We use our grammar to generically and efficiently infer latent components and estimate predictive likelihood for nearly 2500 structures using a small toolbox of reusable algorithms. Using a greedy search over our grammar, we automatically choose the decomposition structure from raw data by evaluating only a small fraction of all models. The proposed method typically finds the correct structure for synthetic data and backs off gracefully to simpler models under heavy noise. It learns sensible structures for datasets as diverse as image patches, motion capture, 20 Questions, and U.S. Senate votes, all using exactly the same code.", "source": "arxiv/ml"}
{"id": "arxiv:2267", "title": "Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators", "text": "We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all the annotators. For this scenario, we derive sample complexity bound for the Minimum Disagreement Algorithm (MDA) on the number of labeled examples to be obtained from each annotator. Next, we consider the incomplete information scenario, where each annotator is strategic and holds the respective noise rate as a private information. For this scenario, we design a cost optimal procurement auction mechanism along the lines of Myerson's optimal auction design framework in a non-trivial manner. This mechanism satisfies incentive compatibility property, thereby facilitating the learner to elicit true noise rates of all the annotators.", "source": "arxiv/ml"}
{"id": "arxiv:2268", "title": "Spectral Estimation of Conditional Random Graph Models for Large-Scale Network Data", "text": "Generative models for graphs have been typically committed to strong prior assumptions concerning the form of the modeled distributions. Moreover, the vast majority of currently available models are either only suitable for characterizing some particular network properties (such as degree distribution or clustering coefficient), or they are aimed at estimating joint probability distributions, which is often intractable in large-scale networks. In this paper, we first propose a novel network statistic, based on the Laplacian spectrum of graphs, which allows to dispense with any parametric assumption concerning the modeled network properties. Second, we use the defined statistic to develop the Fiedler random graph model, switching the focus from the estimation of joint probability distributions to a more tractable conditional estimation setting. After analyzing the dependence structure characterizing Fiedler random graphs, we evaluate them experimentally in edge prediction over several real-world networks, showing that they allow to reach a much higher prediction accuracy than various alternative statistical models.", "source": "arxiv/ml"}
{"id": "arxiv:2269", "title": "Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits", "text": "We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches. In addition, our approach allows generating longer histories by careful control of a bias-variance tradeoff, and further decreases variance by incorporating information about randomness of the target policy. Empirical evidence from synthetic and realworld exploration learning problems shows the new evaluator successfully unifies previous approaches and uses information an order of magnitude more efficiently.", "source": "arxiv/ml"}
{"id": "arxiv:2270", "title": "Lifted Relational Variational Inference", "text": "Hybrid continuous-discrete models naturally represent many real-world applications in robotics, finance, and environmental engineering. Inference with large-scale models is challenging because relational structures deteriorate rapidly during inference with observations. The main contribution of this paper is an efficient relational variational inference algorithm that factors largescale probability models into simpler variational models, composed of mixtures of iid (Bernoulli) random variables. The algorithm takes probability relational models of largescale hybrid systems and converts them to a close-to-optimal variational models. Then, it efficiently calculates marginal probabilities on the variational models by using a latent (or lifted) variable elimination or a lifted stochastic sampling. This inference is unique because it maintains the relational structure upon individual observations and during inference steps.", "source": "arxiv/ml"}
{"id": "arxiv:2271", "title": "Response Aware Model-Based Collaborative Filtering", "text": "Previous work on recommender systems mainly focus on fitting the ratings provided by users. However, the response patterns, i.e., some items are rated while others not, are generally ignored. We argue that failing to observe such response patterns can lead to biased parameter estimation and sub-optimal model performance. Although several pieces of work have tried to model users' response patterns, they miss the effectiveness and interpretability of the successful matrix factorization collaborative filtering approaches. To bridge the gap, in this paper, we unify explicit response models and PMF to establish the Response Aware Probabilistic Matrix Factorization (RAPMF) framework. We show that RAPMF subsumes PMF as a special case. Empirically we demonstrate the merits of RAPMF from various aspects.", "source": "arxiv/ml"}
{"id": "arxiv:2272", "title": "Crowdsourcing Control: Moving Beyond Multiple Choice", "text": "To ensure quality results from crowdsourced tasks, requesters often aggregate worker responses and use one of a plethora of strategies to infer the correct answer from the set of noisy responses. However, all current models assume prior knowledge of all possible outcomes of the task. While not an unreasonable assumption for tasks that can be posited as multiple-choice questions (e.g. n-ary classification), we observe that many tasks do not naturally fit this paradigm, but instead demand a free-response formulation where the outcome space is of infinite size (e.g. audio transcription). We model such tasks with a novel probabilistic graphical model, and design and implement LazySusan, a decision-theoretic controller that dynamically requests responses as necessary in order to infer answers to these tasks. We also design an EM algorithm to jointly learn the parameters of our model while inferring the correct answers to multiple tasks at a time. Live experiments on Amazon Mechanical Turk demonstrate the superiority of LazySusan at solving SAT Math questions, eliminating 83.2% of the error and achieving greater net utility compared to the state-ofthe-art strategy, majority-voting. We also show in live experiments that our EM algorithm outperforms majority-voting on a visualization task that we design.", "source": "arxiv/ml"}
{"id": "arxiv:2273", "title": "Learning Mixtures of Submodular Shells with Application to Document Summarization", "text": "We introduce a method to learn a mixture of submodular \"shells\" in a large-margin setting. A submodular shell is an abstract submodular function that can be instantiated with a ground set and a set of parameters to produce a submodular function. A mixture of such shells can then also be so instantiated to produce a more complex submodular function. What our algorithm learns are the mixture weights over such shells. We provide a risk bound guarantee when learning in a large-margin structured-prediction setting using a projected subgradient method when only approximate submodular optimization is possible (such as with submodular function maximization). We apply this method to the problem of multi-document summarization and produce the best results reported so far on the widely used NIST DUC-05 through DUC-07 document summarization corpora.", "source": "arxiv/ml"}
{"id": "arxiv:2274", "title": "Nested Dictionary Learning for Hierarchical Organization of Imagery and Text", "text": "A tree-based dictionary learning model is developed for joint analysis of imagery and associated text. The dictionary learning may be applied directly to the imagery from patches, or to general feature vectors extracted from patches or superpixels (using any existing method for image feature extraction). Each image is associated with a path through the tree (from root to a leaf), and each of the multiple patches in a given image is associated with one node in that path. Nodes near the tree root are shared between multiple paths, representing image characteristics that are common among different types of images. Moving toward the leaves, nodes become specialized, representing details in image classes. If available, words (text) are also jointly modeled, with a path-dependent probability over words. The tree structure is inferred via a nested Dirichlet process, and a retrospective stick-breaking sampler is used to infer the tree depth and width.", "source": "arxiv/ml"}
{"id": "arxiv:2275", "title": "Active Imitation Learning via Reduction to I.I.D. Active Learning", "text": "In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in some cases. In this paper, we consider active imitation learning with the goal of reducing this effort by querying the expert about the desired action at individual states, which are selected based on answers to past queries and the learner's interactions with an environment simulator. We introduce a new approach based on reducing active imitation learning to i.i.d. active learning, which can leverage progress in the i.i.d. setting. Our first contribution, is to analyze reductions for both non-stationary and stationary policies, showing that the label complexity (number of queries) of active imitation learning can be substantially less than passive learning. Our second contribution, is to introduce a practical algorithm inspired by the reductions, which is shown to be highly effective in four test domains compared to a number of alternatives.", "source": "arxiv/ml"}
{"id": "arxiv:2276", "title": "Inferring Strategies from Limited Reconnaissance in Real-time Strategy Games", "text": "In typical real-time strategy (RTS) games, enemy units are visible only when they are within sight range of a friendly unit. Knowledge of an opponent's disposition is limited to what can be observed through scouting. Information is costly, since units dedicated to scouting are unavailable for other purposes, and the enemy will resist scouting attempts. It is important to infer as much as possible about the opponent's current and future strategy from the available observations. We present a dynamic Bayes net model of strategies in the RTS game Starcraft that combines a generative model of how strategies relate to observable quantities with a principled framework for incorporating evidence gained via scouting. We demonstrate the model's ability to infer unobserved aspects of the game from realistic observations.", "source": "arxiv/ml"}
{"id": "arxiv:2277", "title": "Tightening Fractional Covering Upper Bounds on the Partition Function for High-Order Region Graphs", "text": "In this paper we present a new approach for tightening upper bounds on the partition function. Our upper bounds are based on fractional covering bounds on the entropy function, and result in a concave program to compute these bounds and a convex program to tighten them. To solve these programs effectively for general region graphs we utilize the entropy barrier method, thus decomposing the original programs by their dual programs and solve them with dual block optimization scheme. The entropy barrier method provides an elegant framework to generalize the message-passing scheme to high-order region graph, as well as to solve the block dual steps in closed-form. This is a key for computational relevancy for large problems with thousands of regions.", "source": "arxiv/ml"}
{"id": "arxiv:2278", "title": "A Model-Based Approach to Rounding in Spectral Clustering", "text": "In spectral clustering, one defines a similarity matrix for a collection of data points, transforms the matrix to get the Laplacian matrix, finds the eigenvectors of the Laplacian matrix, and obtains a partition of the data using the leading eigenvectors. The last step is sometimes referred to as rounding, where one needs to decide how many leading eigenvectors to use, to determine the number of clusters, and to partition the data points. In this paper, we propose a novel method for rounding. The method differs from previous methods in three ways. First, we relax the assumption that the number of clusters equals the number of eigenvectors used. Second, when deciding the number of leading eigenvectors to use, we not only rely on information contained in the leading eigenvectors themselves, but also use subsequent eigenvectors. Third, our method is model-based and solves all the three subproblems of rounding using a class of graphical models called latent tree models. We evaluate our method on both synthetic and real-world data. The results show that our method works correctly in the ideal case where between-clusters similarity is 0, and degrades gracefully as one moves away from the ideal case.", "source": "arxiv/ml"}
{"id": "arxiv:2279", "title": "A Spectral Algorithm for Latent Junction Trees", "text": "Latent variable models are an elegant framework for capturing rich probabilistic dependencies in many applications. However, current approaches typically parametrize these models using conditional probability tables, and learning relies predominantly on local search heuristics such as Expectation Maximization. Using tensor algebra, we propose an alternative parameterization of latent variable models (where the model structures are junction trees) that still allows for computation of marginals among observed variables. While this novel representation leads to a moderate increase in the number of parameters for junction trees of low treewidth, it lets us design a local-minimum-free algorithm for learning this parameterization. The main computation of the algorithm involves only tensor operations and SVDs which can be orders of magnitude faster than EM algorithms for large datasets. To our knowledge, this is the first provably consistent parameter learning technique for a large class of low-treewidth latent graphical models beyond trees. We demonstrate the advantages of our method on synthetic and real datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2280", "title": "Hilbert Space Embeddings of POMDPs", "text": "A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' rule to these distribution embeddings. Policies and value functions are defined on the feature space over states, which leads to a feature space expression for the Bellman equation. Value iteration may then be used to estimate the optimal value function and associated policy. Experimental results confirm that the correct policy is learned using the feature space representation.", "source": "arxiv/ml"}
{"id": "arxiv:2281", "title": "Local Structure Discovery in Bayesian Networks", "text": "Learning a Bayesian network structure from data is an NP-hard problem and thus exact algorithms are feasible only for small data sets. Therefore, network structures for larger networks are usually learned with various heuristics. Another approach to scaling up the structure learning is local learning. In local learning, the modeler has one or more target variables that are of special interest; he wants to learn the structure near the target variables and is not interested in the rest of the variables. In this paper, we present a score-based local learning algorithm called SLL. We conjecture that our algorithm is theoretically sound in the sense that it is optimal in the limit of large sample size. Empirical results suggest that SLL is competitive when compared to the constraint-based HITON algorithm. We also study the prospects of constructing the network structure for the whole node set based on local results by presenting two algorithms and comparing them to several heuristics.", "source": "arxiv/ml"}
{"id": "arxiv:2282", "title": "Learning STRIPS Operators from Noisy and Incomplete Observations", "text": "Agents learning to act autonomously in real-world domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing approaches cannot learn from noisy, incomplete observations typical of real-world domains. We propose a method which learns STRIPS action models in such domains, by decomposing the problem into first learning a transition function between states in the form of a set of classifiers, and then deriving explicit STRIPS rules from the classifiers' parameters. We evaluate our approach on simulated standard planning domains from the International Planning Competition, and show that it learns useful domain descriptions from noisy, incomplete observations.", "source": "arxiv/ml"}
{"id": "arxiv:2283", "title": "Unsupervised Joint Alignment and Clustering using Bayesian Nonparametrics", "text": "Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the form of the functions or transformations, limiting their generality. We present a transformed Bayesian infinite mixture model that can simultaneously align and cluster a data set. Our model and associated learning scheme offer two key advantages: the optimal number of clusters is determined in a data-driven fashion through the use of a Dirichlet process prior, and it can accommodate any transformation function parameterized by a continuous parameter vector. As a result, it is applicable to a wide range of data types, and transformation functions. We present positive results on synthetic two-dimensional data, on a set of one-dimensional curves, and on various image data sets, showing large improvements over previous work. We discuss several variations of the model and conclude with directions for future work.", "source": "arxiv/ml"}
{"id": "arxiv:2284", "title": "Sparse Q-learning with Mirror Descent", "text": "This paper explores a new framework for reinforcement learning based on online convex optimization, in particular mirror descent and related algorithms. Mirror descent can be viewed as an enhanced gradient method, particularly suited to minimization of convex functions in highdimensional spaces. Unlike traditional gradient methods, mirror descent undertakes gradient updates of weights in both the dual space and primal space, which are linked together using a Legendre transform. Mirror descent can be viewed as a proximal algorithm where the distance generating function used is a Bregman divergence. A new class of proximal-gradient based temporal-difference (TD) methods are presented based on different Bregman divergences, which are more powerful than regular TD learning. Examples of Bregman divergences that are studied include p-norm functions, and Mahalanobis distance based on the covariance of sample gradients. A new family of sparse mirror-descent reinforcement learning methods are proposed, which are able to find sparse fixed points of an l1-regularized Bellman equation at significantly less computational cost than previous methods based on second-order matrix methods. An experimental study of mirror-descent reinforcement learning is presented using discrete and continuous Markov decision processes.", "source": "arxiv/ml"}
{"id": "arxiv:2285", "title": "Closed-Form Learning of Markov Networks from Dependency Networks", "text": "Markov networks (MNs) are a powerful way to compactly represent a joint probability distribution, but most MN structure learning methods are very slow, due to the high cost of evaluating candidates structures. Dependency networks (DNs) represent a probability distribution as a set of conditional probability distributions. DNs are very fast to learn, but the conditional distributions may be inconsistent with each other and few inference algorithms support DNs. In this paper, we present a closed-form method for converting a DN into an MN, allowing us to enjoy both the efficiency of DN learning and the convenience of the MN representation. When the DN is consistent, this conversion is exact. For inconsistent DNs, we present averaging methods that significantly improve the approximation. In experiments on 12 standard datasets, our methods are orders of magnitude faster than and often more accurate than combining conditional distributions using weight learning.", "source": "arxiv/ml"}
{"id": "arxiv:2286", "title": "Value Function Approximation in Noisy Environments Using Locally Smoothed Regularized Approximate Linear Programs", "text": "Recently, Petrik et al. demonstrated that L1Regularized Approximate Linear Programming (RALP) could produce value functions and policies which compared favorably to established linear value function approximation techniques like LSPI. RALP's success primarily stems from the ability to solve the feature selection and value function approximation steps simultaneously. RALP's performance guarantees become looser if sampled next states are used. For very noisy domains, RALP requires an accurate model rather than samples, which can be unrealistic in some practical scenarios. In this paper, we demonstrate this weakness, and then introduce Locally Smoothed L1-Regularized Approximate Linear Programming (LS-RALP). We demonstrate that LS-RALP mitigates inaccuracies stemming from noise even without an accurate model. We show that, given some smoothness assumptions, as the number of samples increases, error from noise approaches zero, and provide experimental examples of LS-RALP's success on common reinforcement learning benchmark problems.", "source": "arxiv/ml"}
{"id": "arxiv:2287", "title": "Fast Exact Inference for Recursive Cardinality Models", "text": "Cardinality potentials are a generally useful class of high order potential that affect probabilities based on how many of D binary variables are active. Maximum a posteriori (MAP) inference for cardinality potential models is well-understood, with efficient computations taking O(DlogD) time. Yet efficient marginalization and sampling have not been addressed as thoroughly in the machine learning community. We show that there exists a simple algorithm for computing marginal probabilities and drawing exact joint samples that runs in O(Dlog2 D) time, and we show how to frame the algorithm as efficient belief propagation in a low order tree-structured model that includes additional auxiliary variables. We then develop a new, more general class of models, termed Recursive Cardinality models, which take advantage of this efficiency. Finally, we show how to do efficient exact inference in models composed of a tree structure and a cardinality potential. We explore the expressive power of Recursive Cardinality models and empirically demonstrate their utility.", "source": "arxiv/ml"}
{"id": "arxiv:2288", "title": "Efficiently Searching for Frustrated Cycles in MAP Inference", "text": "Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large integrality gap, due to frustrated cycles. One way to tighten the relaxation is to introduce additional constraints that explicitly enforce cycle consistency. Earlier work showed that cluster-pursuit algorithms, which iteratively introduce cycle and other higherorder consistency constraints, allows one to exactly solve many hard inference problems. However, these algorithms explicitly enumerate a candidate set of clusters, limiting them to triplets or other short cycles. We solve the search problem for cycle constraints, giving a nearly linear time algorithm for finding the most frustrated cycle of arbitrary length. We show how to use this search algorithm together with the dual decomposition framework and clusterpursuit. The new algorithm exactly solves MAP inference problems arising from relational classification and stereo vision.", "source": "arxiv/ml"}
{"id": "arxiv:2289", "title": "Latent Composite Likelihood Learning for the Structured Canonical Correlation Model", "text": "Latent variable models are used to estimate variables of interest quantities which are observable only up to some measurement error. In many studies, such variables are known but not precisely quantifiable (such as \"job satisfaction\" in social sciences and marketing, \"analytical ability\" in educational testing, or \"inflation\" in economics). This leads to the development of measurement instruments to record noisy indirect evidence for such unobserved variables such as surveys, tests and price indexes. In such problems, there are postulated latent variables and a given measurement model. At the same time, other unantecipated latent variables can add further unmeasured confounding to the observed variables. The problem is how to deal with unantecipated latents variables. In this paper, we provide a method loosely inspired by canonical correlation that makes use of background information concerning the \"known\" latent variables. Given a partially specified structure, it provides a structure learning approach to detect \"unknown unknowns,\" the confounding effect of potentially infinitely many other latent variables. This is done without explicitly modeling such extra latent factors. Because of the special structure of the problem, we are able to exploit a new variation of composite likelihood fitting to efficiently learn this structure. Validation is provided with experiments in synthetic data and the analysis of a large survey done with a sample of over 100,000 staff members of the National Health Service of the United Kingdom.", "source": "arxiv/ml"}
{"id": "arxiv:2290", "title": "Active Learning with Distributional Estimates", "text": "Active Learning (AL) is increasingly important in a broad range of applications. Two main AL principles to obtain accurate classification with few labeled data are refinement of the current decision boundary and exploration of poorly sampled regions. In this paper we derive a novel AL scheme that balances these two principles in a natural way. In contrast to many AL strategies, which are based on an estimated class conditional probability ^p(y|x), a key component of our approach is to view this quantity as a random variable, hence explicitly considering the uncertainty in its estimated value. Our main contribution is a novel mathematical framework for uncertainty-based AL, and a corresponding AL scheme, where the uncertainty in ^p(y|x) is modeled by a second-order distribution. On the practical side, we show how to approximate such second-order distributions for kernel density classification. Finally, we find that over a large number of UCI, USPS and Caltech4 datasets, our AL scheme achieves significantly better learning curves than popular AL methods such as uncertainty sampling and error reduction sampling, when all use the same kernel density classifier.", "source": "arxiv/ml"}
{"id": "arxiv:2291", "title": "New Advances and Theoretical Insights into EDML", "text": "EDML is a recently proposed algorithm for learning MAP parameters in Bayesian networks. In this paper, we present a number of new advances and insights on the EDML algorithm. First, we provide the multivalued extension of EDML, originally proposed for Bayesian networks over binary variables. Next, we identify a simplified characterization of EDML that further implies a simple fixed-point algorithm for the convex optimization problem that underlies it. This characterization further reveals a connection between EDML and EM: a fixed point of EDML is a fixed point of EM, and vice versa. We thus identify also a new characterization of EM fixed points, but in the semantics of EDML. Finally, we propose a hybrid EDML/EM algorithm that takes advantage of the improved empirical convergence behavior of EDML, while maintaining the monotonic improvement property of EM.", "source": "arxiv/ml"}
{"id": "arxiv:2292", "title": "An Improved Admissible Heuristic for Learning Optimal Bayesian Networks", "text": "Recently two search algorithms, A* and breadth-first branch and bound (BFBnB), were developed based on a simple admissible heuristic for learning Bayesian network structures that optimize a scoring function. The heuristic represents a relaxation of the learning problem such that each variable chooses optimal parents independently. As a result, the heuristic may contain many directed cycles and result in a loose bound. This paper introduces an improved admissible heuristic that tries to avoid directed cycles within small groups of variables. A sparse representation is also introduced to store only the unique optimal parent choices. Empirical results show that the new techniques significantly improved the efficiency and scalability of A* and BFBnB on most of datasets tested in this paper.", "source": "arxiv/ml"}
{"id": "arxiv:2293", "title": "Latent Structured Ranking", "text": "Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items are scored independently by their similarity to the query in the latent embedding space. The structure of the ranked list (i.e. considering the set of items returned as a whole) is not taken into account. This can be a problem because the set of top predictions can be either too diverse (contain results that contradict each other) or are not diverse enough. In this paper we introduce a method for learning latent structured rankings that improves over existing methods by providing the right blend of predictions at the top of the ranked list. Particular emphasis is put on making this method scalable. Empirical results on large scale image annotation and music recommendation tasks show improvements over existing approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2294", "title": "Fast Graph Construction Using Auction Algorithm", "text": "In practical machine learning systems, graph based data representation has been widely used in various learning paradigms, ranging from unsupervised clustering to supervised classification. Besides those applications with natural graph or network structure data, such as social network analysis and relational learning, many other applications often involve a critical step in converting data vectors to an adjacency graph. In particular, a sparse subgraph extracted from the original graph is often required due to both theoretic and practical needs. Previous study clearly shows that the performance of different learning algorithms, e.g., clustering and classification, benefits from such sparse subgraphs with balanced node connectivity. However, the existing graph construction methods are either computationally expensive or with unsatisfactory performance. In this paper, we utilize a scalable method called auction algorithm and its parallel extension to recover a sparse yet nearly balanced subgraph with significantly reduced computational cost. Empirical study and comparison with the state-ofart approaches clearly demonstrate the superiority of the proposed method in both efficiency and accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2295", "title": "Dynamic Teaching in Sequential Decision Making Environments", "text": "We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose different policies to teach different parts of the environment. We develop several teaching frameworks based on previously defined supervised protocols, such as Teaching Dimension, extending them to handle noise and sequences of inputs encountered in an MDP.We provide theoretical bounds on the learnability of several important model classes in this setting and suggest a practical algorithm for dynamic teaching.", "source": "arxiv/ml"}
{"id": "arxiv:2296", "title": "Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants", "text": "Understanding the adaptation process of plants to drought stress is essential in improving management practices, breeding strategies as well as engineering viable crops for a sustainable agriculture in the coming decades. Hyper-spectral imaging provides a particularly promising approach to gain such understanding since it allows to discover non-destructively spectral characteristics of plants governed primarily by scattering and absorption characteristics of the leaf internal structure and biochemical constituents. Several drought stress indices have been derived using hyper-spectral imaging. However, they are typically based on few hyper-spectral images only, rely on interpretations of experts, and consider few wavelengths only. In this study, we present the first data-driven approach to discovering spectral drought stress indices, treating it as an unsupervised labeling problem at massive scale. To make use of short range dependencies of spectral wavelengths, we develop an online variational Bayes algorithm for latent Dirichlet allocation with convolved Dirichlet regularizer. This approach scales to massive datasets and, hence, provides a more objective complement to plant physiological practices. The spectral topics found conform to plant physiological knowledge and can be computed in a fraction of the time compared to existing LDA approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2297", "title": "Factorized Multi-Modal Topic Model", "text": "Multi-modal data collections, such as corpora of paired images and text snippets, require analysis methods beyond single-view component and topic models. For continuous observations the current dominant approach is based on extensions of canonical correlation analysis, factorizing the variation into components shared by the different modalities and those private to each of them. For count data, multiple variants of topic models attempting to tie the modalities together have been presented. All of these, however, lack the ability to learn components private to one modality, and consequently will try to force dependencies even between minimally correlating modalities. In this work we combine the two approaches by presenting a novel HDP-based topic model that automatically learns both shared and private topics. The model is shown to be especially useful for querying the contents of one domain given samples of the other.", "source": "arxiv/ml"}
{"id": "arxiv:2298", "title": "Optimal Computational Trade-Off of Inexact Proximal Methods", "text": "In this paper, we investigate the trade-off between convergence rate and computational cost when minimizing a composite functional with proximal-gradient methods, which are popular optimisation tools in machine learning. We consider the case when the proximity operator is computed via an iterative procedure, which provides an approximation of the exact proximity operator. In that case, we obtain algorithms with two nested loops. We show that the strategy that minimizes the computational cost to reach a solution with a desired accuracy in finite time is to set the number of inner iterations to a constant, which differs from the strategy indicated by a convergence rate analysis. In the process, we also present a new procedure called SIP (that is Speedy Inexact Proximal-gradient algorithm) that is both computationally efficient and easy to implement. Our numerical experiments confirm the theoretical findings and suggest that SIP can be a very competitive alternative to the standard procedure.", "source": "arxiv/ml"}
{"id": "arxiv:2299", "title": "A Novel Learning Algorithm for Bayesian Network and Its Efficient Implementation on GPU", "text": "Computational inference of causal relationships underlying complex networks, such as gene-regulatory pathways, is NP-complete due to its combinatorial nature when permuting all possible interactions. Markov chain Monte Carlo (MCMC) has been introduced to sample only part of the combinations while still guaranteeing convergence and traversability, which therefore becomes widely used. However, MCMC is not able to perform efficiently enough for networks that have more than 15~20 nodes because of the computational complexity. In this paper, we use general purpose processor (GPP) and general purpose graphics processing unit (GPGPU) to implement and accelerate a novel Bayesian network learning algorithm. With a hash-table-based memory-saving strategy and a novel task assigning strategy, we achieve a 10-fold acceleration per iteration than using a serial GPP. Specially, we use a greedy method to search for the best graph from a given order. We incorporate a prior component in the current scoring function, which further facilitates the searching. Overall, we are able to apply this system to networks with more than 60 nodes, allowing inferences and modeling of bigger and more complex networks than current methods.", "source": "arxiv/ml"}
{"id": "arxiv:2300", "title": "LSBN: A Large-Scale Bayesian Structure Learning Framework for Model Averaging", "text": "The motivation for this paper is to apply Bayesian structure learning using Model Averaging in large-scale networks. Currently, Bayesian model averaging algorithm is applicable to networks with only tens of variables, restrained by its super-exponential complexity. We present a novel framework, called LSBN(Large-Scale Bayesian Network), making it possible to handle networks with infinite size by following the principle of divide-and-conquer. The method of LSBN comprises three steps. In general, LSBN first performs the partition by using a second-order partition strategy, which achieves more robust results. LSBN conducts sampling and structure learning within each overlapping community after the community is isolated from other variables by Markov Blanket. Finally LSBN employs an efficient algorithm, to merge structures of overlapping communities into a whole. In comparison with other four state-of-art large-scale network structure learning algorithms such as ARACNE, PC, Greedy Search and MMHC, LSBN shows comparable results in five common benchmark datasets, evaluated by precision, recall and f-score. What's more, LSBN makes it possible to learn large-scale Bayesian structure by Model Averaging which used to be intractable. In summary, LSBN provides an scalable and parallel framework for the reconstruction of network structures. Besides, the complete information of overlapping communities serves as the byproduct, which could be used to mine meaningful clusters in biological networks, such as protein-protein-interaction network or gene regulatory network, as well as in social network.", "source": "arxiv/ml"}
{"id": "arxiv:2301", "title": "Matrix reconstruction with the local max norm", "text": "We introduce a new family of matrix norms, the \"local max\" norms, generalizing existing methods such as the max norm, the trace norm (nuclear norm), and the weighted or smoothed weighted trace norms, which have been extensively used in the literature as regularizers for matrix reconstruction problems. We show that this new family can be used to interpolate between the (weighted or unweighted) trace norm and the more conservative max norm. We test this interpolation on simulated data and on the large-scale Netflix and MovieLens ratings data, and find improved accuracy relative to the existing matrix norms. We also provide theoretical results showing learning guarantees for some of the new norms.", "source": "arxiv/ml"}
{"id": "arxiv:2302", "title": "The performance of orthogonal multi-matching pursuit under RIP", "text": "The orthogonal multi-matching pursuit (OMMP) is a natural extension of orthogonal matching pursuit (OMP). We denote the OMMP with the parameter $M$ as OMMP(M) where $M\\geq 1$ is an integer. The main difference between OMP and OMMP(M) is that OMMP(M) selects $M$ atoms per iteration, while OMP only adds one atom to the optimal atom set. In this paper, we study the performance of orthogonal multi-matching pursuit (OMMP) under RIP. In particular, we show that, when the measurement matrix A satisfies $(9s, 1/10)$-RIP, there exists an absolutely constant $M_0\\leq 8$ so that OMMP(M_0) can recover $s$-sparse signal within $s$ iterations. We furthermore prove that, for slowly-decaying $s$-sparse signal, OMMP(M) can recover s-sparse signal within $O(\\frac{s}{M})$ iterations for a large class of $M$. In particular, for $M=s^a$ with $a\\in [0,1/2]$, OMMP(M) can recover slowly-decaying $s$-sparse signal within $O(s^{1-a})$ iterations. The result implies that OMMP can reduce the computational complexity heavily.", "source": "arxiv/ml"}
{"id": "arxiv:2303", "title": "Pairwise MRF Calibration by Perturbation of the Bethe Reference Point", "text": "We investigate different ways of generating approximate solutions to the pairwise Markov random field (MRF) selection problem. We focus mainly on the inverse Ising problem, but discuss also the somewhat related inverse Gaussian problem because both types of MRF are suitable for inference tasks with the belief propagation algorithm (BP) under certain conditions. Our approach consists in to take a Bethe mean-field solution obtained with a maximum spanning tree (MST) of pairwise mutual information, referred to as the \\emph{Bethe reference point}, for further perturbation procedures. We consider three different ways following this idea: in the first one, we select and calibrate iteratively the optimal links to be added starting from the Bethe reference point; the second one is based on the observation that the natural gradient can be computed analytically at the Bethe point; in the third one, assuming no local field and using low temperature expansion we develop a dual loop joint model based on a well chosen fundamental cycle basis. We indeed identify a subclass of planar models, which we refer to as \\emph{Bethe-dual graph models}, having possibly many loops, but characterized by a singly connected dual factor graph, for which the partition function and the linear response can be computed exactly in respectively O(N) and $O(N^2)$ operations, thanks to a dual weight propagation (DWP) message passing procedure that we set up. When restricted to this subclass of models, the inverse Ising problem being convex, becomes tractable at any temperature. Experimental tests on various datasets with refined $L_0$ or $L_1$ regularization procedures indicate that these approaches may be competitive and useful alternatives to existing ones.", "source": "arxiv/ml"}
{"id": "arxiv:2304", "title": "Bayesian Estimation for Continuous-Time Sparse Stochastic Processes", "text": "We consider continuous-time sparse stochastic processes from which we have only a finite number of noisy/noiseless samples. Our goal is to estimate the noiseless samples (denoising) and the signal in-between (interpolation problem). By relying on tools from the theory of splines, we derive the joint a priori distribution of the samples and show how this probability density function can be factorized. The factorization enables us to tractably implement the maximum a posteriori and minimum mean-square error (MMSE) criteria as two statistical approaches for estimating the unknowns. We compare the derived statistical methods with well-known techniques for the recovery of sparse signals, such as the $\\ell_1$ norm and Log ($\\ell_1$-$\\ell_0$ relaxation) regularization methods. The simulation results show that, under certain conditions, the performance of the regularization techniques can be very close to that of the MMSE estimator.", "source": "arxiv/ml"}
{"id": "arxiv:2305", "title": "Disentangling Factors of Variation via Generative Entangling", "text": "Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include higher-order interactions among multiple latent variables. Seen from a generative perspective, the multiplicative interactions emulates the entangling of factors of variation. Inference in the model can be seen as disentangling these generative factors. Unlike previous attempts at disentangling latent factors, the proposed model is trained using no supervised information regarding the latent factors. We apply our model to the task of facial expression classification.", "source": "arxiv/ml"}
{"id": "arxiv:2306", "title": "Online Learning in Decentralized Multiuser Resource Sharing Problems", "text": "In this paper, we consider the general scenario of resource sharing in a decentralized system when the resource rewards/qualities are time-varying and unknown to the users, and using the same resource by multiple users leads to reduced quality due to resource sharing. Firstly, we consider a user-independent reward model with no communication between the users, where a user gets feedback about the congestion level in the resource it uses. Secondly, we consider user-specific rewards and allow costly communication between the users. The users have a cooperative goal of achieving the highest system utility. There are multiple obstacles in achieving this goal such as the decentralized nature of the system, unknown resource qualities, communication, computation and switching costs. We propose distributed learning algorithms with logarithmic regret with respect to the optimal allocation. Our logarithmic regret result holds under both i.i.d. and Markovian reward models, as well as under communication, computation and switching costs.", "source": "arxiv/ml"}
{"id": "arxiv:2307", "title": "Content-boosted Matrix Factorization Techniques for Recommender Systems", "text": "Many businesses are using recommender systems for marketing outreach. Recommendation algorithms can be either based on content or driven by collaborative filtering. We study different ways to incorporate content information directly into the matrix factorization approach of collaborative filtering. These content-boosted matrix factorization algorithms not only improve recommendation accuracy, but also provide useful insights about the contents, as well as make recommendations more easily interpretable.", "source": "arxiv/ml"}
{"id": "arxiv:2308", "title": "Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials", "text": "Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experiments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2309", "title": "Choice of V for V-Fold Cross-Validation in Least-Squares Density Estimation", "text": "This paper studies V-fold cross-validation for model selection in least-squares density estimation. The goal is to provide theoretical grounds for choosing V in order to minimize the least-squares loss of the selected estimator. We first prove a non-asymptotic oracle inequality for V-fold cross-validation and its bias-corrected version (V-fold penalization). In particular, this result implies that V-fold penalization is asymptotically optimal in the nonparametric case. Then, we compute the variance of V-fold cross-validation and related criteria, as well as the variance of key quantities for model selection performance. We show that these variances depend on V like 1+4/(V-1), at least in some particular cases, suggesting that the performance increases much from V=2 to V=5 or 10, and then is almost constant. Overall, this can explain the common advice to take V=5---at least in our setting and when the computational power is limited---, as supported by some simulation experiments. An oracle inequality and exact formulas for the variance are also proved for Monte-Carlo cross-validation, also known as repeated cross-validation, where the parameter V is replaced by the number B of random splits of the data.", "source": "arxiv/ml"}
{"id": "arxiv:2310", "title": "Supervised Learning with Similarity Functions", "text": "We address the problem of general supervised learning when data can only be accessed through an (indefinite) similarity function between data points. Existing work on learning with indefinite kernels has concentrated solely on binary/multi-class classification problems. We propose a model that is generic enough to handle any supervised learning task and also subsumes the model previously proposed for classification. We give a \"goodness\" criterion for similarity functions w.r.t. a given supervised learning task and then adapt a well-known landmarking technique to provide efficient algorithms for supervised learning using \"good\" similarity functions. We demonstrate the effectiveness of our model on three important super-vised learning problems: a) real-valued regression, b) ordinal regression and c) ranking where we show that our method guarantees bounded generalization error. Furthermore, for the case of real-valued regression, we give a natural goodness definition that, when used in conjunction with a recent result in sparse vector recovery, guarantees a sparse predictor with bounded generalization error. Finally, we report results of our learning algorithms on regression and ordinal regression tasks using non-PSD similarity functions and demonstrate the effectiveness of our algorithms, especially that of the sparse landmark selection algorithm that achieves significantly higher accuracies than the baseline methods while offering reduced computational costs.", "source": "arxiv/ml"}
{"id": "arxiv:2311", "title": "Initialization of Self-Organizing Maps: Principal Components Versus Random Initialization. A Case Study", "text": "The performance of the Self-Organizing Map (SOM) algorithm is dependent on the initial weights of the map. The different initialization methods can broadly be classified into random and data analysis based initialization approach. In this paper, the performance of random initialization (RI) approach is compared to that of principal component initialization (PCI) in which the initial map weights are chosen from the space of the principal component. Performance is evaluated by the fraction of variance unexplained (FVU). Datasets were classified into quasi-linear and non-linear and it was observed that RI performed better for non-linear datasets; however the performance of PCI approach remains inconclusive for quasi-linear datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2312", "title": "Reducing statistical time-series problems to binary classification", "text": "We show how binary classification methods developed to work on i.i.d. data can be used for solving statistical problems that are seemingly unrelated to classification and concern highly-dependent time series. Specifically, the problems of time-series clustering, homogeneity testing and the three-sample problem are addressed. The algorithms that we construct for solving these problems are based on a new metric between time-series distributions, which can be evaluated using binary classification methods. Universal consistency of the proposed algorithms is proven under most general assumptions. The theoretical results are illustrated with experiments on synthetic and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:2313", "title": "Fast Exact Max-Kernel Search", "text": "The wide applicability of kernels makes the problem of max-kernel search ubiquitous and more general than the usual similarity search in metric spaces. We focus on solving this problem efficiently. We begin by characterizing the inherent hardness of the max-kernel search problem with a novel notion of directional concentration. Following that, we present a method to use an $O(n \\log n)$ algorithm to index any set of objects (points in $\\Real^\\dims$ or abstract objects) directly in the Hilbert space without any explicit feature representations of the objects in this space. We present the first provably $O(\\log n)$ algorithm for exact max-kernel search using this index. Empirical results for a variety of data sets as well as abstract objects demonstrate up to 4 orders of magnitude speedup in some cases. Extensions for approximate max-kernel search are also presented.", "source": "arxiv/ml"}
{"id": "arxiv:2314", "title": "A density-sensitive hierarchical clustering method", "text": "We define a hierarchical clustering method: $\\alpha$-unchaining single linkage or $SL(\\alpha)$. The input of this algorithm is a finite metric space and a certain parameter $\\alpha$. This method is sensitive to the density of the distribution and offers some solution to the so called chaining effect. We also define a modified version, $SL^*(\\alpha)$, to treat the chaining through points or small blocks. We study the theoretical properties of these methods and offer some theoretical background for the treatment of chaining effects.", "source": "arxiv/ml"}
{"id": "arxiv:2315", "title": "MLPACK: A Scalable C++ Machine Learning Library", "text": "MLPACK is a state-of-the-art, scalable, multi-platform C++ machine learning library released in late 2011 offering both a simple, consistent API accessible to novice users and high performance and flexibility to expert users by leveraging modern features of C++. MLPACK provides cutting-edge algorithms whose benchmarks exhibit far better performance than other leading machine learning libraries. MLPACK version 1.0.3, licensed under the LGPL, is available at http://www.mlpack.org.", "source": "arxiv/ml"}
{"id": "arxiv:2316", "title": "High quality topic extraction from business news explains abnormal financial market volatility", "text": "Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences. In financial economics, the key issue in this regard is understanding and quantifying how news of all possible types (geopolitical, environmental, social, financial, economic, etc.) affect trading and the pricing of firms in organized stock markets. In this article, we seek to address this issue by performing an analysis of more than 24 million news records provided by Thompson Reuters and of their relationship with trading activity for 206 major stocks in the S&P US stock index. We show that the whole landscape of news that affect stock price movements can be automatically summarized via simple regularized regressions between trading activity and news information pieces decomposed, with the help of simple topic modeling techniques, into their \"thematic\" features. Using these methods, we are able to estimate and quantify the impacts of news on trading. We introduce network-based visualization techniques to represent the whole landscape of news information associated with a basket of stocks. The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market. Our results show that one of the most puzzling stylized fact in financial economies, namely that at certain times trading volumes appear to be \"abnormally large,\" can be partially explained by the flow of news. In this sense, our results prove that there is no \"excess trading,\" when restricting to times when news are genuinely novel and provide relevant financial information.", "source": "arxiv/ml"}
{"id": "arxiv:2317", "title": "Topic-Level Opinion Influence Model(TOIM): An Investigation Using Tencent Micro-Blogging", "text": "Mining user opinion from Micro-Blogging has been extensively studied on the most popular social networking sites such as Twitter and Facebook in the U.S., but few studies have been done on Micro-Blogging websites in other countries (e.g. China). In this paper, we analyze the social opinion influence on Tencent, one of the largest Micro-Blogging websites in China, endeavoring to unveil the behavior patterns of Chinese Micro-Blogging users. This paper proposes a Topic-Level Opinion Influence Model (TOIM) that simultaneously incorporates topic factor and social direct influence in a unified probabilistic framework. Based on TOIM, two topic level opinion influence propagation and aggregation algorithms are developed to consider the indirect influence: CP (Conservative Propagation) and NCP (None Conservative Propagation). Users' historical social interaction records are leveraged by TOIM to construct their progressive opinions and neighbors' opinion influence through a statistical learning process, which can be further utilized to predict users' future opinions on some specific topics. To evaluate and test this proposed model, an experiment was designed and a sub-dataset from Tencent Micro-Blogging was used. The experimental results show that TOIM outperforms baseline methods on predicting users' opinion. The applications of CP and NCP have no significant differences and could significantly improve recall and F1-measure of TOIM.", "source": "arxiv/ml"}
{"id": "arxiv:2318", "title": "Neural Networks for Complex Data", "text": "Artificial neural networks are simple and efficient machine learning tools. Defined originally in the traditional setting of simple vector data, neural network models have evolved to address more and more difficulties of complex real world problems, ranging from time evolving data to sophisticated data structures such as graphs and functions. This paper summarizes advances on those themes from the last decade, with a focus on results obtained by members of the SAMM team of Universit\\'e Paris 1", "source": "arxiv/ml"}
{"id": "arxiv:2319", "title": "Clustering hidden Markov models with variational HEM", "text": "The hidden Markov model (HMM) is a widely-used generative model that copes with sequential data, assuming that each observation is conditioned on the state of a hidden Markov chain. In this paper, we derive a novel algorithm to cluster HMMs based on the hierarchical EM (HEM) algorithm. The proposed algorithm i) clusters a given collection of HMMs into groups of HMMs that are similar, in terms of the distributions they represent, and ii) characterizes each group by a \"cluster center\", i.e., a novel HMM that is representative for the group, in a manner that is consistent with the underlying generative model of the HMM. To cope with intractable inference in the E-step, the HEM algorithm is formulated as a variational optimization problem, and efficiently solved for the HMM case by leveraging an appropriate variational approximation. The benefits of the proposed algorithm, which we call variational HEM (VHEM), are demonstrated on several tasks involving time-series data, such as hierarchical clustering of motion capture sequences, and automatic annotation and retrieval of music and of online hand-writing data, showing improvements over current methods. In particular, our variational HEM algorithm effectively leverages large amounts of data when learning annotation models by using an efficient hierarchical estimation procedure, which reduces learning times and memory requirements, while improving model robustness through better regularization.", "source": "arxiv/ml"}
{"id": "arxiv:2320", "title": "Nested Hierarchical Dirichlet Processes", "text": "We develop a nested hierarchical Dirichlet process (nHDP) for hierarchical topic modeling. The nHDP is a generalization of the nested Chinese restaurant process (nCRP) that allows each word to follow its own path to a topic node according to a document-specific distribution on a shared tree. This alleviates the rigid, single-path formulation of the nCRP, allowing a document to more easily express thematic borrowings as a random effect. We derive a stochastic variational inference algorithm for the model, in addition to a greedy subtree selection method for each document, which allows for efficient inference using massive collections of text documents. We demonstrate our algorithm on 1.8 million documents from The New York Times and 3.3 million documents from Wikipedia.", "source": "arxiv/ml"}
{"id": "arxiv:2321", "title": "Structured Sparsity Models for Multiparty Speech Recovery from Reverberant Recordings", "text": "We tackle the multi-party speech recovery problem through modeling the acoustic of the reverberant chambers. Our approach exploits structured sparsity models to perform room modeling and speech recovery. We propose a scheme for characterizing the room acoustic from the unknown competing speech sources relying on localization of the early images of the speakers by sparse approximation of the spatial spectra of the virtual sources in a free-space model. The images are then clustered exploiting the low-rank structure of the spectro-temporal components belonging to each source. This enables us to identify the early support of the room impulse response function and its unique map to the room geometry. To further tackle the ambiguity of the reflection ratios, we propose a novel formulation of the reverberation model and estimate the absorption coefficients through a convex optimization exploiting joint sparsity model formulated upon spatio-spectral sparsity of concurrent speech representation. The acoustic parameters are then incorporated for separating individual speech signals through either structured sparse recovery or inverse filtering the acoustic channels. The experiments conducted on real data recordings demonstrate the effectiveness of the proposed approach for multi-party speech recovery and recognition.", "source": "arxiv/ml"}
{"id": "arxiv:2322", "title": "Predicting Near-Future Churners and Win-Backs in the Telecommunications Industry", "text": "In this work, we presented the strategies and techniques that we have developed for predicting the near-future churners and win-backs for a telecom company. On a large-scale and real-world database containing customer profiles and some transaction data from a telecom company, we first analyzed the data schema, developed feature computation strategies and then extracted a large set of relevant features that can be associated with the customer churning and returning behaviors. Our features include both the original driver factors as well as some derived features. We evaluated our features on the imbalance corrected dataset, i.e. under-sampled dataset and compare a large number of existing machine learning tools, especially decision tree-based classifiers, for predicting the churners and win-backs. In general, we find RandomForest and SimpleCart learning algorithms generally perform well and tend to provide us with highly competitive prediction performance. Among the top-15 driver factors that signal the churn behavior, we find that the service utilization, e.g. last two months' download and upload volume, last three months' average upload and download, and the payment related factors are the most indicative features for predicting if churn will happen soon. Such features can collectively tell discrepancies between the service plans, payments and the dynamically changing utilization needs of the customers. Our proposed features and their computational strategy exhibit reasonable precision performance to predict churn behavior in near future.", "source": "arxiv/ml"}
{"id": "arxiv:2323", "title": "Enhancing the functional content of protein interaction networks", "text": "Protein interaction networks are a promising type of data for studying complex biological systems. However, despite the rich information embedded in these networks, they face important data quality challenges of noise and incompleteness that adversely affect the results obtained from their analysis. Here, we explore the use of the concept of common neighborhood similarity (CNS), which is a form of local structure in networks, to address these issues. Although several CNS measures have been proposed in the literature, an understanding of their relative efficacies for the analysis of interaction networks has been lacking. We follow the framework of graph transformation to convert the given interaction network into a transformed network corresponding to a variety of CNS measures evaluated. The effectiveness of each measure is then estimated by comparing the quality of protein function predictions obtained from its corresponding transformed network with those from the original network. Using a large set of S. cerevisiae interactions, and a set of 136 GO terms, we find that several of the transformed networks produce more accurate predictions than those obtained from the original network. In particular, the $HC.cont$ measure proposed here performs particularly well for this task. Further investigation reveals that the two major factors contributing to this improvement are the abilities of CNS measures, especially $HC.cont$, to prune out noisy edges and introduce new links between functionally related proteins.", "source": "arxiv/ml"}
{"id": "arxiv:2324", "title": "User-level Weibo Recommendation incorporating Social Influence based on Semi-Supervised Algorithm", "text": "Tencent Weibo, as one of the most popular micro-blogging services in China, has attracted millions of users, producing 30-60 millions of weibo (similar as tweet in Twitter) daily. With the overload problem of user generate content, Tencent users find it is more and more hard to browse and find valuable information at the first time. In this paper, we propose a Factor Graph based weibo recommendation algorithm TSI-WR (Topic-Level Social Influence based Weibo Recommendation), which could help Tencent users to find most suitable information. The main innovation is that we consider both direct and indirect social influence from topic level based on social balance theory. The main advantages of adopting this strategy are that it could first build a more accurate description of latent relationship between two users with weak connections, which could help to solve the data sparsity problem; second provide a more accurate recommendation for a certain user from a wider range. Other meaningful contextual information is also combined into our model, which include: Users profile, Users influence, Content of weibos, Topic information of weibos and etc. We also design a semi-supervised algorithm to further reduce the influence of data sparisty. The experiments show that all the selected variables are important and the proposed model outperforms several baseline methods.", "source": "arxiv/ml"}
{"id": "arxiv:2325", "title": "Large-Scale Sparse Principal Component Analysis with Application to Text Data", "text": "Sparse PCA provides a linear combination of small number of features that maximizes variance across data. Although Sparse PCA has apparent advantages compared to PCA, such as better interpretability, it is generally thought to be computationally much more expensive. In this paper, we demonstrate the surprising fact that sparse PCA can be easier than PCA in practice, and that it can be reliably applied to very large data sets. This comes from a rigorous feature elimination pre-processing result, coupled with the favorable fact that features in real-life data typically have exponentially decreasing variances, which allows for many features to be eliminated. We introduce a fast block coordinate ascent algorithm with much better computational complexity than the existing first-order ones. We provide experimental results obtained on text corpora involving millions of documents and hundreds of thousands of features. These results illustrate how Sparse PCA can help organize a large corpus of text data in a user-interpretable way, providing an attractive alternative approach to topic models.", "source": "arxiv/ml"}
{"id": "arxiv:2326", "title": "Selective Transfer Learning for Cross Domain Recommendation", "text": "Collaborative filtering (CF) aims to predict users' ratings on items according to historical user-item preference data. In many real-world applications, preference data are usually sparse, which would make models overfit and fail to give accurate predictions. Recently, several research works show that by transferring knowledge from some manually selected source domains, the data sparseness problem could be mitigated. However for most cases, parts of source domain data are not consistent with the observations in the target domain, which may misguide the target domain model building. In this paper, we propose a novel criterion based on empirical prediction error and its variance to better capture the consistency across domains in CF settings. Consequently, we embed this criterion into a boosting framework to perform selective knowledge transfer. Comparing to several state-of-the-art methods, we show that our proposed selective transfer learning framework can significantly improve the accuracy of rating prediction tasks on several real-world recommendation tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2327", "title": "A Multiscale Framework for Challenging Discrete Optimization", "text": "Current state-of-the-art discrete optimization methods struggle behind when it comes to challenging contrast-enhancing discrete energies (i.e., favoring different labels for neighboring variables). This work suggests a multiscale approach for these challenging problems. Deriving an algebraic representation allows us to coarsen any pair-wise energy using any interpolation in a principled algebraic manner. Furthermore, we propose an energy-aware interpolation operator that efficiently exposes the multiscale landscape of the energy yielding an effective coarse-to-fine optimization scheme. Results on challenging contrast-enhancing energies show significant improvement over state-of-the-art methods.", "source": "arxiv/ml"}
{"id": "arxiv:2328", "title": "Discrete Energy Minimization, beyond Submodularity: Applications and Approximations", "text": "In this thesis I explore challenging discrete energy minimization problems that arise mainly in the context of computer vision tasks. This work motivates the use of such \"hard-to-optimize\" non-submodular functionals, and proposes methods and algorithms to cope with the NP-hardness of their optimization. Consequently, this thesis revolves around two axes: applications and approximations. The applications axis motivates the use of such \"hard-to-optimize\" energies by introducing new tasks. As the energies become less constrained and structured one gains more expressive power for the objective function achieving more accurate models. Results show how challenging, hard-to-optimize, energies are more adequate for certain computer vision applications. To overcome the resulting challenging optimization tasks the second axis of this thesis proposes approximation algorithms to cope with the NP-hardness of the optimization. Experiments show that these new methods yield good results for representative challenging problems.", "source": "arxiv/ml"}
{"id": "arxiv:2329", "title": "Recognizing Static Signs from the Brazilian Sign Language: Comparing Large-Margin Decision Directed Acyclic Graphs, Voting Support Vector Machines and Artificial Neural Networks", "text": "In this paper, we explore and detail our experiments in a high-dimensionality, multi-class image classification problem often found in the automatic recognition of Sign Languages. Here, our efforts are directed towards comparing the characteristics, advantages and drawbacks of creating and training Support Vector Machines disposed in a Directed Acyclic Graph and Artificial Neural Networks to classify signs from the Brazilian Sign Language (LIBRAS). We explore how the different heuristics, hyperparameters and multi-class decision schemes affect the performance, efficiency and ease of use for each classifier. We provide hyperparameter surface maps capturing accuracy and efficiency, comparisons between DDAGs and 1-vs-1 SVMs, and effects of heuristics when training ANNs with Resilient Backpropagation. We report statistically significant results using Cohen's Kappa statistic for contingency tables.", "source": "arxiv/ml"}
{"id": "arxiv:2330", "title": "Tensor decompositions for learning latent variable models", "text": "This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain tensor structure in their low-order observable moments (typically, of second- and third-order). Specifically, parameter estimation is reduced to the problem of extracting a certain (orthogonal) decomposition of a symmetric tensor derived from the moments; this decomposition can be viewed as a natural generalization of the singular value decomposition for matrices. Although tensor decompositions are generally intractable to compute, the decomposition of these specially structured tensors can be efficiently obtained by a variety of approaches, including power iterations and maximization approaches (similar to the case of matrices). A detailed analysis of a robust tensor power method is provided, establishing an analogue of Wedin's perturbation theorem for the singular vectors of matrices. This implies a robust and computationally tractable estimation approach for several popular latent variable models.", "source": "arxiv/ml"}
{"id": "arxiv:2331", "title": "Text Classification with Compression Algorithms", "text": "This work concerns a comparison of SVM kernel methods in text categorization tasks. In particular I define a kernel function that estimates the similarity between two objects computing by their compressed lengths. In fact, compression algorithms can detect arbitrarily long dependencies within the text strings. Data text vectorization looses information in feature extractions and is highly sensitive by textual language. Furthermore, these methods are language independent and require no text preprocessing. Moreover, the accuracy computed on the datasets (Web-KB, 20ng and Reuters-21578), in some case, is greater than Gaussian, linear and polynomial kernels. The method limits are represented by computational time complexity of the Gram matrix and by very poor performance on non-textual datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2332", "title": "Learning in the Model Space for Fault Diagnosis", "text": "The emergence of large scaled sensor networks facilitates the collection of large amounts of real-time data to monitor and control complex engineering systems. However, in many cases the collected data may be incomplete or inconsistent, while the underlying environment may be time-varying or un-formulated. In this paper, we have developed an innovative cognitive fault diagnosis framework that tackles the above challenges. This framework investigates fault diagnosis in the model space instead of in the signal space. Learning in the model space is implemented by fitting a series of models using a series of signal segments selected with a rolling window. By investigating the learning techniques in the fitted model space, faulty models can be discriminated from healthy models using one-class learning algorithm. The framework enables us to construct fault library when unknown faults occur, which can be regarded as cognitive fault isolation. This paper also theoretically investigates how to measure the pairwise distance between two models in the model space and incorporates the model distance into the learning algorithm in the model space. The results on three benchmark applications and one simulated model for the Barcelona water distribution network have confirmed the effectiveness of the proposed framework.", "source": "arxiv/ml"}
{"id": "arxiv:2333", "title": "Temporal Autoencoding Restricted Boltzmann Machine", "text": "Much work has been done refining and characterizing the receptive fields learned by deep learning algorithms. A lot of this work has focused on the development of Gabor-like filters learned when enforcing sparsity constraints on a natural image dataset. Little work however has investigated how these filters might expand to the temporal domain, namely through training on natural movies. Here we investigate exactly this problem in established temporal deep learning algorithms as well as a new learning paradigm suggested here, the Temporal Autoencoding Restricted Boltzmann Machine (TARBM).", "source": "arxiv/ml"}
{"id": "arxiv:2334", "title": "First Experiments with PowerPlay", "text": "Like a scientist or a playing child, PowerPlay not only learns new skills to solve given problems, but also invents new interesting problems by itself. By design, it continually comes up with the fastest to find, initially novel, but eventually solvable tasks. It also continually simplifies or compresses or speeds up solutions to previous tasks. Here we describe first experiments with PowerPlay. A self-delimiting recurrent neural network SLIM RNN is used as a general computational problem solving architecture. Its connection weights can encode arbitrary, self-delimiting, halting or non-halting programs affecting both environment (through effectors) and internal states encoding abstractions of event sequences. Our PowerPlay-driven SLIM RNN learns to become an increasingly general solver of self-invented problems, continually adding new problem solving procedures to its growing skill repertoire. Extending a recent conference paper, we identify interesting, emerging, developmental stages of our open-ended system. We also show how it automatically self-modularizes, frequently re-using code for previously invented skills, always trying to invent novel tasks that can be quickly validated because they do not require too many weight changes affecting too many previous tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2335", "title": "Venn-Abers predictors", "text": "This paper continues study, both theoretical and empirical, of the method of Venn prediction, concentrating on binary prediction problems. Venn predictors produce probability-type predictions for the labels of test objects which are guaranteed to be well calibrated under the standard assumption that the observations are generated independently from the same distribution. We give a simple formalization and proof of this property. We also introduce Venn-Abers predictors, a new class of Venn predictors based on the idea of isotonic regression, and report promising empirical results both for Venn-Abers predictors and for their more computationally efficient simplified version.", "source": "arxiv/ml"}
{"id": "arxiv:2336", "title": "Understanding the Interaction between Interests, Conversations and Friendships in Facebook", "text": "In this paper, we explore salient questions about user interests, conversations and friendships in the Facebook social network, using a novel latent space model that integrates several data types. A key challenge of studying Facebook's data is the wide range of data modalities such as text, network links, and categorical labels. Our latent space model seamlessly combines all three data modalities over millions of users, allowing us to study the interplay between user friendships, interests, and higher-order network-wide social trends on Facebook. The recovered insights not only answer our initial questions, but also reveal surprising facts about user interests in the context of Facebook's ecosystem. We also confirm that our results are significant with respect to evidential information from the study subjects.", "source": "arxiv/ml"}
{"id": "arxiv:2337", "title": "The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains", "text": "In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs. The emerging field of signal processing on graphs merges algebraic and spectral graph theoretic concepts with computational harmonic analysis to process such signals on graphs. In this tutorial overview, we outline the main challenges of the area, discuss different ways to define graph spectral domains, which are the analogues to the classical frequency domain, and highlight the importance of incorporating the irregular structures of graph data domains when processing signals on graphs. We then review methods to generalize fundamental operations such as filtering, translation, modulation, dilation, and downsampling to the graph setting, and survey the localized, multiscale transforms that have been proposed to efficiently extract information from high-dimensional data on graphs. We conclude with a brief discussion of open issues and possible extensions.", "source": "arxiv/ml"}
{"id": "arxiv:2338", "title": "Iterative Hard Thresholding Methods for $l_0$ Regularized Convex Cone Programming", "text": "In this paper we consider $l_0$ regularized convex cone programming problems. In particular, we first propose an iterative hard thresholding (IHT) method and its variant for solving $l_0$ regularized box constrained convex programming. We show that the sequence generated by these methods converges to a local minimizer. Also, we establish the iteration complexity of the IHT method for finding an $\\epsilon$-local-optimal solution. We then propose a method for solving $l_0$ regularized convex cone programming by applying the IHT method to its quadratic penalty relaxation and establish its iteration complexity for finding an $\\epsilon$-approximate local minimizer. Finally, we propose a variant of this method in which the associated penalty parameter is dynamically updated, and show that every accumulation point is a local minimizer of the problem.", "source": "arxiv/ml"}
{"id": "arxiv:2339", "title": "Extension of TSVM to Multi-Class and Hierarchical Text Classification Problems With General Losses", "text": "Transductive SVM (TSVM) is a well known semi-supervised large margin learning method for binary text classification. In this paper we extend this method to multi-class and hierarchical classification problems. We point out that the determination of labels of unlabeled examples with fixed classifier weights is a linear programming problem. We devise an efficient technique for solving it. The method is applicable to general loss functions. We demonstrate the value of the new method using large margin loss on a number of multi-class and hierarchical classification datasets. For maxent loss we show empirically that our method is better than expectation regularization/constraint and posterior regularization methods, and competitive with the version of entropy regularization method which uses label constraints.", "source": "arxiv/ml"}
{"id": "arxiv:2340", "title": "Deep Gaussian Processes", "text": "In this paper we introduce deep Gaussian process (GP) models. Deep GPs are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inputs to that Gaussian process are then governed by another GP. A single layer model is equivalent to a standard GP or the GP latent variable model (GP-LVM). We perform inference in the model by approximate variational marginalization. This results in a strict lower bound on the marginal likelihood of the model which we use for model selection (number of layers and nodes per layer). Deep belief networks are typically applied to relatively large data sets using stochastic gradient descent for optimization. Our fully Bayesian treatment allows for the application of deep models even when data is scarce. Model selection by our variational bound shows that a five layer hierarchy is justified even when modelling a digit data set containing only 150 examples.", "source": "arxiv/ml"}
{"id": "arxiv:2341", "title": "Learning curves for multi-task Gaussian process regression", "text": "We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples $n$ for all tasks. For GP covariances that are the product of an input-dependent covariance function and a free-form inter-task covariance matrix, we show that accurate approximations for the learning curve can be obtained for an arbitrary number of tasks $T$. We use these to study the asymptotic learning behaviour for large $n$. Surprisingly, multi-task learning can be asymptotically essentially useless, in the sense that examples from other tasks help only when the degree of inter-task correlation, $\\rho$, is near its maximal value $\\rho=1$. This effect is most extreme for learning of smooth target functions as described by e.g. squared exponential kernels. We also demonstrate that when learning many tasks, the learning curves separate into an initial phase, where the Bayes error on each task is reduced down to a plateau value by \"collective learning\" even though most tasks have not seen examples, and a final decay that occurs once the number of examples is proportional to the number of tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2342", "title": "Ordinal Rating of Network Performance and Inference by Matrix Completion", "text": "This paper addresses the large-scale acquisition of end-to-end network performance. We made two distinct contributions: ordinal rating of network performance and inference by matrix completion. The former reduces measurement costs and unifies various metrics which eases their processing in applications. The latter enables scalable and accurate inference with no requirement of structural information of the network nor geometric constraints. By combining both, the acquisition problem bears strong similarities to recommender systems. This paper investigates the applicability of various matrix factorization models used in recommender systems. We found that the simple regularized matrix factorization is not only practical but also produces accurate results that are beneficial for peer selection.", "source": "arxiv/ml"}
{"id": "arxiv:2343", "title": "Partition Tree Weighting", "text": "This paper introduces the Partition Tree Weighting technique, an efficient meta-algorithm for piecewise stationary sources. The technique works by performing Bayesian model averaging over a large class of possible partitions of the data into locally stationary segments. It uses a prior, closely related to the Context Tree Weighting technique of Willems, that is well suited to data compression applications. Our technique can be applied to any coding distribution at an additional time and space cost only logarithmic in the sequence length. We provide a competitive analysis of the redundancy of our method, and explore its application in a variety of settings. The order of the redundancy and the complexity of our algorithm matches those of the best competitors available in the literature, and the new algorithm exhibits a superior complexity-performance trade-off in our experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2344", "title": "The complexity of learning halfspaces using generalized linear methods", "text": "Many popular learning algorithms (E.g. Regression, Fourier-Transform based algorithms, Kernel SVM and Kernel ridge regression) operate by reducing the problem to a convex optimization problem over a vector space of functions. These methods offer the currently best approach to several central problems such as learning half spaces and learning DNF's. In addition they are widely used in numerous application domains. Despite their importance, there are still very few proof techniques to show limits on the power of these algorithms. We study the performance of this approach in the problem of (agnostically and improperly) learning halfspaces with margin $\\gamma$. Let $\\mathcal{D}$ be a distribution over labeled examples. The $\\gamma$-margin error of a hyperplane $h$ is the probability of an example to fall on the wrong side of $h$ or at a distance $\\le\\gamma$ from it. The $\\gamma$-margin error of the best $h$ is denoted $\\mathrm{Err}_\\gamma(\\mathcal{D})$. An $\\alpha(\\gamma)$-approximation algorithm receives $\\gamma,\\epsilon$ as input and, using i.i.d. samples of $\\mathcal{D}$, outputs a classifier with error rate $\\le \\alpha(\\gamma)\\mathrm{Err}_\\gamma(\\mathcal{D}) + \\epsilon$. Such an algorithm is efficient if it uses $\\mathrm{poly}(\\frac{1}{\\gamma},\\frac{1}{\\epsilon})$ samples and runs in time polynomial in the sample size. The best approximation ratio achievable by an efficient algorithm is $O\\left(\\frac{1/\\gamma}{\\sqrt{\\log(1/\\gamma)}}\\right)$ and is achieved using an algorithm from the above class. Our main result shows that the approximation ratio of every efficient algorithm from this family must be $\\ge \\Omega\\left(\\frac{1/\\gamma}{\\mathrm{poly}\\left(\\log\\left(1/\\gamma\\right)\\right)}\\right)$, essentially matching the best known upper bound.", "source": "arxiv/ml"}
{"id": "arxiv:2345", "title": "Stochastic ADMM for Nonsmooth Optimization", "text": "We present a stochastic setting for optimization problems with nonsmooth convex separable objective functions over linear equality constraints. To solve such problems, we propose a stochastic Alternating Direction Method of Multipliers (ADMM) algorithm. Our algorithm applies to a more general class of nonsmooth convex functions that does not necessarily have a closed-form solution by minimizing the augmented function directly. We also demonstrate the rates of convergence for our algorithm under various structural assumptions of the stochastic functions: $O(1/\\sqrt{t})$ for convex functions and $O(\\log t/t)$ for strongly convex functions. Compared to previous literature, we establish the convergence rate of ADMM algorithm, for the first time, in terms of both the objective value and the feasibility violation.", "source": "arxiv/ml"}
{"id": "arxiv:2346", "title": "Discussion: Latent variable graphical model selection via convex optimization", "text": "Discussion of \"Latent variable graphical model selection via convex optimization\" by Venkat Chandrasekaran, Pablo A. Parrilo and Alan S. Willsky [arXiv:1008.1290].", "source": "arxiv/ml"}
{"id": "arxiv:2350", "title": "Rejoinder: Latent variable graphical model selection via convex optimization", "text": "Rejoinder to \"Latent variable graphical model selection via convex optimization\" by Venkat Chandrasekaran, Pablo A. Parrilo and Alan S. Willsky [arXiv:1008.1290].", "source": "arxiv/ml"}
{"id": "arxiv:2351", "title": "Comparing K-Nearest Neighbors and Potential Energy Method in classification problem. A case study using KNN applet by E.M. Mirkes and real life benchmark data sets", "text": "K-nearest neighbors (KNN) method is used in many supervised learning classification problems. Potential Energy (PE) method is also developed for classification problems based on its physical metaphor. The energy potential used in the experiments are Yukawa potential and Gaussian Potential. In this paper, I use both applet and MATLAB program with real life benchmark data to analyze the performances of KNN and PE method in classification problems. The results show that in general, KNN and PE methods have similar performance. In particular, PE with Yukawa potential has worse performance than KNN when the density of the data is higher in the distribution of the database. When the Gaussian potential is applied, the results from PE and KNN have similar behavior. The indicators used are correlation coefficients and information gain.", "source": "arxiv/ml"}
{"id": "arxiv:2352", "title": "APPLE: Approximate Path for Penalized Likelihood Estimators", "text": "In high-dimensional data analysis, penalized likelihood estimators are shown to provide superior results in both variable selection and parameter estimation. A new algorithm, APPLE, is proposed for calculating the Approximate Path for Penalized Likelihood Estimators. Both the convex penalty (such as LASSO) and the nonconvex penalty (such as SCAD and MCP) cases are considered. The APPLE efficiently computes the solution path for the penalized likelihood estimator using a hybrid of the modified predictor-corrector method and the coordinate-descent algorithm. APPLE is compared with several well-known packages via simulation and analysis of two gene expression data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2353", "title": "Algorithm Runtime Prediction: Methods & Evaluation", "text": "Perhaps surprisingly, it is possible to predict how long an algorithm will take to run on a previously unseen input, using machine learning techniques to build a model of the algorithm's runtime as a function of problem-specific instance features. Such models have important applications to algorithm analysis, portfolio-based algorithm selection, and the automatic configuration of parameterized algorithms. Over the past decade, a wide variety of techniques have been studied for building such models. Here, we describe extensions and improvements of existing models, new families of models, and -- perhaps most importantly -- a much more thorough treatment of algorithm parameters as model inputs. We also comprehensively describe new and existing features for predicting algorithm runtime for propositional satisfiability (SAT), travelling salesperson (TSP) and mixed integer programming (MIP) problems. We evaluate these innovations through the largest empirical analysis of its kind, comparing to a wide range of runtime modelling techniques from the literature. Our experiments consider 11 algorithms and 35 instance distributions; they also span a very wide range of SAT, MIP, and TSP instances, with the least structured having been generated uniformly at random and the most structured having emerged from real industrial applications. Overall, we demonstrate that our new models yield substantially better runtime predictions than previous approaches in terms of their generalization to new problem instances, to new algorithms from a parameterized space, and to both simultaneously.", "source": "arxiv/ml"}
{"id": "arxiv:2354", "title": "Learning using Local Membership Queries", "text": "We introduce a new model of membership query (MQ) learning, where the learning algorithm is restricted to query points that are \\emph{close} to random examples drawn from the underlying distribution. The learning model is intermediate between the PAC model (Valiant, 1984) and the PAC+MQ model (where the queries are allowed to be arbitrary points). Membership query algorithms are not popular among machine learning practitioners. Apart from the obvious difficulty of adaptively querying labelers, it has also been observed that querying \\emph{unnatural} points leads to increased noise from human labelers (Lang and Baum, 1992). This motivates our study of learning algorithms that make queries that are close to examples generated from the data distribution. We restrict our attention to functions defined on the $n$-dimensional Boolean hypercube and say that a membership query is local if its Hamming distance from some example in the (random) training data is at most $O(\\log(n))$. We show the following results in this model: (i) The class of sparse polynomials (with coefficients in R) over $\\{0,1\\}^n$ is polynomial time learnable under a large class of \\emph{locally smooth} distributions using $O(\\log(n))$-local queries. This class also includes the class of $O(\\log(n))$-depth decision trees. (ii) The class of polynomial-sized decision trees is polynomial time learnable under product distributions using $O(\\log(n))$-local queries. (iii) The class of polynomial size DNF formulas is learnable under the uniform distribution using $O(\\log(n))$-local queries in time $n^{O(\\log(\\log(n)))}$. (iv) In addition we prove a number of results relating the proposed model to the traditional PAC model and the PAC+MQ model.", "source": "arxiv/ml"}
{"id": "arxiv:2355", "title": "Algorithms and Hardness for Robust Subspace Recovery", "text": "We consider a fundamental problem in unsupervised learning called \\emph{subspace recovery}: given a collection of $m$ points in $\\mathbb{R}^n$, if many but not necessarily all of these points are contained in a $d$-dimensional subspace $T$ can we find it? The points contained in $T$ are called {\\em inliers} and the remaining points are {\\em outliers}. This problem has received considerable attention in computer science and in statistics. Yet efficient algorithms from computer science are not robust to {\\em adversarial} outliers, and the estimators from robust statistics are hard to compute in high dimensions. Are there algorithms for subspace recovery that are both robust to outliers and efficient? We give an algorithm that finds $T$ when it contains more than a $\\frac{d}{n}$ fraction of the points. Hence, for say $d = n/2$ this estimator is both easy to compute and well-behaved when there are a constant fraction of outliers. We prove that it is Small Set Expansion hard to find $T$ when the fraction of errors is any larger, thus giving evidence that our estimator is an {\\em optimal} compromise between efficiency and robustness. As it turns out, this basic problem has a surprising number of connections to other areas including small set expansion, matroid theory and functional analysis that we make use of here.", "source": "arxiv/ml"}
{"id": "arxiv:2356", "title": "Soft (Gaussian CDE) regression models and loss functions", "text": "Regression, unlike classification, has lacked a comprehensive and effective approach to deal with cost-sensitive problems by the reuse (and not a re-training) of general regression models. In this paper, a wide variety of cost-sensitive problems in regression (such as bids, asymmetric losses and rejection rules) can be solved effectively by a lightweight but powerful approach, consisting of: (1) the conversion of any traditional one-parameter crisp regression model into a two-parameter soft regression model, seen as a normal conditional density estimator, by the use of newly-introduced enrichment methods; and (2) the reframing of an enriched soft regression model to new contexts by an instance-dependent optimisation of the expected loss derived from the conditional normal distribution.", "source": "arxiv/ml"}
{"id": "arxiv:2357", "title": "Active and passive learning of linear separators under log-concave distributions", "text": "We provide new results concerning label efficient, polynomial time, passive and active learning of linear separators. We prove that active learning provides an exponential improvement over PAC (passive) learning of homogeneous linear separators under nearly log-concave distributions. Building on this, we provide a computationally efficient PAC algorithm with optimal (up to a constant factor) sample complexity for such problems. This resolves an open question concerning the sample complexity of efficient PAC algorithms under the uniform distribution in the unit ball. Moreover, it provides the first bound for a polynomial-time PAC algorithm that is tight for an interesting infinite class of hypothesis functions under a general and natural class of data-distributions, providing significant progress towards a longstanding open question. We also provide new bounds for active and passive learning in the case that the data might not be linearly separable, both in the agnostic case and and under the Tsybakov low-noise condition. To derive our results, we provide new structural results for (nearly) log-concave distributions, which might be of independent interest as well.", "source": "arxiv/ml"}
{"id": "arxiv:2358", "title": "Visual Transfer Learning: Informal Introduction and Literature Overview", "text": "Transfer learning techniques are important to handle small training sets and to allow for quick generalization even from only a few examples. The following paper is the introduction as well as the literature overview part of my thesis related to the topic of transfer learning for visual recognition problems.", "source": "arxiv/ml"}
{"id": "arxiv:2359", "title": "Handwritten digit recognition by bio-inspired hierarchical networks", "text": "The human brain processes information showing learning and prediction abilities but the underlying neuronal mechanisms still remain unknown. Recently, many studies prove that neuronal networks are able of both generalizations and associations of sensory inputs. In this paper, following a set of neurophysiological evidences, we propose a learning framework with a strong biological plausibility that mimics prominent functions of cortical circuitries. We developed the Inductive Conceptual Network (ICN), that is a hierarchical bio-inspired network, able to learn invariant patterns by Variable-order Markov Models implemented in its nodes. The outputs of the top-most node of ICN hierarchy, representing the highest input generalization, allow for automatic classification of inputs. We found that the ICN clusterized MNIST images with an error of 5.73% and USPS images with an error of 12.56%.", "source": "arxiv/ml"}
{"id": "arxiv:2360", "title": "Random walk kernels and learning curves for Gaussian process regression on random graphs", "text": "We consider learning on graphs, guided by kernels that encode similarity between vertices. Our focus is on random walk kernels, the analogues of squared exponential kernels in Euclidean spaces. We show that on large, locally treelike, graphs these have some counter-intuitive properties, specifically in the limit of large kernel lengthscales. We consider using these kernels as covariance matrices of e.g.\\ Gaussian processes (GPs). In this situation one typically scales the prior globally to normalise the average of the prior variance across vertices. We demonstrate that, in contrast to the Euclidean case, this generically leads to significant variation in the prior variance across vertices, which is undesirable from the probabilistic modelling point of view. We suggest the random walk kernel should be normalised locally, so that each vertex has the same prior variance, and analyse the consequences of this by studying learning curves for Gaussian process regression. Numerical calculations as well as novel theoretical predictions for the learning curves using belief propagation make it clear that one obtains distinctly different probabilistic models depending on the choice of normalisation. Our method for predicting the learning curves using belief propagation is significantly more accurate than previous approximations and should become exact in the limit of large random graphs.", "source": "arxiv/ml"}
{"id": "arxiv:2361", "title": "K-Plane Regression", "text": "In this paper, we present a novel algorithm for piecewise linear regression which can learn continuous as well as discontinuous piecewise linear functions. The main idea is to repeatedly partition the data and learn a liner model in in each partition. While a simple algorithm incorporating this idea does not work well, an interesting modification results in a good algorithm. The proposed algorithm is similar in spirit to $k$-means clustering algorithm. We show that our algorithm can also be viewed as an EM algorithm for maximum likelihood estimation of parameters under a reasonable probability model. We empirically demonstrate the effectiveness of our approach by comparing its performance with the state of art regression learning algorithms on some real world datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2362", "title": "Explosion prediction of oil gas using SVM and Logistic Regression", "text": "The prevention of dangerous chemical accidents is a primary problem of industrial manufacturing. In the accidents of dangerous chemicals, the oil gas explosion plays an important role. The essential task of the explosion prevention is to estimate the better explosion limit of a given oil gas. In this paper, Support Vector Machines (SVM) and Logistic Regression (LR) are used to predict the explosion of oil gas. LR can get the explicit probability formula of explosion, and the explosive range of the concentrations of oil gas according to the concentration of oxygen. Meanwhile, SVM gives higher accuracy of prediction. Furthermore, considering the practical requirements, the effects of penalty parameter on the distribution of two types of errors are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2363", "title": "Image denoising with multi-layer perceptrons, part 1: comparison with existing algorithms and with bounds", "text": "Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to learn this mapping directly with plain multi layer perceptrons (MLP) applied to image patches. We will show that by training on large image databases we are able to outperform the current state-of-the-art image denoising methods. In addition, our method achieves results that are superior to one type of theoretical bound and goes a large way toward closing the gap with a second type of theoretical bound. Our approach is easily adapted to less extensively studied types of noise, such as mixed Poisson-Gaussian noise, JPEG artifacts, salt-and-pepper noise and noise resembling stripes, for which we achieve excellent results as well. We will show that combining a block-matching procedure with MLPs can further improve the results on certain images. In a second paper, we detail the training trade-offs and the inner mechanisms of our MLPs.", "source": "arxiv/ml"}
{"id": "arxiv:2364", "title": "A Riemannian geometry for low-rank matrix completion", "text": "We propose a new Riemannian geometry for fixed-rank matrices that is specifically tailored to the low-rank matrix completion problem. Exploiting the degree of freedom of a quotient space, we tune the metric on our search space to the particular least square cost function. At one level, it illustrates in a novel way how to exploit the versatile framework of optimization on quotient manifold. At another level, our algorithm can be considered as an improved version of LMaFit, the state-of-the-art Gauss-Seidel algorithm. We develop necessary tools needed to perform both first-order and second-order optimization. In particular, we propose gradient descent schemes (steepest descent and conjugate gradient) and trust-region algorithms. We also show that, thanks to the simplicity of the cost function, it is numerically cheap to perform an exact linesearch given a search direction, which makes our algorithms competitive with the state-of-the-art on standard low-rank matrix completion instances.", "source": "arxiv/ml"}
{"id": "arxiv:2365", "title": "Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms", "text": "Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. In another paper, we show that multi-layer perceptrons can achieve outstanding image denoising performance for various types of noise (additive white Gaussian noise, mixed Poisson-Gaussian noise, JPEG artifacts, salt-and-pepper noise and noise resembling stripes). In this work we discuss in detail which trade-offs have to be considered during the training procedure. We will show how to achieve good results and which pitfalls to avoid. By analysing the activation patterns of the hidden units we are able to make observations regarding the functioning principle of multi-layer perceptrons trained for image denoising.", "source": "arxiv/ml"}
{"id": "arxiv:2366", "title": "Learning Monocular Reactive UAV Control in Cluttered Natural Environments", "text": "Autonomous navigation for large Unmanned Aerial Vehicles (UAVs) is fairly straight-forward, as expensive sensors and monitoring devices can be employed. In contrast, obstacle avoidance remains a challenging task for Micro Aerial Vehicles (MAVs) which operate at low altitude in cluttered environments. Unlike large vehicles, MAVs can only carry very light sensors, such as cameras, making autonomous navigation through obstacles much more challenging. In this paper, we describe a system that navigates a small quadrotor helicopter autonomously at low altitude through natural forest environments. Using only a single cheap camera to perceive the environment, we are able to maintain a constant velocity of up to 1.5m/s. Given a small set of human pilot demonstrations, we use recent state-of-the-art imitation learning techniques to train a controller that can avoid trees by adapting the MAVs heading. We demonstrate the performance of our system in a more controlled environment indoors, and in real natural forest environments outdoors.", "source": "arxiv/ml"}
{"id": "arxiv:2367", "title": "Blind Signal Separation in the Presence of Gaussian Noise", "text": "A prototypical blind signal separation problem is the so-called cocktail party problem, with n people talking simultaneously and n different microphones within a room. The goal is to recover each speech signal from the microphone inputs. Mathematically this can be modeled by assuming that we are given samples from an n-dimensional random variable X=AS, where S is a vector whose coordinates are independent random variables corresponding to each speaker. The objective is to recover the matrix A^{-1} given random samples from X. A range of techniques collectively known as Independent Component Analysis (ICA) have been proposed to address this problem in the signal processing and machine learning literature. Many of these techniques are based on using the kurtosis or other cumulants to recover the components. In this paper we propose a new algorithm for solving the blind signal separation problem in the presence of additive Gaussian noise, when we are given samples from X=AS+\\eta, where \\eta is drawn from an unknown, not necessarily spherical n-dimensional Gaussian distribution. Our approach is based on a method for decorrelating a sample with additive Gaussian noise under the assumption that the underlying distribution is a linear transformation of a distribution with independent components. Our decorrelation routine is based on the properties of cumulant tensors and can be combined with any standard cumulant-based method for ICA to get an algorithm that is provably robust in the presence of Gaussian noise. We derive polynomial bounds for the sample complexity and error propagation of our method.", "source": "arxiv/ml"}
{"id": "arxiv:2368", "title": "Inverse problems in approximate uniform generation", "text": "We initiate the study of \\emph{inverse} problems in approximate uniform generation, focusing on uniform generation of satisfying assignments of various types of Boolean functions. In such an inverse problem, the algorithm is given uniform random satisfying assignments of an unknown function $f$ belonging to a class $\\C$ of Boolean functions, and the goal is to output a probability distribution $D$ which is $\\epsilon$-close, in total variation distance, to the uniform distribution over $f^{-1}(1)$. Positive results: We prove a general positive result establishing sufficient conditions for efficient inverse approximate uniform generation for a class $\\C$. We define a new type of algorithm called a \\emph{densifier} for $\\C$, and show (roughly speaking) how to combine (i) a densifier, (ii) an approximate counting / uniform generation algorithm, and (iii) a Statistical Query learning algorithm, to obtain an inverse approximate uniform generation algorithm. We apply this general result to obtain a poly$(n,1/\\eps)$-time algorithm for the class of halfspaces; and a quasipoly$(n,1/\\eps)$-time algorithm for the class of $\\poly(n)$-size DNF formulas. Negative results: We prove a general negative result establishing that the existence of certain types of signature schemes in cryptography implies the hardness of certain inverse approximate uniform generation problems. This implies that there are no {subexponential}-time inverse approximate uniform generation algorithms for 3-CNF formulas; for intersections of two halfspaces; for degree-2 polynomial threshold functions; and for monotone 2-CNF formulas. Finally, we show that there is no general relationship between the complexity of the \"forward\" approximate uniform generation problem and the complexity of the inverse problem for a class $\\C$ -- it is possible for either one to be easy while the other is hard.", "source": "arxiv/ml"}
{"id": "arxiv:2369", "title": "Algorithm for Missing Values Imputation in Categorical Data with Use of Association Rules", "text": "This paper presents algorithm for missing values imputation in categorical data. The algorithm is based on using association rules and is presented in three variants. Experimental shows better accuracy of missing values imputation using the algorithm then using most common attribute value.", "source": "arxiv/ml"}
{"id": "arxiv:2370", "title": "Tangent-based manifold approximation with locally linear models", "text": "In this paper, we consider the problem of manifold approximation with affine subspaces. Our objective is to discover a set of low dimensional affine subspaces that represents manifold data accurately while preserving the manifold's structure. For this purpose, we employ a greedy technique that partitions manifold samples into groups that can be each approximated by a low dimensional subspace. We start by considering each manifold sample as a different group and we use the difference of tangents to determine appropriate group mergings. We repeat this procedure until we reach the desired number of sample groups. The best low dimensional affine subspaces corresponding to the final groups constitute our approximate manifold representation. Our experiments verify the effectiveness of the proposed scheme and show its superior performance compared to state-of-the-art methods for manifold approximation.", "source": "arxiv/ml"}
{"id": "arxiv:2371", "title": "LAGE: A Java Framework to reconstruct Gene Regulatory Networks from Large-Scale Continues Expression Data", "text": "LAGE is a systematic framework developed in Java. The motivation of LAGE is to provide a scalable and parallel solution to reconstruct Gene Regulatory Networks (GRNs) from continuous gene expression data for very large amount of genes. The basic idea of our framework is motivated by the philosophy of divideand-conquer. Specifically, LAGE recursively partitions genes into multiple overlapping communities with much smaller sizes, learns intra-community GRNs respectively before merge them altogether. Besides, the complete information of overlapping communities serves as the byproduct, which could be used to mine meaningful functional modules in biological networks.", "source": "arxiv/ml"}
{"id": "arxiv:2372", "title": "Efficient Monte Carlo Methods for Multi-Dimensional Learning with Classifier Chains", "text": "Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance - at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest- performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2373", "title": "Efficient learning of simplices", "text": "We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan [FJK]. Our result can also be interpreted as efficiently learning the intersection of n+1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by [FJK]. Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA.", "source": "arxiv/ml"}
{"id": "arxiv:2374", "title": "No-Regret Algorithms for Unconstrained Online Convex Optimization", "text": "Some of the most compelling applications of online convex optimization, including online prediction and classification, are unconstrained: the natural feasible set is R^n. Existing algorithms fail to achieve sub-linear regret in this setting unless constraints on the comparator point x^* are known in advance. We present algorithms that, without such prior knowledge, offer near-optimal regret bounds with respect to any choice of x^*. In particular, regret with respect to x^* = 0 is constant. We then prove lower bounds showing that our guarantees are near-optimal in this setting.", "source": "arxiv/ml"}
{"id": "arxiv:2375", "title": "Probabilistic Combination of Classifier and Cluster Ensembles for Non-transductive Learning", "text": "Unsupervised models can provide supplementary soft constraints to help classify new target data under the assumption that similar objects in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in applications where concept drift may take place. This paper describes a Bayesian framework that takes as input class labels from existing classifiers (designed based on labeled data from the source domain), as well as cluster labels from a cluster ensemble operating solely on the target data to be classified, and yields a consensus labeling of the target data. This framework is particularly useful when the statistics of the target data drift or change from those of the training data. We also show that the proposed framework is privacy-aware and allows performing distributed learning when data/models have sharing restrictions. Experiments show that our framework can yield superior results to those provided by applying classifier ensembles only.", "source": "arxiv/ml"}
{"id": "arxiv:2376", "title": "Hybrid methodology for hourly global radiation forecasting in Mediterranean area", "text": "The renewable energies prediction and particularly global radiation forecasting is a challenge studied by a growing number of research teams. This paper proposes an original technique to model the insolation time series based on combining Artificial Neural Network (ANN) and Auto-Regressive and Moving Average (ARMA) model. While ANN by its non-linear nature is effective to predict cloudy days, ARMA techniques are more dedicated to sunny days without cloud occurrences. Thus, three hybrids models are suggested: the first proposes simply to use ARMA for 6 months in spring and summer and to use an optimized ANN for the other part of the year; the second model is equivalent to the first but with a seasonal learning; the last model depends on the error occurred the previous hour. These models were used to forecast the hourly global radiation for five places in Mediterranean area. The forecasting performance was compared among several models: the 3 above mentioned models, the best ANN and ARMA for each location. In the best configuration, the coupling of ANN and ARMA allows an improvement of more than 1%, with a maximum in autumn (3.4%) and a minimum in winter (0.9%) where ANN alone is the best.", "source": "arxiv/ml"}
{"id": "arxiv:2377", "title": "Measures of Entropy from Data Using Infinitely Divisible Kernels", "text": "Information theory provides principled ways to analyze different inference and learning problems such as hypothesis testing, clustering, dimensionality reduction, classification, among others. However, the use of information theoretic quantities as test statistics, that is, as quantities obtained from empirical data, poses a challenging estimation problem that often leads to strong simplifications such as Gaussian models, or the use of plug in density estimators that are restricted to certain representation of the data. In this paper, a framework to non-parametrically obtain measures of entropy directly from data using operators in reproducing kernel Hilbert spaces defined by infinitely divisible kernels is presented. The entropy functionals, which bear resemblance with quantum entropies, are defined on positive definite matrices and satisfy similar axioms to those of Renyi's definition of entropy. Convergence of the proposed estimators follows from concentration results on the difference between the ordered spectrum of the Gram matrices and the integral operators associated to the population quantities. In this way, capitalizing on both the axiomatic definition of entropy and on the representation power of positive definite kernels, the proposed measure of entropy avoids the estimation of the probability distribution underlying the data. Moreover, estimators of kernel-based conditional entropy and mutual information are also defined. Numerical experiments on independence tests compare favourably with state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:2378", "title": "Random Utility Theory for Social Choice", "text": "Random utility theory models an agent's preferences on alternatives by drawing a real-valued score on each alternative (typically independently) from a parameterized distribution, and then ranking the alternatives according to scores. A special case that has received significant attention is the Plackett-Luce model, for which fast inference methods for maximum likelihood estimators are available. This paper develops conditions on general random utility models that enable fast inference within a Bayesian framework through MC-EM, providing concave loglikelihood functions and bounded sets of global maxima solutions. Results on both real-world and simulated data provide support for the scalability of the approach and capability for model selection among general random utility models including Plackett-Luce.", "source": "arxiv/ml"}
{"id": "arxiv:2379", "title": "Minimal cost feature selection of data with normal distribution measurement errors", "text": "Minimal cost feature selection is devoted to obtain a trade-off between test costs and misclassification costs. This issue has been addressed recently on nominal data. In this paper, we consider numerical data with measurement errors and study minimal cost feature selection in this model. First, we build a data model with normal distribution measurement errors. Second, the neighborhood of each data item is constructed through the confidence interval. Comparing with discretized intervals, neighborhoods are more reasonable to maintain the information of data. Third, we define a new minimal total cost feature selection problem through considering the trade-off between test costs and misclassification costs. Fourth, we proposed a backtracking algorithm with three effective pruning techniques to deal with this problem. The algorithm is tested on four UCI data sets. Experimental results indicate that the pruning techniques are effective, and the algorithm is efficient for data sets with nearly one thousand objects.", "source": "arxiv/ml"}
{"id": "arxiv:2380", "title": "Iterative Thresholding Algorithm for Sparse Inverse Covariance Estimation", "text": "The L1-regularized maximum likelihood estimation problem has recently become a topic of great interest within the machine learning, statistics, and optimization communities as a method for producing sparse inverse covariance estimators. In this paper, a proximal gradient method (G-ISTA) for performing L1-regularized covariance matrix estimation is presented. Although numerous algorithms have been proposed for solving this problem, this simple proximal gradient method is found to have attractive theoretical and numerical properties. G-ISTA has a linear rate of convergence, resulting in an O(log e) iteration complexity to reach a tolerance of e. This paper gives eigenvalue bounds for the G-ISTA iterates, providing a closed-form linear convergence rate. The rate is shown to be closely related to the condition number of the optimal point. Numerical convergence results and timing comparisons for the proposed method are presented. G-ISTA is shown to perform very well, especially when the optimal point is well-conditioned.", "source": "arxiv/ml"}
{"id": "arxiv:2381", "title": "A Comparative Study of Gaussian Mixture Model and Radial Basis Function for Voice Recognition", "text": "A comparative study of the application of Gaussian Mixture Model (GMM) and Radial Basis Function (RBF) in biometric recognition of voice has been carried out and presented. The application of machine learning techniques to biometric authentication and recognition problems has gained a widespread acceptance. In this research, a GMM model was trained, using Expectation Maximization (EM) algorithm, on a dataset containing 10 classes of vowels and the model was used to predict the appropriate classes using a validation dataset. For experimental validity, the model was compared to the performance of two different versions of RBF model using the same learning and validation datasets. The results showed very close recognition accuracy between the GMM and the standard RBF model, but with GMM performing better than the standard RBF by less than 1% and the two models outperformed similar models reported in literature. The DTREG version of RBF outperformed the other two models by producing 94.8% recognition accuracy. In terms of recognition time, the standard RBF was found to be the fastest among the three models.", "source": "arxiv/ml"}
{"id": "arxiv:2382", "title": "Proximal Stochastic Dual Coordinate Ascent", "text": "We introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including $\\ell_1$ regularization and structured output SVM. The convergence rates we obtain match, and sometimes improve, state-of-the-art results.", "source": "arxiv/ml"}
{"id": "arxiv:2383", "title": "Deep Attribute Networks", "text": "Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the basis of high-level features that carry semantic meaning which humans can understand. In this paper, a model coined deep attribute network (DAN) is proposed to address this issue. For an input image, the model outputs the attributes of the input image without performing any classification. The efficacy of the proposed model is evaluated on unconstrained face verification and real-world object recognition tasks using the LFW and the a-PASCAL datasets. We demonstrate the potential of deep learning for attribute-based classification by showing comparable results with existing state-of-the-art results. Once properly trained, the DAN is fast and does away with calculating low-level features which are maybe unreliable and computationally expensive.", "source": "arxiv/ml"}
{"id": "arxiv:2384", "title": "Boosting Simple Collaborative Filtering Models Using Ensemble Methods", "text": "In this paper we examine the effect of applying ensemble learning to the performance of collaborative filtering methods. We present several systematic approaches for generating an ensemble of collaborative filtering models based on a single collaborative filtering algorithm (single-model or homogeneous ensemble). We present an adaptation of several popular ensemble techniques in machine learning for the collaborative filtering domain, including bagging, boosting, fusion and randomness injection. We evaluate the proposed approach on several types of collaborative filtering base models: k- NN, matrix factorization and a neighborhood matrix factorization model. Empirical evaluation shows a prediction improvement compared to all base CF algorithms. In particular, we show that the performance of an ensemble of simple (weak) CF models such as k-NN is competitive compared with a single strong CF model (such as matrix factorization) while requiring an order of magnitude less computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:2385", "title": "Shattering-Extremal Systems", "text": "The Shatters relation and the VC dimension have been investigated since the early seventies. These concepts have found numerous applications in statistics, combinatorics, learning theory and computational geometry. Shattering extremal systems are set-systems with a very rich structure and many different characterizations. The goal of this thesis is to elaborate on the structure of these systems.", "source": "arxiv/ml"}
{"id": "arxiv:2386", "title": "Time-series Scenario Forecasting", "text": "Many applications require the ability to judge uncertainty of time-series forecasts. Uncertainty is often specified as point-wise error bars around a mean or median forecast. Due to temporal dependencies, such a method obscures some information. We would ideally have a way to query the posterior probability of the entire time-series given the predictive variables, or at a minimum, be able to draw samples from this distribution. We use a Bayesian dictionary learning algorithm to statistically generate an ensemble of forecasts. We show that the algorithm performs as well as a physics-based ensemble method for temperature forecasts for Houston. We conclude that the method shows promise for scenario forecasting where physics-based methods are absent.", "source": "arxiv/ml"}
{"id": "arxiv:2387", "title": "Recovering the Optimal Solution by Dual Random Projection", "text": "Random projection has been widely used in data classification. It maps high-dimensional data into a low-dimensional subspace in order to reduce the computational cost in solving the related optimization problem. While previous studies are focused on analyzing the classification performance of using random projection, in this work, we consider the recovery problem, i.e., how to accurately recover the optimal solution to the original optimization problem in the high-dimensional space based on the solution learned from the subspace spanned by random projections. We present a simple algorithm, termed Dual Random Projection, that uses the dual solution of the low-dimensional optimization problem to recover the optimal solution to the original problem. Our theoretical analysis shows that with a high probability, the proposed algorithm is able to accurately recover the optimal solution to the original problem, provided that the data matrix is of low rank or can be well approximated by a low rank matrix.", "source": "arxiv/ml"}
{"id": "arxiv:2388", "title": "Distributed Non-Stochastic Experts", "text": "We consider the online distributed non-stochastic experts problem, where the distributed system consists of one coordinator node that is connected to $k$ sites, and the sites are required to communicate with each other via the coordinator. At each time-step $t$, one of the $k$ site nodes has to pick an expert from the set ${1, ..., n}$, and the same site receives information about payoffs of all experts for that round. The goal of the distributed system is to minimize regret at time horizon $T$, while simultaneously keeping communication to a minimum. The two extreme solutions to this problem are: (i) Full communication: This essentially simulates the non-distributed setting to obtain the optimal $O(\\sqrt{\\log(n)T})$ regret bound at the cost of $T$ communication. (ii) No communication: Each site runs an independent copy : the regret is $O(\\sqrt{log(n)kT})$ and the communication is 0. This paper shows the difficulty of simultaneously achieving regret asymptotically better than $\\sqrt{kT}$ and communication better than $T$. We give a novel algorithm that for an oblivious adversary achieves a non-trivial trade-off: regret $O(\\sqrt{k^{5(1+\\epsilon)/6} T})$ and communication $O(T/k^{\\epsilon})$, for any value of $\\epsilon \\in (0, 1/5)$. We also consider a variant of the model, where the coordinator picks the expert. In this model, we show that the label-efficient forecaster of Cesa-Bianchi et al. (2005) already gives us strategy that is near optimal in regret vs communication trade-off.", "source": "arxiv/ml"}
{"id": "arxiv:2389", "title": "Order-independent constraint-based causal structure learning", "text": "We consider constraint-based methods for causal structure learning, such as the PC-, FCI-, RFCI- and CCD- algorithms (Spirtes et al. (2000, 1993), Richardson (1996), Colombo et al. (2012), Claassen et al. (2013)). The first step of all these algorithms consists of the PC-algorithm. This algorithm is known to be order-dependent, in the sense that the output can depend on the order in which the variables are given. This order-dependence is a minor issue in low-dimensional settings. We show, however, that it can be very pronounced in high-dimensional settings, where it can lead to highly variable results. We propose several modifications of the PC-algorithm (and hence also of the other algorithms) that remove part or all of this order-dependence. All proposed modifications are consistent in high-dimensional settings under the same conditions as their original counterparts. We compare the PC-, FCI-, and RFCI-algorithms and their modifications in simulation studies and on a yeast gene expression data set. We show that our modifications yield similar performance in low-dimensional settings and improved performance in high-dimensional settings. All software is implemented in the R-package pcalg.", "source": "arxiv/ml"}
{"id": "arxiv:2390", "title": "Network Sampling: From Static to Streaming Graphs", "text": "Network sampling is integral to the analysis of social, information, and biological networks. Since many real-world networks are massive in size, continuously evolving, and/or distributed in nature, the network structure is often sampled in order to facilitate study. For these reasons, a more thorough and complete understanding of network sampling is critical to support the field of network science. In this paper, we outline a framework for the general problem of network sampling, by highlighting the different objectives, population and units of interest, and classes of network sampling methods. In addition, we propose a spectrum of computational models for network sampling methods, ranging from the traditionally studied model based on the assumption of a static domain to a more challenging model that is appropriate for streaming domains. We design a family of sampling methods based on the concept of graph induction that generalize across the full spectrum of computational models (from static to streaming) while efficiently preserving many of the topological properties of the input graphs. Furthermore, we demonstrate how traditional static sampling algorithms can be modified for graph streams for each of the three main classes of sampling methods: node, edge, and topology-based sampling. Our experimental results indicate that our proposed family of sampling methods more accurately preserves the underlying properties of the graph for both static and streaming graphs. Finally, we study the impact of network sampling algorithms on the parameter estimation and performance evaluation of relational classification algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2391", "title": "Spectral Clustering: An empirical study of Approximation Algorithms and its Application to the Attrition Problem", "text": "Clustering is the problem of separating a set of objects into groups (called clusters) so that objects within the same cluster are more similar to each other than to those in different clusters. Spectral clustering is a now well-known method for clustering which utilizes the spectrum of the data similarity matrix to perform this separation. Since the method relies on solving an eigenvector problem, it is computationally expensive for large datasets. To overcome this constraint, approximation methods have been developed which aim to reduce running time while maintaining accurate classification. In this article, we summarize and experimentally evaluate several approximation methods for spectral clustering. From an applications standpoint, we employ spectral clustering to solve the so-called attrition problem, where one aims to identify from a set of employees those who are likely to voluntarily leave the company from those who are not. Our study sheds light on the empirical performance of existing approximate spectral clustering methods and shows the applicability of these methods in an important business optimization related problem.", "source": "arxiv/ml"}
{"id": "arxiv:2392", "title": "Accelerated Canonical Polyadic Decomposition by Using Mode Reduction", "text": "Canonical Polyadic (or CANDECOMP/PARAFAC, CP) decompositions (CPD) are widely applied to analyze high order tensors. Existing CPD methods use alternating least square (ALS) iterations and hence need to unfold tensors to each of the $N$ modes frequently, which is one major bottleneck of efficiency for large-scale data and especially when $N$ is large. To overcome this problem, in this paper we proposed a new CPD method which converts the original $N$th ($N>3$) order tensor to a 3rd-order tensor first. Then the full CPD is realized by decomposing this mode reduced tensor followed by a Khatri-Rao product projection procedure. This way is quite efficient as unfolding to each of the $N$ modes are avoided, and dimensionality reduction can also be easily incorporated to further improve the efficiency. We show that, under mild conditions, any $N$th-order CPD can be converted into a 3rd-order case but without destroying the essential uniqueness, and theoretically gives the same results as direct $N$-way CPD methods. Simulations show that, compared with state-of-the-art CPD methods, the proposed method is more efficient and escape from local solutions more easily.", "source": "arxiv/ml"}
{"id": "arxiv:2393", "title": "Sequence Transduction with Recurrent Neural Networks", "text": "Many machine learning tasks can be expressed as the transformation---or \\emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating. Recurrent neural networks (RNNs) are a powerful sequence learning architecture that has proven capable of learning such representations. However RNNs traditionally require a pre-defined alignment between the input and output sequences to perform transduction. This is a severe limitation since \\emph{finding} the alignment is the most difficult aspect of many sequence transduction problems. Indeed, even determining the length of the output sequence is often challenging. This paper introduces an end-to-end, probabilistic sequence transduction system, based entirely on RNNs, that is in principle able to transform any input sequence into any finite, discrete output sequence. Experimental results for phoneme recognition are provided on the TIMIT speech corpus.", "source": "arxiv/ml"}
{"id": "arxiv:2394", "title": "Objective Improvement in Information-Geometric Optimization", "text": "Information-Geometric Optimization (IGO) is a unified framework of stochastic algorithms for optimization problems. Given a family of probability distributions, IGO turns the original optimization problem into a new maximization problem on the parameter space of the probability distributions. IGO updates the parameter of the probability distribution along the natural gradient, taken with respect to the Fisher metric on the parameter manifold, aiming at maximizing an adaptive transform of the objective function. IGO recovers several known algorithms as particular instances: for the family of Bernoulli distributions IGO recovers PBIL, for the family of Gaussian distributions the pure rank-mu CMA-ES update is recovered, and for exponential families in expectation parametrization the cross-entropy/ML method is recovered. This article provides a theoretical justification for the IGO framework, by proving that any step size not greater than 1 guarantees monotone improvement over the course of optimization, in terms of q-quantile values of the objective function f. The range of admissible step sizes is independent of f and its domain. We extend the result to cover the case of different step sizes for blocks of the parameters in the IGO algorithm. Moreover, we prove that expected fitness improves over time when fitness-proportional selection is applied, in which case the RPP algorithm is recovered.", "source": "arxiv/ml"}
{"id": "arxiv:2395", "title": "On Calibrated Predictions for Auction Selection Mechanisms", "text": "Calibration is a basic property for prediction systems, and algorithms for achieving it are well-studied in both statistics and machine learning. In many applications, however, the predictions are used to make decisions that select which observations are made. This makes calibration difficult, as adjusting predictions to achieve calibration changes future data. We focus on click-through-rate (CTR) prediction for search ad auctions. Here, CTR predictions are used by an auction that determines which ads are shown, and we want to maximize the value generated by the auction. We show that certain natural notions of calibration can be impossible to achieve, depending on the details of the auction. We also show that it can be impossible to maximize auction efficiency while using calibrated predictions. Finally, we give conditions under which calibration is achievable and simultaneously maximizes auction efficiency: roughly speaking, bids and queries must not contain information about CTRs that is not already captured by the predictions.", "source": "arxiv/ml"}
{"id": "arxiv:2396", "title": "Lasso Screening Rules via Dual Polytope Projection", "text": "Lasso is a widely used regression technique to find sparse representations. When the dimension of the feature space and the number of samples are extremely large, solving the Lasso problem remains challenging. To improve the efficiency of solving large-scale Lasso problems, El Ghaoui and his colleagues have proposed the SAFE rules which are able to quickly identify the inactive predictors, i.e., predictors that have $0$ components in the solution vector. Then, the inactive predictors or features can be removed from the optimization problem to reduce its scale. By transforming the standard Lasso to its dual form, it can be shown that the inactive predictors include the set of inactive constraints on the optimal dual solution. In this paper, we propose an efficient and effective screening rule via Dual Polytope Projections (DPP), which is mainly based on the uniqueness and nonexpansiveness of the optimal dual solution due to the fact that the feasible set in the dual space is a convex and closed polytope. Moreover, we show that our screening rule can be extended to identify inactive groups in group Lasso. To the best of our knowledge, there is currently no \"exact\" screening rule for group Lasso. We have evaluated our screening rule using synthetic and real data sets. Results show that our rule is more effective in identifying inactive predictors than existing state-of-the-art screening rules for Lasso.", "source": "arxiv/ml"}
{"id": "arxiv:2397", "title": "The Algebraic Combinatorial Approach for Low-Rank Matrix Completion", "text": "We present a novel algebraic combinatorial view on low-rank matrix completion based on studying relations between a few entries with tools from algebraic geometry and matroid theory. The intrinsic locality of the approach allows for the treatment of single entries in a closed theoretical and practical framework. More specifically, apart from introducing an algebraic combinatorial theory of low-rank matrix completion, we present probability-one algorithms to decide whether a particular entry of the matrix can be completed. We also describe methods to complete that entry from a few others, and to estimate the error which is incurred by any method completing that entry. Furthermore, we show how known results on matrix completion and their sampling assumptions can be related to our new perspective and interpreted in terms of a completability phase transition.", "source": "arxiv/ml"}
{"id": "arxiv:2398", "title": "Data Clustering via Principal Direction Gap Partitioning", "text": "We explore the geometrical interpretation of the PCA based clustering algorithm Principal Direction Divisive Partitioning (PDDP). We give several examples where this algorithm breaks down, and suggest a new method, gap partitioning, which takes into account natural gaps in the data between clusters. Geometric features of the PCA space are derived and illustrated and experimental results are given which show our method is comparable on the datasets used in the original paper on PDDP.", "source": "arxiv/ml"}
{"id": "arxiv:2399", "title": "Efficiently Learning from Revealed Preference", "text": "In this paper, we consider the revealed preferences problem from a learning perspective. Every day, a price vector and a budget is drawn from an unknown distribution, and a rational agent buys his most preferred bundle according to some unknown utility function, subject to the given prices and budget constraint. We wish not only to find a utility function which rationalizes a finite set of observations, but to produce a hypothesis valuation function which accurately predicts the behavior of the agent in the future. We give efficient algorithms with polynomial sample-complexity for agents with linear valuation functions, as well as for agents with linearly separable, concave valuation functions with bounded second derivative.", "source": "arxiv/ml"}
{"id": "arxiv:2400", "title": "What Regularized Auto-Encoders Learn from the Data Generating Distribution", "text": "What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density. We show that the auto-encoder captures the score (derivative of the log-density with respect to the input). It contradicts previous interpretations of reconstruction error as an energy function. Unlike previous results, the theorems provided here are completely generic and do not depend on the parametrization of the auto-encoder: they show what the auto-encoder would tend to if given enough capacity and examples. These results are for a contractive training criterion we show to be similar to the denoising auto-encoder training criterion with small corruption noise, but with contraction applied on the whole reconstruction function rather than just encoder. Similarly to score matching, one can consider the proposed training criterion as a convenient alternative to maximum likelihood because it does not involve a partition function. Finally, we show how an approximate Metropolis-Hastings MCMC can be setup to recover samples from the estimated distribution, and this is confirmed in sampling experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2401", "title": "Application of three graph Laplacian based semi-supervised learning methods to protein function prediction problem", "text": "Protein function prediction is the important problem in modern biology. In this paper, the un-normalized, symmetric normalized, and random walk graph Laplacian based semi-supervised learning methods will be applied to the integrated network combined from multiple networks to predict the functions of all yeast proteins in these multiple networks. These multiple networks are network created from Pfam domain structure, co-participation in a protein complex, protein-protein interaction network, genetic interaction network, and network created from cell cycle gene expression measurements. Multiple networks are combined with fixed weights instead of using convex optimization to determine the combination weights due to high time complexity of convex optimization method. This simple combination method will not affect the accuracy performance measures of the three semi-supervised learning methods. Experiment results show that the un-normalized and symmetric normalized graph Laplacian based methods perform slightly better than random walk graph Laplacian based method for integrated network. Moreover, the accuracy performance measures of these three semi-supervised learning methods for integrated network are much better than the best accuracy performance measures of these three methods for the individual network.", "source": "arxiv/ml"}
{"id": "arxiv:2402", "title": "Bayesian nonparametric models for ranked data", "text": "We develop a Bayesian nonparametric extension of the popular Plackett-Luce choice model that can handle an infinite number of choice items. Our framework is based on the theory of random atomic measures, with the prior specified by a gamma process. We derive a posterior characterization and a simple and effective Gibbs sampler for posterior simulation. We develop a time-varying extension of our model, and apply it to the New York Times lists of weekly bestselling books.", "source": "arxiv/ml"}
{"id": "arxiv:2403", "title": "A Sensing Policy Based on Confidence Bounds and a Restless Multi-Armed Bandit Model", "text": "A sensing policy for the restless multi-armed bandit problem with stationary but unknown reward distributions is proposed. The work is presented in the context of cognitive radios in which the bandit problem arises when deciding which parts of the spectrum to sense and exploit. It is shown that the proposed policy attains asymptotically logarithmic weak regret rate when the rewards are bounded independent and identically distributed or finite state Markovian. Simulation results verifying uniformly logarithmic weak regret are also presented. The proposed policy is a centrally coordinated index policy, in which the index of a frequency band is comprised of a sample mean term and a confidence term. The sample mean term promotes spectrum exploitation whereas the confidence term encourages exploration. The confidence term is designed such that the time interval between consecutive sensing instances of any suboptimal band grows exponentially. This exponential growth between suboptimal sensing time instances leads to logarithmically growing weak regret. Simulation results demonstrate that the proposed policy performs better than other similar methods in the literature.", "source": "arxiv/ml"}
{"id": "arxiv:2404", "title": "Mixture Gaussian Process Conditional Heteroscedasticity", "text": "Generalized autoregressive conditional heteroscedasticity (GARCH) models have long been considered as one of the most successful families of approaches for volatility modeling in financial return series. In this paper, we propose an alternative approach based on methodologies widely used in the field of statistical machine learning. Specifically, we propose a novel nonparametric Bayesian mixture of Gaussian process regression models, each component of which models the noise variance process that contaminates the observed data as a separate latent Gaussian process driven by the observed data. This way, we essentially obtain a mixture Gaussian process conditional heteroscedasticity (MGPCH) model for volatility modeling in financial return series. We impose a nonparametric prior with power-law nature over the distribution of the model mixture components, namely the Pitman-Yor process prior, to allow for better capturing modeled data distributions with heavy tails and skewness. Finally, we provide a copula- based approach for obtaining a predictive posterior for the covariances over the asset returns modeled by means of a postulated MGPCH model. We evaluate the efficacy of our approach in a number of benchmark scenarios, and compare its performance to state-of-the-art methodologies.", "source": "arxiv/ml"}
{"id": "arxiv:2405", "title": "Hypothesis Testing in Feedforward Networks with Broadcast Failures", "text": "Consider a countably infinite set of nodes, which sequentially make decisions between two given hypotheses. Each node takes a measurement of the underlying truth, observes the decisions from some immediate predecessors, and makes a decision between the given hypotheses. We consider two classes of broadcast failures: 1) each node broadcasts a decision to the other nodes, subject to random erasure in the form of a binary erasure channel; 2) each node broadcasts a randomly flipped decision to the other nodes in the form of a binary symmetric channel. We are interested in whether there exists a decision strategy consisting of a sequence of likelihood ratio tests such that the node decisions converge in probability to the underlying truth. In both cases, we show that if each node only learns from a bounded number of immediate predecessors, then there does not exist a decision strategy such that the decisions converge in probability to the underlying truth. However, in case 1, we show that if each node learns from an unboundedly growing number of predecessors, then the decisions converge in probability to the underlying truth, even when the erasure probabilities converge to 1. We also derive the convergence rate of the error probability. In case 2, we show that if each node learns from all of its previous predecessors, then the decisions converge in probability to the underlying truth when the flipping probabilities of the binary symmetric channels are bounded away from 1/2. In the case where the flipping probabilities converge to 1/2, we derive a necessary condition on the convergence rate of the flipping probabilities such that the decisions still converge to the underlying truth. We also explicitly characterize the relationship between the convergence rate of the error probability and the convergence rate of the flipping probabilities.", "source": "arxiv/ml"}
{"id": "arxiv:2406", "title": "Forest Sparsity for Multi-channel Compressive Sensing", "text": "In this paper, we investigate a new compressive sensing model for multi-channel sparse data where each channel can be represented as a hierarchical tree and different channels are highly correlated. Therefore, the full data could follow the forest structure and we call this property as \\emph{forest sparsity}. It exploits both intra- and inter- channel correlations and enriches the family of existing model-based compressive sensing theories. The proposed theory indicates that only $\\mathcal{O}(Tk+\\log(N/k))$ measurements are required for multi-channel data with forest sparsity, where $T$ is the number of channels, $N$ and $k$ are the length and sparsity number of each channel respectively. This result is much better than $\\mathcal{O}(Tk+T\\log(N/k))$ of tree sparsity, $\\mathcal{O}(Tk+k\\log(N/k))$ of joint sparsity, and far better than $\\mathcal{O}(Tk+Tk\\log(N/k))$ of standard sparsity. In addition, we extend the forest sparsity theory to the multiple measurement vectors problem, where the measurement matrix is a block-diagonal matrix. The result shows that the required measurement bound can be the same as that for dense random measurement matrix, when the data shares equal energy in each channel. A new algorithm is developed and applied on four example applications to validate the benefit of the proposed model. Extensive experiments demonstrate the effectiveness and efficiency of the proposed theory and algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2407", "title": "A unifying representation for a class of dependent random measures", "text": "We present a general construction for dependent random measures based on thinning Poisson processes on an augmented space. The framework is not restricted to dependent versions of a specific nonparametric model, but can be applied to all models that can be represented using completely random measures. Several existing dependent random measures can be seen as specific cases of this framework. Interesting properties of the resulting measures are derived and the efficacy of the framework is demonstrated by constructing a covariate-dependent latent feature model and topic model that obtain superior predictive performance.", "source": "arxiv/ml"}
{"id": "arxiv:2408", "title": "A survey of non-exchangeable priors for Bayesian nonparametric models", "text": "Dependent nonparametric processes extend distributions over measures, such as the Dirichlet process and the beta process, to give distributions over collections of measures, typically indexed by values in some covariate space. Such models are appropriate priors when exchangeability assumptions do not hold, and instead we want our model to vary fluidly with some set of covariates. Since the concept of dependent nonparametric processes was formalized by MacEachern [1], there have been a number of models proposed and used in the statistics and machine learning literatures. Many of these models exhibit underlying similarities, an understanding of which, we hope, will help in selecting an appropriate prior, developing new models, and leveraging inference techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2409", "title": "Domain Adaptations for Computer Vision Applications", "text": "A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a particular `source' domain while inference is needed in another, `target' domain. Domain adaptation methods leverage labeled data from both domains to improve classification on unseen data in the target domain. In this work we survey domain transfer learning methods for various application domains with focus on recent work in Computer Vision.", "source": "arxiv/ml"}
{"id": "arxiv:2410", "title": "A Traveling Salesman Learns Bayesian Networks", "text": "Structure learning of Bayesian networks is an important problem that arises in numerous machine learning applications. In this work, we present a novel approach for learning the structure of Bayesian networks using the solution of an appropriately constructed traveling salesman problem. In our approach, one computes an optimal ordering (partially ordered set) of random variables using methods for the traveling salesman problem. This ordering significantly reduces the search space for the subsequent greedy optimization that computes the final structure of the Bayesian network. We demonstrate our approach of learning Bayesian networks on real world census and weather datasets. In both cases, we demonstrate that the approach very accurately captures dependencies between random variables. We check the accuracy of the predictions based on independent studies in both application domains.", "source": "arxiv/ml"}
{"id": "arxiv:2411", "title": "Fast Marginalized Block Sparse Bayesian Learning Algorithm", "text": "The performance of sparse signal recovery from noise corrupted, underdetermined measurements can be improved if both sparsity and correlation structure of signals are exploited. One typical correlation structure is the intra-block correlation in block sparse signals. To exploit this structure, a framework, called block sparse Bayesian learning (BSBL), has been proposed recently. Algorithms derived from this framework showed superior performance but they are not very fast, which limits their applications. This work derives an efficient algorithm from this framework, using a marginalized likelihood maximization method. Compared to existing BSBL algorithms, it has close recovery performance but is much faster. Therefore, it is more suitable for large scale datasets and applications requiring real-time implementation.", "source": "arxiv/ml"}
{"id": "arxiv:2412", "title": "Bayesian nonparametric Plackett-Luce models for the analysis of preferences for college degree programmes", "text": "In this paper we propose a Bayesian nonparametric model for clustering partial ranking data. We start by developing a Bayesian nonparametric extension of the popular Plackett-Luce choice model that can handle an infinite number of choice items. Our framework is based on the theory of random atomic measures, with the prior specified by a completely random measure. We characterise the posterior distribution given data, and derive a simple and effective Gibbs sampler for posterior simulation. We then develop a Dirichlet process mixture extension of our model and apply it to investigate the clustering of preferences for college degree programmes amongst Irish secondary school graduates. The existence of clusters of applicants who have similar preferences for degree programmes is established and we determine that subject matter and geographical location of the third level institution characterise these clusters.", "source": "arxiv/ml"}
{"id": "arxiv:2413", "title": "On the difficulty of training Recurrent Neural Networks", "text": "There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying issues by exploring these problems from an analytical, a geometric and a dynamical systems perspective. Our analysis is used to justify a simple yet effective solution. We propose a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section.", "source": "arxiv/ml"}
{"id": "arxiv:2414", "title": "Optimally fuzzy temporal memory", "text": "Any learner with the ability to predict the future of a structured time-varying signal must maintain a memory of the recent past. If the signal has a characteristic timescale relevant to future prediction, the memory can be a simple shift register---a moving window extending into the past, requiring storage resources that linearly grows with the timescale to be represented. However, an independent general purpose learner cannot a priori know the characteristic prediction-relevant timescale of the signal. Moreover, many naturally occurring signals show scale-free long range correlations implying that the natural prediction-relevant timescale is essentially unbounded. Hence the learner should maintain information from the longest possible timescale allowed by resource availability. Here we construct a fuzzy memory system that optimally sacrifices the temporal accuracy of information in a scale-free fashion in order to represent prediction-relevant information from exponentially long timescales. Using several illustrative examples, we demonstrate the advantage of the fuzzy memory system over a shift register in time series forecasting of natural signals. When the available storage resources are limited, we suggest that a general purpose learner would be better off committing to such a fuzzy memory system.", "source": "arxiv/ml"}
{"id": "arxiv:2415", "title": "Service Composition Design Pattern for Autonomic Computing Systems using Association Rule based Learning and Service-Oriented Architecture", "text": "In this paper we present a Service Injection and composition Design Pattern for Unstructured Peer-to-Peer networks, which is designed with Aspect-oriented design patterns, and amalgamation of the Strategy, Worker Object, and Check-List Design Patterns used to design the Self-Adaptive Systems. It will apply self reconfiguration planes dynamically without the interruption or intervention of the administrator for handling service failures at the servers. When a client requests for a complex service, Service Composition should be done to fulfil the request. If a service is not available in the memory, it will be injected as Aspectual Feature Module code. We used Service Oriented Architecture (SOA) with Web Services in Java to Implement the composite Design Pattern. As far as we know, there are no studies on composition of design patterns for Peer-to-peer computing domain. The pattern is described using a java-like notation for the classes and interfaces. A simple UML class and Sequence diagrams are depicted.", "source": "arxiv/ml"}
{"id": "arxiv:2416", "title": "Analysis of a randomized approximation scheme for matrix multiplication", "text": "This note gives a simple analysis of a randomized approximation scheme for matrix multiplication proposed by Sarlos (2006) based on a random rotation followed by uniform column sampling. The result follows from a matrix version of Bernstein's inequality and a tail inequality for quadratic forms in subgaussian random vectors.", "source": "arxiv/ml"}
{"id": "arxiv:2417", "title": "Theano: new features and speed improvements", "text": "Theano is a linear algebra compiler that optimizes a user's symbolically-specified mathematical computations to produce efficient low-level implementations. In this paper, we present new features and efficiency improvements to Theano, and benchmarks demonstrating Theano's performance relative to Torch7, a recently introduced machine learning library, and to RNNLM, a C++ library targeted at recurrent neural networks.", "source": "arxiv/ml"}
{"id": "arxiv:2418", "title": "Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions", "text": "We apply the spike-and-slab Restricted Boltzmann Machine (ssRBM) to texture modeling. The ssRBM with tiled-convolution weight sharing (TssRBM) achieves or surpasses the state-of-the-art on texture synthesis and inpainting by parametric models. We also develop a novel RBM model with a spike-and-slab visible layer and binary variables in the hidden layer. This model is designed to be stacked on top of the TssRBM. We show the resulting deep belief network (DBN) is a powerful generative model that improves on single-layer models and is capable of modeling not only single high-resolution and challenging textures but also multiple textures.", "source": "arxiv/ml"}
{"id": "arxiv:2419", "title": "Bayesian learning of noisy Markov decision processes", "text": "We consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, which is shown to be essential for good convergence properties of the MCMC sampler. As an illustration, the method is applied to learning a human controller.", "source": "arxiv/ml"}
{"id": "arxiv:2420", "title": "Online Stochastic Optimization with Multiple Objectives", "text": "In this paper we propose a general framework to characterize and solve the stochastic optimization problems with multiple objectives underlying many real world learning applications. We first propose a projection based algorithm which attains an $O(T^{-1/3})$ convergence rate. Then, by leveraging on the theory of Lagrangian in constrained optimization, we devise a novel primal-dual stochastic approximation algorithm which attains the optimal convergence rate of $O(T^{-1/2})$ for general Lipschitz continuous objectives.", "source": "arxiv/ml"}
{"id": "arxiv:2421", "title": "Random Projections for Linear Support Vector Machines", "text": "Let X be a data matrix of rank \\rho, whose rows represent n points in d-dimensional space. The linear support vector machine constructs a hyperplane separator that maximizes the 1-norm soft margin. We develop a new oblivious dimension reduction technique which is precomputed and can be applied to any input matrix X. We prove that, with high probability, the margin and minimum enclosing ball in the feature space are preserved to within \\epsilon-relative error, ensuring comparable generalization as in the original space in the case of classification. For regression, we show that the margin is preserved to \\epsilon-relative error with high probability. We present extensive experiments with real and synthetic data to support our theory.", "source": "arxiv/ml"}
{"id": "arxiv:2422", "title": "The Interplay Between Stability and Regret in Online Learning", "text": "This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given stability, bounded forward regret is equivalent to bounded regret. We also show that the existence of an algorithm with bounded regret implies the existence of a stable algorithm with bounded regret and bounded forward regret. The equivalence results apply to general, possibly non-convex problems. To the best of our knowledge, our analysis provides the first general connection between stability and regret in the online setting that is not restricted to a particular class of algorithms. Our stability-regret connection provides a simple recipe for analyzing regret incurred by any online learning algorithm. Using our framework, we analyze several existing online learning algorithms as well as the \"approximate\" versions of algorithms like RDA that solve an optimization problem at each iteration. Our proofs are simpler than existing analysis for the respective algorithms, show a clear trade-off between stability and forward regret, and provide tighter regret bounds in some cases. Furthermore, using our recipe, we analyze \"approximate\" versions of several algorithms such as follow-the-regularized-leader (FTRL) that requires solving an optimization problem at each step.", "source": "arxiv/ml"}
{"id": "arxiv:2423", "title": "A simple non-parametric Topic Mixture for Authors and Documents", "text": "This article reviews the Author-Topic Model and presents a new non-parametric extension based on the Hierarchical Dirichlet Process. The extension is especially suitable when no prior information about the number of components necessary is available. A blocked Gibbs sampler is described and focus put on staying as close as possible to the original model with only the minimum of theoretical and implementation overhead necessary.", "source": "arxiv/ml"}
{"id": "arxiv:2424", "title": "Duality between subgradient and conditional gradient methods", "text": "Given a convex optimization problem and its dual, there are many possible first-order algorithms. In this paper, we show the equivalence between mirror descent algorithms and algorithms generalizing the conditional gradient method. This is done through convex duality, and implies notably that for certain problems, such as for supervised machine learning problems with non-smooth losses or problems regularized by non-smooth regularizers, the primal subgradient method and the dual conditional gradient method are formally equivalent. The dual interpretation leads to a form of line search for mirror descent, as well as guarantees of convergence for primal-dual certificates.", "source": "arxiv/ml"}
{"id": "arxiv:2425", "title": "An Approach of Improving Students Academic Performance by using k means clustering algorithm and Decision tree", "text": "Improving students academic performance is not an easy task for the academic community of higher learning. The academic performance of engineering and science students during their first year at university is a turning point in their educational path and usually encroaches on their General Point Average,GPA in a decisive manner. The students evaluation factors like class quizzes mid and final exam assignment lab work are studied. It is recommended that all these correlated information should be conveyed to the class teacher before the conduction of final exam. This study will help the teachers to reduce the drop out ratio to a significant level and improve the performance of students. In this paper, we present a hybrid procedure based on Decision Tree of Data mining method and Data Clustering that enables academicians to predict students GPA and based on that instructor can take necessary step to improve student academic performance.", "source": "arxiv/ml"}
{"id": "arxiv:2426", "title": "Multi-Target Regression via Input Space Expansion: Treating Targets as Inputs", "text": "In many practical applications of supervised learning the task involves the prediction of multiple target variables from a common set of input variables. When the prediction targets are binary the task is called multi-label classification, while when the targets are continuous the task is called multi-target regression. In both tasks, target variables often exhibit statistical dependencies and exploiting them in order to improve predictive accuracy is a core challenge. A family of multi-label classification methods address this challenge by building a separate model for each target on an expanded input space where other targets are treated as additional input variables. Despite the success of these methods in the multi-label classification domain, their applicability and effectiveness in multi-target regression has not been studied until now. In this paper, we introduce two new methods for multi-target regression, called Stacked Single-Target and Ensemble of Regressor Chains, by adapting two popular multi-label classification methods of this family. Furthermore, we highlight an inherent problem of these methods - a discrepancy of the values of the additional input variables between training and prediction - and develop extensions that use out-of-sample estimates of the target variables during training in order to tackle this problem. The results of an extensive experimental evaluation carried out on a large and diverse collection of datasets show that, when the discrepancy is appropriately mitigated, the proposed methods attain consistent improvements over the independent regressions baseline. Moreover, two versions of Ensemble of Regression Chains perform significantly better than four state-of-the-art methods including regularization-based multi-task learning methods and a multi-objective random forest approach.", "source": "arxiv/ml"}
{"id": "arxiv:2427", "title": "TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks", "text": "Recent works have validated the possibility of improving energy efficiency in radio access networks (RANs), achieved by dynamically turning on/off some base stations (BSs). In this paper, we extend the research over BS switching operations, which should match up with traffic load variations. Instead of depending on the dynamic traffic loads which are still quite challenging to precisely forecast, we firstly formulate the traffic variations as a Markov decision process. Afterwards, in order to foresightedly minimize the energy consumption of RANs, we design a reinforcement learning framework based BS switching operation scheme. Furthermore, to avoid the underlying curse of dimensionality in reinforcement learning, a transfer actor-critic algorithm (TACT), which utilizes the transferred learning expertise in historical periods or neighboring regions, is proposed and provably converges. In the end, we evaluate our proposed scheme by extensive simulations under various practical configurations and show that the proposed TACT algorithm contributes to a performance jumpstart and demonstrates the feasibility of significant energy efficiency improvement at the expense of tolerable delay performance.", "source": "arxiv/ml"}
{"id": "arxiv:2428", "title": "Nonparametric Bayesian Mixed-effect Model: a Sparse Gaussian Process Approach", "text": "Multi-task learning models using Gaussian processes (GP) have been developed and successfully applied in various applications. The main difficulty with this approach is the computational cost of inference using the union of examples from all tasks. Therefore sparse solutions, that avoid using the entire data directly and instead use a set of informative \"representatives\" are desirable. The paper investigates this problem for the grouped mixed-effect GP model where each individual response is given by a fixed-effect, taken from one of a set of unknown groups, plus a random individual effect function that captures variations among individuals. Such models have been widely used in previous work but no sparse solutions have been developed. The paper presents the first sparse solution for such problems, showing how the sparse approximation can be obtained by maximizing a variational lower bound on the marginal likelihood, generalizing ideas from single-task Gaussian processes to handle the mixed-effect model as well as grouping. Experiments using artificial and real data validate the approach showing that it can recover the performance of inference with the full sample, that it outperforms baseline methods, and that it outperforms state of the art sparse solutions for other multi-task GP formulations.", "source": "arxiv/ml"}
{"id": "arxiv:2429", "title": "Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative Matrices", "text": "Although nonnegative matrix factorization (NMF) is NP-hard in general, it has been shown very recently that it is tractable under the assumption that the input nonnegative data matrix is close to being separable (separability requires that all columns of the input matrix belongs to the cone spanned by a small subset of these columns). Since then, several algorithms have been designed to handle this subclass of NMF problems. In particular, Bittorf, Recht, R\\'e and Tropp (`Factoring nonnegative matrices with linear programs', NIPS 2012) proposed a linear programming model, referred to as Hottopixx. In this paper, we provide a new and more general robustness analysis of their method. In particular, we design a provably more robust variant using a post-processing strategy which allows us to deal with duplicates and near duplicates in the dataset.", "source": "arxiv/ml"}
{"id": "arxiv:2430", "title": "Graph Laplacians on Singular Manifolds: Toward understanding complex spaces: graph Laplacians on manifolds with singularities and boundaries", "text": "Recently, much of the existing work in manifold learning has been done under the assumption that the data is sampled from a manifold without boundaries and singularities or that the functions of interest are evaluated away from such points. At the same time, it can be argued that singularities and boundaries are an important aspect of the geometry of realistic data. In this paper we consider the behavior of graph Laplacians at points at or near boundaries and two main types of other singularities: intersections, where different manifolds come together and sharp \"edges\", where a manifold sharply changes direction. We show that the behavior of graph Laplacian near these singularities is quite different from that in the interior of the manifolds. In fact, a phenomenon somewhat reminiscent of the Gibbs effect in the analysis of Fourier series, can be observed in the behavior of graph Laplacian near such points. Unlike in the interior of the domain, where graph Laplacian converges to the Laplace-Beltrami operator, near singularities graph Laplacian tends to a first-order differential operator, which exhibits different scaling behavior as a function of the kernel width. One important implication is that while points near the singularities occupy only a small part of the total volume, the difference in scaling results in a disproportionately large contribution to the total behavior. Another significant finding is that while the scaling behavior of the operator is the same near different types of singularities, they are very distinct at a more refined level of analysis. We believe that a comprehensive understanding of these structures in addition to the standard case of a smooth manifold can take us a long way toward better methods for analysis of complex non-linear data and can lead to significant progress in algorithm design.", "source": "arxiv/ml"}
{"id": "arxiv:2431", "title": "On unbiased performance evaluation for protein inference", "text": "This letter is a response to the comments of Serang (2012) on Huang and He (2012) in Bioinformatics. Serang (2012) claimed that the parameters for the Fido algorithm should be specified using the grid search method in Serang et al. (2010) so as to generate a deserved accuracy in performance comparison. It seems that it is an argument on parameter tuning. However, it is indeed the issue of how to conduct an unbiased performance evaluation for comparing different protein inference algorithms. In this letter, we would explain why we don't use the grid search for parameter selection in Huang and He (2012) and show that this procedure may result in an over-estimated performance that is unfair to competing algorithms. In fact, this issue has also been pointed out by Li and Radivojac (2012).", "source": "arxiv/ml"}
{"id": "arxiv:2432", "title": "Classification Recouvrante Bas\\'ee sur les M\\'ethodes \\`a Noyau", "text": "Overlapping clustering problem is an important learning issue in which clusters are not mutually exclusive and each object may belongs simultaneously to several clusters. This paper presents a kernel based method that produces overlapping clusters on a high feature space using mercer kernel techniques to improve separability of input patterns. The proposed method, called OKM-K(Overlapping $k$-means based kernel method), extends OKM (Overlapping $k$-means) method to produce overlapping schemes. Experiments are performed on overlapping dataset and empirical results obtained with OKM-K outperform results obtained with OKM.", "source": "arxiv/ml"}
{"id": "arxiv:2433", "title": "Overlapping clustering based on kernel similarity metric", "text": "Producing overlapping schemes is a major issue in clustering. Recent proposed overlapping methods relies on the search of an optimal covering and are based on different metrics, such as Euclidean distance and I-Divergence, used to measure closeness between observations. In this paper, we propose the use of another measure for overlapping clustering based on a kernel similarity metric .We also estimate the number of overlapped clusters using the Gram matrix. Experiments on both Iris and EachMovie datasets show the correctness of the estimation of number of clusters and show that measure based on kernel similarity metric improves the precision, recall and f-measure in overlapping clustering.", "source": "arxiv/ml"}
{"id": "arxiv:2434", "title": "Automating rule generation for grammar checkers", "text": "In this paper, I describe several approaches to automatic or semi-automatic development of symbolic rules for grammar checkers from the information contained in corpora. The rules obtained this way are an important addition to manually-created rules that seem to dominate in rule-based checkers. However, the manual process of creation of rules is costly, time-consuming and error-prone. It seems therefore advisable to use machine-learning algorithms to create the rules automatically or semi-automatically. The results obtained seem to corroborate my initial hypothesis that symbolic machine learning algorithms can be useful for acquiring new rules for grammar checking. It turns out, however, that for practical uses, error corpora cannot be the sole source of information used in grammar checking. I suggest therefore that only by using different approaches, grammar-checkers, or more generally, computer-aided proofreading tools, will be able to cover most frequent and severe mistakes and avoid false alarms that seem to distract users.", "source": "arxiv/ml"}
{"id": "arxiv:2435", "title": "On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes", "text": "We consider infinite-horizon stationary $\\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. Using Value and Policy Iteration with some error $\\epsilon$ at each iteration, it is well-known that one can compute stationary policies that are $\\frac{2\\gamma}{(1-\\gamma)^2}\\epsilon$-optimal. After arguing that this guarantee is tight, we develop variations of Value and Policy Iteration for computing non-stationary policies that can be up to $\\frac{2\\gamma}{1-\\gamma}\\epsilon$-optimal, which constitutes a significant improvement in the usual situation when $\\gamma$ is close to 1. Surprisingly, this shows that the problem of \"computing near-optimal non-stationary policies\" is much simpler than that of \"computing near-optimal stationary policies\".", "source": "arxiv/ml"}
{"id": "arxiv:2436", "title": "Learning-Assisted Automated Reasoning with Flyspeck", "text": "The considerable mathematical knowledge encoded by the Flyspeck project is combined with external automated theorem provers (ATPs) and machine-learning premise selection methods trained on the proofs, producing an AI system capable of answering a wide range of mathematical queries automatically. The performance of this architecture is evaluated in a bootstrapping scenario emulating the development of Flyspeck from axioms to the last theorem, each time using only the previous theorems and proofs. It is shown that 39% of the 14185 theorems could be proved in a push-button mode (without any high-level advice and user interaction) in 30 seconds of real time on a fourteen-CPU workstation. The necessary work involves: (i) an implementation of sound translations of the HOL Light logic to ATP formalisms: untyped first-order, polymorphic typed first-order, and typed higher-order, (ii) export of the dependency information from HOL Light and ATP proofs for the machine learners, and (iii) choice of suitable representations and methods for learning from previous proofs, and their integration as advisors with HOL Light. This work is described and discussed here, and an initial analysis of the body of proofs that were found fully automatically is provided.", "source": "arxiv/ml"}
{"id": "arxiv:2437", "title": "Orientation Determination from Cryo-EM images Using Least Unsquared Deviation", "text": "A major challenge in single particle reconstruction from cryo-electron microscopy is to establish a reliable ab-initio three-dimensional model using two-dimensional projection images with unknown orientations. Common-lines based methods estimate the orientations without additional geometric information. However, such methods fail when the detection rate of common-lines is too low due to the high level of noise in the images. An approximation to the least squares global self consistency error was obtained using convex relaxation by semidefinite programming. In this paper we introduce a more robust global self consistency error and show that the corresponding optimization problem can be solved via semidefinite relaxation. In order to prevent artificial clustering of the estimated viewing directions, we further introduce a spectral norm term that is added as a constraint or as a regularization term to the relaxed minimization problem. The resulted problems are solved by using either the alternating direction method of multipliers or an iteratively reweighted least squares procedure. Numerical experiments with both simulated and real images demonstrate that the proposed methods significantly reduce the orientation estimation error when the detection rate of common-lines is low.", "source": "arxiv/ml"}
{"id": "arxiv:2438", "title": "A recursive divide-and-conquer approach for sparse principal component analysis", "text": "In this paper, a new method is proposed for sparse PCA based on the recursive divide-and-conquer methodology. The main idea is to separate the original sparse PCA problem into a series of much simpler sub-problems, each having a closed-form solution. By recursively solving these sub-problems in an analytical way, an efficient algorithm is constructed to solve the sparse PCA problem. The algorithm only involves simple computations and is thus easy to implement. The proposed method can also be very easily extended to other sparse PCA problems with certain constraints, such as the nonnegative sparse PCA problem. Furthermore, we have shown that the proposed algorithm converges to a stationary point of the problem, and its computational complexity is approximately linear in both data size and dimensionality. The effectiveness of the proposed method is substantiated by extensive experiments implemented on a series of synthetic and real data in both reconstruction-error-minimization and data-variance-maximization viewpoints.", "source": "arxiv/ml"}
{"id": "arxiv:2439", "title": "Efficient algorithms for robust recovery of images from compressed data", "text": "Compressed sensing (CS) is an important theory for sub-Nyquist sampling and recovery of compressible data. Recently, it has been extended by Pham and Venkatesh to cope with the case where corruption to the CS data is modeled as impulsive noise. The new formulation, termed as robust CS, combines robust statistics and CS into a single framework to suppress outliers in the CS recovery. To solve the newly formulated robust CS problem, Pham and Venkatesh suggested a scheme that iteratively solves a number of CS problems, the solutions from which converge to the true robust compressed sensing solution. However, this scheme is rather inefficient as it has to use existing CS solvers as a proxy. To overcome limitation with the original robust CS algorithm, we propose to solve the robust CS problem directly in this paper and drive more computationally efficient algorithms by following latest advances in large-scale convex optimization for non-smooth regularization. Furthermore, we also extend the robust CS formulation to various settings, including additional affine constraints, $\\ell_1$-norm loss function, mixed-norm regularization, and multi-tasking, so as to further improve robust CS. We also derive simple but effective algorithms to solve these extensions. We demonstrate that the new algorithms provide much better computational advantage over the original robust CS formulation, and effectively solve more sophisticated extensions where the original methods simply cannot. We demonstrate the usefulness of the extensions on several CS imaging tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2440", "title": "Approximate Rank-Detecting Factorization of Low-Rank Tensors", "text": "We present an algorithm, AROFAC2, which detects the (CP-)rank of a degree 3 tensor and calculates its factorization into rank-one components. We provide generative conditions for the algorithm to work and demonstrate on both synthetic and real world data that AROFAC2 is a potentially outperforming alternative to the gold standard PARAFAC over which it has the advantages that it can intrinsically detect the true rank, avoids spurious components, and is stable with respect to outliers and non-Gaussian noise.", "source": "arxiv/ml"}
{"id": "arxiv:2441", "title": "Cumulative Step-size Adaptation on Linear Functions", "text": "The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies the CSA-ES on composites of strictly increasing functions with affine linear functions through the investigation of its underlying Markov chains. Rigorous results on the change and the variation of the step size are derived with and without cumulation. The step-size diverges geometrically fast in most cases. Furthermore, the influence of the cumulation parameter is studied.", "source": "arxiv/ml"}
{"id": "arxiv:2442", "title": "Pedestrian Detection with Unsupervised Multi-Stage Feature Learning", "text": "Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.", "source": "arxiv/ml"}
{"id": "arxiv:2443", "title": "Message-Passing Algorithms for Quadratic Minimization", "text": "Gaussian belief propagation (GaBP) is an iterative algorithm for computing the mean of a multivariate Gaussian distribution, or equivalently, the minimum of a multivariate positive definite quadratic function. Sufficient conditions, such as walk-summability, that guarantee the convergence and correctness of GaBP are known, but GaBP may fail to converge to the correct solution given an arbitrary positive definite quadratic function. As was observed in previous work, the GaBP algorithm fails to converge if the computation trees produced by the algorithm are not positive definite. In this work, we will show that the failure modes of the GaBP algorithm can be understood via graph covers, and we prove that a parameterized generalization of the min-sum algorithm can be used to ensure that the computation trees remain positive definite whenever the input matrix is positive definite. We demonstrate that the resulting algorithm is closely related to other iterative schemes for quadratic minimization such as the Gauss-Seidel and Jacobi algorithms. Finally, we observe, empirically, that there always exists a choice of parameters such that the above generalization of the GaBP algorithm converges.", "source": "arxiv/ml"}
{"id": "arxiv:2444", "title": "Hypergraph and protein function prediction with gene expression data", "text": "Most network-based protein (or gene) function prediction methods are based on the assumption that the labels of two adjacent proteins in the network are likely to be the same. However, assuming the pairwise relationship between proteins or genes is not complete, the information a group of genes that show very similar patterns of expression and tend to have similar functions (i.e. the functional modules) is missed. The natural way overcoming the information loss of the above assumption is to represent the gene expression data as the hypergraph. Thus, in this paper, the three un-normalized, random walk, and symmetric normalized hypergraph Laplacian based semi-supervised learning methods applied to hypergraph constructed from the gene expression data in order to predict the functions of yeast proteins are introduced. Experiment results show that the average accuracy performance measures of these three hypergraph Laplacian based semi-supervised learning methods are the same. However, their average accuracy performance measures of these three methods are much greater than the average accuracy performance measures of un-normalized graph Laplacian based semi-supervised learning method (i.e. the baseline method of this paper) applied to gene co-expression network created from the gene expression data.", "source": "arxiv/ml"}
{"id": "arxiv:2445", "title": "Nonparametric risk bounds for time-series forecasting", "text": "We derive generalization error bounds for traditional time-series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space models. These non-asymptotic bounds need only weak assumptions on the data-generating process, yet allow forecasters to select among competing models and to guarantee, with high probability, that their chosen model will perform well. We motivate our techniques with and apply them to standard economic and financial forecasting tools---a GARCH model for predicting equity volatility and a dynamic stochastic general equilibrium model (DSGE), the standard tool in macroeconomic forecasting. We demonstrate in particular how our techniques can aid forecasters and policy makers in choosing models which behave well under uncertainty and mis-specification.", "source": "arxiv/ml"}
{"id": "arxiv:2446", "title": "Low-rank Matrix Completion using Alternating Minimization", "text": "Alternating minimization represents a widely applicable and empirically successful approach for finding low-rank matrices that best fit the given data. For example, for the problem of low-rank matrix completion, this method is believed to be one of the most accurate and efficient, and formed a major component of the winning entry in the Netflix Challenge. In the alternating minimization approach, the low-rank target matrix is written in a bi-linear form, i.e. $X = UV^\\dag$; the algorithm then alternates between finding the best $U$ and the best $V$. Typically, each alternating step in isolation is convex and tractable. However the overall problem becomes non-convex and there has been almost no theoretical understanding of when this approach yields a good result. In this paper we present first theoretical analysis of the performance of alternating minimization for matrix completion, and the related problem of matrix sensing. For both these problems, celebrated recent results have shown that they become well-posed and tractable once certain (now standard) conditions are imposed on the problem. We show that alternating minimization also succeeds under similar conditions. Moreover, compared to existing results, our paper shows that alternating minimization guarantees faster (in particular, geometric) convergence to the true matrix, while allowing a simpler analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2447", "title": "Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties", "text": "Predicting the response of a specific cancer to a therapy is a major goal in modern oncology that should ultimately lead to a personalised treatment. High-throughput screenings of potentially active compounds against a panel of genomically heterogeneous cancer cell lines have unveiled multiple relationships between genomic alterations and drug responses. Various computational approaches have been proposed to predict sensitivity based on genomic features, while others have used the chemical properties of the drugs to ascertain their effect. In an effort to integrate these complementary approaches, we developed machine learning models to predict the response of cancer cell lines to drug treatment, quantified through IC50 values, based on both the genomic features of the cell lines and the chemical properties of the considered drugs. Models predicted IC50 values in a 8-fold cross-validation and an independent blind test with coefficient of determination R2 of 0.72 and 0.64 respectively. Furthermore, models were able to predict with comparable accuracy (R2 of 0.61) IC50s of cell lines from a tissue not used in the training stage. Our in silico models can be used to optimise the experimental design of drug-cell screenings by estimating a large proportion of missing IC50 values rather than experimentally measure them. The implications of our results go beyond virtual drug screening design: potentially thousands of drugs could be probed in silico to systematically test their potential efficacy as anti-tumour agents based on their structure, thus providing a computational framework to identify new drug repositioning opportunities as well as ultimately be useful for personalized medicine by linking the genomic traits of patients to drug sensitivity.", "source": "arxiv/ml"}
{"id": "arxiv:2448", "title": "An Empirical Evaluation of Portfolios Approaches for solving CSPs", "text": "Recent research in areas such as SAT solving and Integer Linear Programming has shown that the performances of a single arbitrarily efficient solver can be significantly outperformed by a portfolio of possibly slower on-average solvers. We report an empirical evaluation and comparison of portfolio approaches applied to Constraint Satisfaction Problems (CSPs). We compared models developed on top of off-the-shelf machine learning algorithms with respect to approaches used in the SAT field and adapted for CSPs, considering different portfolio sizes and using as evaluation metrics the number of solved problems and the time taken to solve them. Results indicate that the best SAT approaches have top performances also in the CSP field and are slightly more competitive than simple models built on top of classification algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2449", "title": "Training Support Vector Machines Using Frank-Wolfe Optimization Methods", "text": "Training a Support Vector Machine (SVM) requires the solution of a quadratic programming problem (QP) whose computational complexity becomes prohibitively expensive for large scale datasets. Traditional optimization methods cannot be directly applied in these cases, mainly due to memory restrictions. By adopting a slightly different objective function and under mild conditions on the kernel used within the model, efficient algorithms to train SVMs have been devised under the name of Core Vector Machines (CVMs). This framework exploits the equivalence of the resulting learning problem with the task of building a Minimal Enclosing Ball (MEB) problem in a feature space, where data is implicitly embedded by a kernel function. In this paper, we improve on the CVM approach by proposing two novel methods to build SVMs based on the Frank-Wolfe algorithm, recently revisited as a fast method to approximate the solution of a MEB problem. In contrast to CVMs, our algorithms do not require to compute the solutions of a sequence of increasingly complex QPs and are defined by using only analytic optimization steps. Experiments on a large collection of datasets show that our methods scale better than CVMs in most cases, sometimes at the price of a slightly lower accuracy. As CVMs, the proposed methods can be easily extended to machine learning problems other than binary classification. However, effective classifiers are also obtained using kernels which do not satisfy the condition required by CVMs and can thus be used for a wider set of problems.", "source": "arxiv/ml"}
{"id": "arxiv:2450", "title": "Dynamic recommender system : using cluster-based biases to improve the accuracy of the predictions", "text": "It is today accepted that matrix factorization models allow a high quality of rating prediction in recommender systems. However, a major drawback of matrix factorization is its static nature that results in a progressive declining of the accuracy of the predictions after each factorization. This is due to the fact that the new obtained ratings are not taken into account until a new factorization is computed, which can not be done very often because of the high cost of matrix factorization. In this paper, aiming at improving the accuracy of recommender systems, we propose a cluster-based matrix factorization technique that enables online integration of new ratings. Thus, we significantly enhance the obtained predictions between two matrix factorizations. We use finer-grained user biases by clustering similar items into groups, and allocating in these groups a bias to each user. The experiments we did on large datasets demonstrated the efficiency of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:2451", "title": "Advances in Optimizing Recurrent Networks", "text": "After a more than decade-long period of relatively little research activity in the area of recurrent neural networks, several new developments will be reviewed here that have allowed substantial progress both in understanding and in technical solutions towards more efficient training of recurrent networks. These advances have been motivated by and related to the optimization issues surrounding deep learning. Although recurrent networks are extremely powerful in what they can in principle represent in terms of modelling sequences,their training is plagued by two aspects of the same issue regarding the learning of long-term dependencies. Experiments reported here evaluate the use of clipping gradients, spanning longer time ranges with leaky integration, advanced momentum techniques, using more powerful output probability models, and encouraging sparser gradients to help symmetry breaking and credit assignment. The experiments are performed on text and music data and show off the combined effects of these techniques in generally improving both training and test error.", "source": "arxiv/ml"}
{"id": "arxiv:2452", "title": "Multiclass Diffuse Interface Models for Semi-Supervised Learning on Graphs", "text": "We present a graph-based variational algorithm for multiclass classification of high-dimensional data, motivated by total variation techniques. The energy functional is based on a diffuse interface model with a periodic potential. We augment the model by introducing an alternative measure of smoothness that preserves symmetry among the class labels. Through this modification of the standard Laplacian, we construct an efficient multiclass method that allows for sharp transitions between classes. The experimental results demonstrate that our approach is competitive with the state of the art among other graph-based algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2453", "title": "Evaluating Classifiers Without Expert Labels", "text": "This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottleneck. Instead, we seek methodology for estimating performance of the classifiers which is more scalable than expert labeling yet preserves high correlation with evaluation based on expert labels. We consider both: 1) using only labels automatically generated by the classifiers (blind evaluation); and 2) using labels obtained via crowdsourcing. While crowdsourcing methods are lauded for scalability, using such data for evaluation raises serious concerns given the prevalence of label noise. In regard to blind evaluation, two broad strategies are investigated: combine & score and score & combine methods infer a single pseudo-gold label set by aggregating classifier labels; classifiers are then evaluated based on this single pseudo-gold label set. On the other hand, score & combine methods: 1) sample multiple label sets from classifier outputs, 2) evaluate classifiers on each label set, and 3) average classifier performance across label sets. When additional crowd labels are also collected, we investigate two alternative avenues for exploiting them: 1) direct evaluation of classifiers; or 2) supervision of combine & score methods. To assess generality of our techniques, classifier performance is measured using four common classification metrics, with statistical significance tests. Finally, we measure both score and rank correlations between estimated classifier performance vs. actual performance according to expert judgments. Rigorous evaluation of classifiers from the TREC 2011 Crowdsourcing Track shows reliable evaluation can be achieved without reliance on expert labels.", "source": "arxiv/ml"}
{"id": "arxiv:2454", "title": "Compiling Relational Database Schemata into Probabilistic Graphical Models", "text": "Instead of requiring a domain expert to specify the probabilistic dependencies of the data, in this work we present an approach that uses the relational DB schema to automatically construct a Bayesian graphical model for a database. This resulting model contains customized distributions for columns, latent variables that cluster the data, and factors that reflect and represent the foreign key links. Experiments demonstrate the accuracy of the model and the scalability of inference on synthetic and real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:2455", "title": "Cost-Sensitive Support Vector Machines", "text": "A new procedure for learning cost-sensitive SVM(CS-SVM) classifiers is proposed. The SVM hinge loss is extended to the cost sensitive setting, and the CS-SVM is derived as the minimizer of the associated risk. The extension of the hinge loss draws on recent connections between risk minimization and probability elicitation. These connections are generalized to cost-sensitive classification, in a manner that guarantees consistency with the cost-sensitive Bayes risk, and associated Bayes decision rule. This ensures that optimal decision rules, under the new hinge loss, implement the Bayes-optimal cost-sensitive classification boundary. Minimization of the new hinge loss is shown to be a generalization of the classic SVM optimization problem, and can be solved by identical procedures. The dual problem of CS-SVM is carefully scrutinized by means of regularization theory and sensitivity analysis and the CS-SVM algorithm is substantiated. The proposed algorithm is also extended to cost-sensitive learning with example dependent costs. The minimum cost sensitive risk is proposed as the performance measure and is connected to ROC analysis through vector optimization. The resulting algorithm avoids the shortcomings of previous approaches to cost-sensitive SVM design, and is shown to have superior experimental performance on a large number of cost sensitive and imbalanced datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2456", "title": "Making Early Predictions of the Accuracy of Machine Learning Applications", "text": "The accuracy of machine learning systems is a widely studied research topic. Established techniques such as cross-validation predict the accuracy on unseen data of the classifier produced by applying a given learning method to a given training data set. However, they do not predict whether incurring the cost of obtaining more data and undergoing further training will lead to higher accuracy. In this paper we investigate techniques for making such early predictions. We note that when a machine learning algorithm is presented with a training set the classifier produced, and hence its error, will depend on the characteristics of the algorithm, on training set's size, and also on its specific composition. In particular we hypothesise that if a number of classifiers are produced, and their observed error is decomposed into bias and variance terms, then although these components may behave differently, their behaviour may be predictable. We test our hypothesis by building models that, given a measurement taken from the classifier created from a limited number of samples, predict the values that would be measured from the classifier produced when the full data set is presented. We create separate models for bias, variance and total error. Our models are built from the results of applying ten different machine learning algorithms to a range of data sets, and tested with \"unseen\" algorithms and datasets. We analyse the results for various numbers of initial training samples, and total dataset sizes. Results show that our predictions are very highly correlated with the values observed after undertaking the extra training. Finally we consider the more complex case where an ensemble of heterogeneous classifiers is trained, and show how we can accurately estimate an upper bound on the accuracy achievable after further training.", "source": "arxiv/ml"}
{"id": "arxiv:2457", "title": "On the Convergence Properties of Optimal AdaBoost", "text": "AdaBoost is one of the most popular machine-learning algorithms. It is simple to implement and often found very effective by practitioners, while still being mathematically elegant and theoretically sound. AdaBoost's behavior in practice, and in particular the test-error behavior, has puzzled many eminent researchers for over a decade: It seems to defy our general intuition in machine learning regarding the fundamental trade-off between model complexity and generalization performance. In this paper, we establish the convergence of \"Optimal AdaBoost,\" a term coined by Rudin, Daubechies, and Schapire in 2004. We prove the convergence, with the number of rounds, of the classifier itself, its generalization error, and its resulting margins for fixed data sets, under certain reasonable conditions. More generally, we prove that the time/per-round average of almost any function of the example weights converges. Our approach is to frame AdaBoost as a dynamical system, to provide sufficient conditions for the existence of an invariant measure, and to employ tools from ergodic theory. Unlike previous work, we do not assume AdaBoost cycles; actually, we present empirical evidence against it on real-world datasets. Our main theoretical results hold under a weaker condition. We show sufficient empirical evidence that Optimal AdaBoost always met the condition on every real-world dataset we tried. Our results formally ground future convergence-rate analyses, and may even provide opportunities for slight algorithmic modifications to optimize the generalization ability of AdaBoost classifiers, thus reducing a practitioner's burden of deciding how long to run the algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2458", "title": "Using Wikipedia to Boost SVD Recommender Systems", "text": "Singular Value Decomposition (SVD) has been used successfully in recent years in the area of recommender systems. In this paper we present how this model can be extended to consider both user ratings and information from Wikipedia. By mapping items to Wikipedia pages and quantifying their similarity, we are able to use this information in order to improve recommendation accuracy, especially when the sparsity is high. Another advantage of the proposed approach is the fact that it can be easily integrated into any other SVD implementation, regardless of additional parameters that may have been added to it. Preliminary experimental results on the MovieLens dataset are encouraging.", "source": "arxiv/ml"}
{"id": "arxiv:2459", "title": "On Some Integrated Approaches to Inference", "text": "We present arguments for the formulation of unified approach to different standard continuous inference methods from partial information. It is claimed that an explicit partition of information into a priori (prior knowledge) and a posteriori information (data) is an important way of standardizing inference approaches so that they can be compared on a normative scale, and so that notions of optimal algorithms become farther-reaching. The inference methods considered include neural network approaches, information-based complexity, and Monte Carlo, spline, and regularization methods. The model is an extension of currently used continuous complexity models, with a class of algorithms in the form of optimization methods, in which an optimization functional (involving the data) is minimized. This extends the family of current approaches in continuous complexity theory, which include the use of interpolatory algorithms in worst and average case settings.", "source": "arxiv/ml"}
{"id": "arxiv:2460", "title": "Distributed Adaptive Networks: A Graphical Evolutionary Game-Theoretic View", "text": "Distributed adaptive filtering has been considered as an effective approach for data processing and estimation over distributed networks. Most existing distributed adaptive filtering algorithms focus on designing different information diffusion rules, regardless of the nature evolutionary characteristic of a distributed network. In this paper, we study the adaptive network from the game theoretic perspective and formulate the distributed adaptive filtering problem as a graphical evolutionary game. With the proposed formulation, the nodes in the network are regarded as players and the local combiner of estimation information from different neighbors is regarded as different strategies selection. We show that this graphical evolutionary game framework is very general and can unify the existing adaptive network algorithms. Based on this framework, as examples, we further propose two error-aware adaptive filtering algorithms. Moreover, we use graphical evolutionary game theory to analyze the information diffusion process over the adaptive networks and evolutionarily stable strategy of the system. Finally, simulation results are shown to verify the effectiveness of our analysis and proposed methods.", "source": "arxiv/ml"}
{"id": "arxiv:2461", "title": "Excess risk bounds for multitask learning with trace norm regularization", "text": "Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on the expected norm of sums of random positive semidefinite matrices with subexponential moments.", "source": "arxiv/ml"}
{"id": "arxiv:2462", "title": "Layer-wise learning of deep generative models", "text": "When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. We interpret auto-encoders in this setting as generative models, by showing that they train a lower bound of this criterion. We test the new learning procedure against a state of the art method (stacked RBMs), and find it to improve performance. Both theory and experiments highlight the importance, when training deep architectures, of using an inference model (from data to hidden variables) richer than the generative model (from hidden variables to data).", "source": "arxiv/ml"}
{"id": "arxiv:2463", "title": "Learning Mixtures of Arbitrary Distributions over Large Discrete Domains", "text": "We give an algorithm for learning a mixture of {\\em unstructured} distributions. This problem arises in various unsupervised learning scenarios, for example in learning {\\em topic models} from a corpus of documents spanning several topics. We show how to learn the constituents of a mixture of $k$ arbitrary distributions over a large discrete domain $[n]=\\{1,2,\\dots,n\\}$ and the mixture weights, using $O(n\\polylog n)$ samples. (In the topic-model learning setting, the mixture constituents correspond to the topic distributions.) This task is information-theoretically impossible for $k>1$ under the usual sampling process from a mixture distribution. However, there are situations (such as the above-mentioned topic model case) in which each sample point consists of several observations from the same mixture constituent. This number of observations, which we call the {\\em \"sampling aperture\"}, is a crucial parameter of the problem. We obtain the {\\em first} bounds for this mixture-learning problem {\\em without imposing any assumptions on the mixture constituents.} We show that efficient learning is possible exactly at the information-theoretically least-possible aperture of $2k-1$. Thus, we achieve near-optimal dependence on $n$ and optimal aperture. While the sample-size required by our algorithm depends exponentially on $k$, we prove that such a dependence is {\\em unavoidable} when one considers general mixtures. A sequence of tools contribute to the algorithm, such as concentration results for random matrices, dimension reduction, moment estimations, and sensitivity analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2464", "title": "Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes", "text": "Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness assumptions, which do not apply to many modern applications of SGD with non-smooth objective functions such as support vector machines. In this paper, we investigate the performance of SGD without such smoothness assumptions, as well as a running average scheme to convert the SGD iterates to a solution with optimal optimization accuracy. In this framework, we prove that after T rounds, the suboptimality of the last SGD iterate scales as O(log(T)/\\sqrt{T}) for non-smooth convex objective functions, and O(log(T)/T) in the non-smooth strongly convex case. To the best of our knowledge, these are the first bounds of this kind, and almost match the minimax-optimal rates obtainable by appropriate averaging schemes. We also propose a new and simple averaging scheme, which not only attains optimal rates, but can also be easily computed on-the-fly (in contrast, the suffix averaging scheme proposed in Rakhlin et al. (2011) is not as simple to implement). Finally, we provide some experimental illustrations.", "source": "arxiv/ml"}
{"id": "arxiv:2465", "title": "High-dimensional sequence transduction", "text": "We investigate the problem of transforming an input sequence into a high-dimensional output sequence in order to transcribe polyphonic audio music into symbolic notation. We introduce a probabilistic model based on a recurrent neural network that is able to learn realistic output distributions given the input and we devise an efficient algorithm to search for the global mode of that distribution. The resulting method produces musically plausible transcriptions even under high levels of noise and drastically outperforms previous state-of-the-art approaches on five datasets of synthesized sounds and real recordings, approximately halving the test error rate.", "source": "arxiv/ml"}
{"id": "arxiv:2466", "title": "A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method", "text": "In this note, we present a new averaging technique for the projected stochastic subgradient method. By using a weighted average with a weight of t+1 for each iterate w_t at iteration t, we obtain the convergence rate of O(1/t) with both an easy proof and an easy implementation. The new scheme is compared empirically to existing techniques, with similar performance behavior.", "source": "arxiv/ml"}
{"id": "arxiv:2467", "title": "A class of random fields on complete graphs with tractable partition function", "text": "The aim of this short note is to draw attention to a method by which the partition function and marginal probabilities for a certain class of random fields on complete graphs can be computed in polynomial time. This class includes Ising models with homogeneous pairwise potentials but arbitrary (inhomogeneous) unary potentials. Similarly, the partition function and marginal probabilities can be computed in polynomial time for random fields on complete bipartite graphs, provided they have homogeneous pairwise potentials. We expect that these tractable classes of large scale random fields can be very useful for the evaluation of approximation algorithms by providing exact error estimates.", "source": "arxiv/ml"}
{"id": "arxiv:2468", "title": "Bag-of-Words Representation for Biomedical Time Series Classification", "text": "Automatic analysis of biomedical time series such as electroencephalogram (EEG) and electrocardiographic (ECG) signals has attracted great interest in the community of biomedical engineering due to its important applications in medicine. In this work, a simple yet effective bag-of-words representation that is able to capture both local and global structure similarity information is proposed for biomedical time series representation. In particular, similar to the bag-of-words model used in text document domain, the proposed method treats a time series as a text document and extracts local segments from the time series as words. The biomedical time series is then represented as a histogram of codewords, each entry of which is the count of a codeword appeared in the time series. Although the temporal order of the local segments is ignored, the bag-of-words representation is able to capture high-level structural information because both local and global structural information are well utilized. The performance of the bag-of-words model is validated on three datasets extracted from real EEG and ECG signals. The experimental results demonstrate that the proposed method is not only insensitive to parameters of the bag-of-words model such as local segment length and codebook size, but also robust to noise.", "source": "arxiv/ml"}
{"id": "arxiv:2469", "title": "Runtime Optimizations for Prediction with Tree-Based Models", "text": "Tree-based models have proven to be an effective solution for web ranking as well as other problems in diverse domains. This paper focuses on optimizing the runtime performance of applying such models to make predictions, given an already-trained model. Although exceedingly simple conceptually, most implementations of tree-based models do not efficiently utilize modern superscalar processor architectures. By laying out data structures in memory in a more cache-conscious fashion, removing branches from the execution flow using a technique called predication, and micro-batching predictions using a technique called vectorization, we are able to better exploit modern processor architectures and significantly improve the speed of tree-based models over hard-coded if-else blocks. Our work contributes to the exploration of architecture-conscious runtime implementations of machine learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2470", "title": "PAC-Bayesian Learning and Domain Adaptation", "text": "In machine learning, Domain Adaptation (DA) arises when the distribution gen- erating the test (target) data differs from the one generating the learning (source) data. It is well known that DA is an hard task even under strong assumptions, among which the covariate-shift where the source and target distributions diverge only in their marginals, i.e. they have the same labeling function. Another popular approach is to consider an hypothesis class that moves closer the two distributions while implying a low-error for both tasks. This is a VC-dim approach that restricts the complexity of an hypothesis class in order to get good generalization. Instead, we propose a PAC-Bayesian approach that seeks for suitable weights to be given to each hypothesis in order to build a majority vote. We prove a new DA bound in the PAC-Bayesian context. This leads us to design the first DA-PAC-Bayesian algorithm based on the minimization of the proposed bound. Doing so, we seek for a \\rho-weighted majority vote that takes into account a trade-off between three quantities. The first two quantities being, as usual in the PAC-Bayesian approach, (a) the complexity of the majority vote (measured by a Kullback-Leibler divergence) and (b) its empirical risk (measured by the \\rho-average errors on the source sample). The third quantity is (c) the capacity of the majority vote to distinguish some structural difference between the source and target samples.", "source": "arxiv/ml"}
{"id": "arxiv:2471", "title": "On the complexity of learning a language: An improvement of Block's algorithm", "text": "Language learning is thought to be a highly complex process. One of the hurdles in learning a language is to learn the rules of syntax of the language. Rules of syntax are often ordered in that before one rule can applied one must apply another. It has been thought that to learn the order of n rules one must go through all n! permutations. Thus to learn the order of 27 rules would require 27! steps or 1.08889x10^{28} steps. This number is much greater than the number of seconds since the beginning of the universe! In an insightful analysis the linguist Block ([Block 86], pp. 62-63, p.238) showed that with the assumption of transitivity this vast number of learning steps reduces to a mere 377 steps. We present a mathematical analysis of the complexity of Block's algorithm. The algorithm has a complexity of order n^2 given n rules. In addition, we improve Block's results exponentially, by introducing an algorithm that has complexity of order less than n log n.", "source": "arxiv/ml"}
{"id": "arxiv:2472", "title": "Mining Techniques in Network Security to Enhance Intrusion Detection Systems", "text": "In intrusion detection systems, classifiers still suffer from several drawbacks such as data dimensionality and dominance, different network feature types, and data impact on the classification. In this paper two significant enhancements are presented to solve these drawbacks. The first enhancement is an improved feature selection using sequential backward search and information gain. This, in turn, extracts valuable features that enhance positively the detection rate and reduce the false positive rate. The second enhancement is transferring nominal network features to numeric ones by exploiting the discrete random variable and the probability mass function to solve the problem of different feature types, the problem of data dominance, and data impact on the classification. The latter is combined to known normalization methods to achieve a significant hybrid normalization approach. Finally, an intensive and comparative study approves the efficiency of these enhancements and shows better performance comparing to other proposed methods.", "source": "arxiv/ml"}
{"id": "arxiv:2473", "title": "Robust Face Recognition using Local Illumination Normalization and Discriminant Feature Point Selection", "text": "Face recognition systems must be robust to the variation of various factors such as facial expression, illumination, head pose and aging. Especially, the robustness against illumination variation is one of the most important problems to be solved for the practical use of face recognition systems. Gabor wavelet is widely used in face detection and recognition because it gives the possibility to simulate the function of human visual system. In this paper, we propose a method for extracting Gabor wavelet features which is stable under the variation of local illumination and show experiment results demonstrating its effectiveness.", "source": "arxiv/ml"}
{"id": "arxiv:2474", "title": "Active Collaborative Filtering", "text": "Collaborative filtering (CF) allows the preferences of multiple users to be pooled to make recommendations regarding unseen products. We consider in this paper the problem of online and interactive CF: given the current ratings associated with a user, what queries (new ratings) would most improve the quality of the recommendations made? We cast this terms of expected value of information (EVOI); but the online computational cost of computing optimal queries is prohibitive. We show how offline prototyping and computation of bounds on EVOI can be used to dramatically reduce the required online computation. The framework we develop is general, but we focus on derivations and empirical study in the specific case of the multiple-cause vector quantization model.", "source": "arxiv/ml"}
{"id": "arxiv:2475", "title": "Bayesian Hierarchical Mixtures of Experts", "text": "The Hierarchical Mixture of Experts (HME) is a well-known tree-based model for regression and classification, based on soft probabilistic splits. In its original formulation it was trained by maximum likelihood, and is therefore prone to over-fitting. Furthermore the maximum likelihood framework offers no natural metric for optimizing the complexity and structure of the tree. Previous attempts to provide a Bayesian treatment of the HME model have relied either on ad-hoc local Gaussian approximations or have dealt with related models representing the joint distribution of both input and output variables. In this paper we describe a fully Bayesian treatment of the HME model based on variational inference. By combining local and global variational methods we obtain a rigourous lower bound on the marginal probability of the data under the model. This bound is optimized during the training phase, and its resulting value can be used for model order selection. We present results using this approach for a data set describing robot arm kinematics.", "source": "arxiv/ml"}
{"id": "arxiv:2476", "title": "The Information Bottleneck EM Algorithm", "text": "Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This algorithm, however, can get trapped in local maxima. In this paper we explore a new approach that is based on the Information Bottleneck principle. In this approach, we view the learning problem as a tradeoff between two information theoretic objectives. The first is to make the hidden variables uninformative about the identity of specific instances. The second is to make the hidden variables informative about the observed attributes. By exploring different tradeoffs between these two objectives, we can gradually converge on a high-scoring solution. As we show, the resulting, Information Bottleneck Expectation Maximization (IB-EM) algorithm, manages to find solutions that are superior to standard EM methods.", "source": "arxiv/ml"}
{"id": "arxiv:2477", "title": "A New Algorithm for Maximum Likelihood Estimation in Gaussian Graphical Models for Marginal Independence", "text": "Graphical models with bi-directed edges (<->) represent marginal independence: the absence of an edge between two vertices indicates that the corresponding variables are marginally independent. In this paper, we consider maximum likelihood estimation in the case of continuous variables with a Gaussian joint distribution, sometimes termed a covariance graph model. We present a new fitting algorithm which exploits standard regression techniques and establish its convergence properties. Moreover, we contrast our procedure to existing estimation methods.", "source": "arxiv/ml"}
{"id": "arxiv:2478", "title": "A Robust Independence Test for Constraint-Based Learning of Causal Structure", "text": "Constraint-based (CB) learning is a formalism for learning a causal network with a database D by performing a series of conditional-independence tests to infer structural information. This paper considers a new test of independence that combines ideas from Bayesian learning, Bayesian network inference, and classical hypothesis testing to produce a more reliable and robust test. The new test can be calculated in the same asymptotic time and space required for the standard tests such as the chi-squared test, but it allows the specification of a prior distribution over parameters and can be used when the database is incomplete. We prove that the test is correct, and we demonstrate empirically that, when used with a CB causal discovery algorithm with noninformative priors, it recovers structural features more reliably and it produces networks with smaller KL-Divergence, especially as the number of nodes increases or the number of records decreases. Another benefit is the dramatic reduction in the probability that a CB algorithm will stall during the search, providing a remedy for an annoying problem plaguing CB learning when the database is small.", "source": "arxiv/ml"}
{"id": "arxiv:2479", "title": "On Information Regularization", "text": "We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov style regularization where the regularization penalty articulates the way in which the marginal density should constrain otherwise unrestricted conditional distributions. Specifically, the regularization penalty penalizes any information introduced between the examples and labels beyond what is provided by the available labeled examples. The work extends Szummer and Jaakkola's information regularization (NIPS 2002) to multiple dimensions, providing a regularizer independent of the covering of the space used in the derivation. We show in addition how the information regularizer can be used as a measure of complexity of the classification task with unlabeled data and prove a relevant sample-complexity bound. We illustrate the regularization principle in practice by restricting the class of conditional distributions to be logistic regression models and constructing the regularization penalty from a finite set of unlabeled examples.", "source": "arxiv/ml"}
{"id": "arxiv:2480", "title": "Large-Sample Learning of Bayesian Networks is NP-Hard", "text": "In this paper, we provide new complexity results for algorithms that learn discrete-variable Bayesian networks from data. Our results apply whenever the learning algorithm uses a scoring criterion that favors the simplest model able to represent the generative distribution exactly. Our results therefore hold whenever the learning algorithm uses a consistent scoring criterion and is applied to a sufficiently large dataset. We show that identifying high-scoring structures is hard, even when we are given an independence oracle, an inference oracle, and/or an information oracle. Our negative results also apply to the learning of discrete-variable Bayesian networks in which each node has at most k parents, for all k > 3.", "source": "arxiv/ml"}
{"id": "arxiv:2481", "title": "Reasoning about Bayesian Network Classifiers", "text": "Bayesian network classifiers are used in many fields, and one common class of classifiers are naive Bayes classifiers. In this paper, we introduce an approach for reasoning about Bayesian network classifiers in which we explicitly convert them into Ordered Decision Diagrams (ODDs), which are then used to reason about the properties of these classifiers. Specifically, we present an algorithm for converting any naive Bayes classifier into an ODD, and we show theoretically and experimentally that this algorithm can give us an ODD that is tractable in size even given an intractable number of instances. Since ODDs are tractable representations of classifiers, our algorithm allows us to efficiently test the equivalence of two naive Bayes classifiers and characterize discrepancies between them. We also show a number of additional results including a count of distinct classifiers that can be induced by changing some CPT in a naive Bayes classifier, and the range of allowable changes to a CPT which keeps the current classifier unchanged.", "source": "arxiv/ml"}
{"id": "arxiv:2482", "title": "Monte Carlo Matrix Inversion Policy Evaluation", "text": "In 1950, Forsythe and Leibler (1950) introduced a statistical technique for finding the inverse of a matrix by characterizing the elements of the matrix inverse as expected values of a sequence of random walks. Barto and Duff (1994) subsequently showed relations between this technique and standard dynamic programming and temporal differencing methods. The advantage of the Monte Carlo matrix inversion (MCMI) approach is that it scales better with respect to state-space size than alternative techniques. In this paper, we introduce an algorithm for performing reinforcement learning policy evaluation using MCMI. We demonstrate that MCMI improves on runtime over a maximum likelihood model-based policy evaluation approach and on both runtime and accuracy over the temporal differencing (TD) policy evaluation approach. We further improve on MCMI policy evaluation by adding an importance sampling technique to our algorithm to reduce the variance of our estimator. Lastly, we illustrate techniques for scaling up MCMI to large state spaces in order to perform policy improvement.", "source": "arxiv/ml"}
{"id": "arxiv:2483", "title": "Budgeted Learning of Naive-Bayes Classifiers", "text": "Frequently, acquiring training data has an associated cost. We consider the situation where the learner may purchase data during training, subject TO a budget. IN particular, we examine the CASE WHERE each feature label has an associated cost, AND the total cost OF ALL feature labels acquired during training must NOT exceed the budget.This paper compares methods FOR choosing which feature label TO purchase next, given the budget AND the CURRENT belief state OF naive Bayes model parameters.Whereas active learning has traditionally focused ON myopic(greedy) strategies FOR query selection, this paper presents a tractable method FOR incorporating knowledge OF the budget INTO the decision making process, which improves performance.", "source": "arxiv/ml"}
{"id": "arxiv:2484", "title": "Learning Riemannian Metrics", "text": "We propose a solution to the problem of estimating a Riemannian metric associated with a given differentiable manifold. The metric learning problem is based on minimizing the relative volume of a given set of points. We derive the details for a family of metrics on the multinomial simplex. The resulting metric has applications in text classification and bears some similarity to TFIDF representation of text documents.", "source": "arxiv/ml"}
{"id": "arxiv:2485", "title": "Efficient Gradient Estimation for Motor Control Learning", "text": "The task of estimating the gradient of a function in the presence of noise is central to several forms of reinforcement learning, including policy search methods. We present two techniques for reducing gradient estimation errors in the presence of observable input noise applied to the control signal. The first method extends the idea of a reinforcement baseline by fitting a local linear model to the function whose gradient is being estimated; we show how to find the linear model that minimizes the variance of the gradient estimate, and how to estimate the model from data. The second method improves this further by discounting components of the gradient vector that have high variance. These methods are applied to the problem of motor control learning, where actuator noise has a significant influence on behavior. In particular, we apply the techniques to learn locally optimal controllers for a dart-throwing task using a simulated three-link arm; we demonstrate that proposed methods significantly improve the reward function gradient estimate and, consequently, the learning curve, over existing methods.", "source": "arxiv/ml"}
{"id": "arxiv:2486", "title": "Approximate Inference and Constrained Optimization", "text": "Loopy and generalized belief propagation are popular algorithms for approximate inference in Markov random fields and Bayesian networks. Fixed points of these algorithms correspond to extrema of the Bethe and Kikuchi free energy. However, belief propagation does not always converge, which explains the need for approaches that explicitly minimize the Kikuchi/Bethe free energy, such as CCCP and UPS. Here we describe a class of algorithms that solves this typically nonconvex constrained minimization of the Kikuchi free energy through a sequence of convex constrained minimizations of upper bounds on the Kikuchi free energy. Intuitively one would expect tighter bounds to lead to faster algorithms, which is indeed convincingly demonstrated in our simulations. Several ideas are applied to obtain tight convex bounds that yield dramatic speed-ups over CCCP.", "source": "arxiv/ml"}
{"id": "arxiv:2487", "title": "Sufficient Dimensionality Reduction with Irrelevant Statistics", "text": "The problem of finding a reduced dimensionality representation of categorical variables while preserving their most relevant characteristics is fundamental for the analysis of complex data. Specifically, given a co-occurrence matrix of two variables, one often seeks a compact representation of one variable which preserves information about the other variable. We have recently introduced ``Sufficient Dimensionality Reduction' [GT-2003], a method that extracts continuous reduced dimensional features whose measurements (i.e., expectation values) capture maximal mutual information among the variables. However, such measurements often capture information that is irrelevant for a given task. Widely known examples are illumination conditions, which are irrelevant as features for face recognition, writing style which is irrelevant as a feature for content classification, and intonation which is irrelevant as a feature for speech recognition. Such irrelevance cannot be deduced apriori, since it depends on the details of the task, and is thus inherently ill defined in the purely unsupervised case. Separating relevant from irrelevant features can be achieved using additional side data that contains such irrelevant structures. This approach was taken in [CT-2002], extending the information bottleneck method, which uses clustering to compress the data. Here we use this side-information framework to identify features whose measurements are maximally informative for the original data set, but carry as little information as possible on a side data set. In statistical terms this can be understood as extracting statistics which are maximally sufficient for the original dataset, while simultaneously maximally ancillary for the side dataset. We formulate this tradeoff as a constrained optimization problem and characterize its solutions. We then derive a gradient descent algorithm for this problem, which is based on the Generalized Iterative Scaling method for finding maximum entropy distributions. The method is demonstrated on synthetic data, as well as on real face recognition datasets, and is shown to outperform standard methods such as oriented PCA.", "source": "arxiv/ml"}
{"id": "arxiv:2488", "title": "Locally Weighted Naive Bayes", "text": "Despite its simplicity, the naive Bayes classifier has surprised machine learning researchers by exhibiting good performance on a variety of learning problems. Encouraged by these results, researchers have looked to overcome naive Bayes primary weakness - attribute independence - and improve the performance of the algorithm. This paper presents a locally weighted version of naive Bayes that relaxes the independence assumption by learning local models at prediction time. Experimental results show that locally weighted naive Bayes rarely degrades accuracy compared to standard naive Bayes and, in many cases, improves accuracy dramatically. The main advantage of this method compared to other techniques for enhancing naive Bayes is its conceptual and computational simplicity.", "source": "arxiv/ml"}
{"id": "arxiv:2489", "title": "A Distance-Based Branch and Bound Feature Selection Algorithm", "text": "There is no known efficient method for selecting k Gaussian features from n which achieve the lowest Bayesian classification error. We show an example of how greedy algorithms faced with this task are led to give results that are not optimal. This motivates us to propose a more robust approach. We present a Branch and Bound algorithm for finding a subset of k independent Gaussian features which minimizes the naive Bayesian classification error. Our algorithm uses additive monotonic distance measures to produce bounds for the Bayesian classification error in order to exclude many feature subsets from evaluation, while still returning an optimal solution. We test our method on synthetic data as well as data obtained from gene expression profiling.", "source": "arxiv/ml"}
{"id": "arxiv:2490", "title": "On the Convergence of Bound Optimization Algorithms", "text": "Many practitioners who use the EM algorithm complain that it is sometimes slow. When does this happen, and what can be done about it? In this paper, we study the general class of bound optimization algorithms - including Expectation-Maximization, Iterative Scaling and CCCP - and their relationship to direct optimization algorithms such as gradient-based methods for parameter learning. We derive a general relationship between the updates performed by bound optimization methods and those of gradient and second-order methods and identify analytic conditions under which bound optimization algorithms exhibit quasi-Newton behavior, and conditions under which they possess poor, first-order convergence. Based on this analysis, we consider several specific algorithms, interpret and analyze their convergence properties and provide some recipes for preprocessing input to these algorithms to yield faster convergence behavior. We report empirical results supporting our analysis and showing that simple data preprocessing can result in dramatically improved performance of bound optimizers in practice.", "source": "arxiv/ml"}
{"id": "arxiv:2491", "title": "Automated Analytic Asymptotic Evaluation of the Marginal Likelihood for Latent Models", "text": "We present and implement two algorithms for analytic asymptotic evaluation of the marginal likelihood of data given a Bayesian network with hidden nodes. As shown by previous work, this evaluation is particularly hard for latent Bayesian network models, namely networks that include hidden variables, where asymptotic approximation deviates from the standard BIC score. Our algorithms solve two central difficulties in asymptotic evaluation of marginal likelihood integrals, namely, evaluation of regular dimensionality drop for latent Bayesian network models and computation of non-standard approximation formulas for singular statistics for these models. The presented algorithms are implemented in Matlab and Maple and their usage is demonstrated for marginal likelihood approximations for Bayesian networks with hidden variables.", "source": "arxiv/ml"}
{"id": "arxiv:2492", "title": "Learning Generative Models of Similarity Matrices", "text": "We describe a probabilistic (generative) view of affinity matrices along with inference algorithms for a subclass of problems associated with data clustering. This probabilistic view is helpful in understanding different models and algorithms that are based on affinity functions OF the data. IN particular, we show how(greedy) inference FOR a specific probabilistic model IS equivalent TO the spectral clustering algorithm.It also provides a framework FOR developing new algorithms AND extended models. AS one CASE, we present new generative data clustering models that allow us TO infer the underlying distance measure suitable for the clustering problem at hand. These models seem to perform well in a larger class of problems for which other clustering algorithms (including spectral clustering) usually fail. Experimental evaluation was performed in a variety point data sets, showing excellent performance.", "source": "arxiv/ml"}
{"id": "arxiv:2493", "title": "Learning Continuous Time Bayesian Networks", "text": "Continuous time Bayesian networks (CTBNs) describe structured stochastic processes with finitely many states that evolve over continuous time. A CTBN is a directed (possibly cyclic) dependency graph over a set of variables, each of which represents a finite state continuous time Markov process whose transition model is a function of its parents. We address the problem of learning parameters and structure of a CTBN from fully observed data. We define a conjugate prior for CTBNs, and show how it can be used both for Bayesian parameter estimation and as the basis of a Bayesian score for structure learning. Because acyclicity is not a constraint in CTBNs, we can show that the structure learning problem is significantly easier, both in theory and in practice, than structure learning for dynamic Bayesian networks (DBNs). Furthermore, as CTBNs can tailor the parameters and dependency structure to the different time granularities of the evolution of different variables, they can provide a better fit to continuous-time processes than DBNs with a fixed time granularity.", "source": "arxiv/ml"}
{"id": "arxiv:2494", "title": "On Local Optima in Learning Bayesian Networks", "text": "This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima. When greediness is set at maximum, KES corresponds to the greedy equivalence search algorithm (GES). When greediness is kept at minimum, we prove that under mild assumptions KES asymptotically returns any inclusion optimal BN with nonzero probability. Experimental results for both synthetic and real data are reported showing that KES often finds a better local optima than GES. Moreover, we use KES to experimentally confirm that the number of different local optima is often huge.", "source": "arxiv/ml"}
{"id": "arxiv:2495", "title": "Efficiently Inducing Features of Conditional Random Fields", "text": "Conditional Random Fields (CRFs) are undirected graphical models, a special case of which correspond to conditionally-trained finite state machines. A key advantage of these models is their great flexibility to include a wide array of overlapping, multi-granularity, non-independent features of the input. In face of this freedom, an important question that remains is, what features should be used? This paper presents a feature induction method for CRFs. Founded on the principle of constructing only those feature conjunctions that significantly increase log-likelihood, the approach is based on that of Della Pietra et al [1997], but altered to work with conditional rather than joint probabilities, and with additional modifications for providing tractability specifically for a sequence model. In comparison with traditional approaches, automated feature induction offers both improved accuracy and more than an order of magnitude reduction in feature count; it enables the use of richer, higher-order Markov models, and offers more freedom to liberally guess about which atomic features may be relevant to a task. The induction method applies to linear-chain CRFs, as well as to more arbitrary CRF structures, also known as Relational Markov Networks [Taskar & Koller, 2002]. We present experimental results on a named entity extraction task.", "source": "arxiv/ml"}
{"id": "arxiv:2496", "title": "Collaborative Ensemble Learning: Combining Collaborative and Content-Based Information Filtering via Hierarchical Bayes", "text": "Collaborative filtering (CF) and content-based filtering (CBF) have widely been used in information filtering applications. Both approaches have their strengths and weaknesses which is why researchers have developed hybrid systems. This paper proposes a novel approach to unify CF and CBF in a probabilistic framework, named collaborative ensemble learning. It uses probabilistic SVMs to model each user's profile (as CBF does).At the prediction phase, it combines a society OF users profiles, represented by their respective SVM models, to predict an active users preferences(the CF idea).The combination scheme is embedded in a probabilistic framework and retains an intuitive explanation.Moreover, collaborative ensemble learning does not require a global training stage and thus can incrementally incorporate new data.We report results based on two data sets. For the Reuters-21578 text data set, we simulate user ratings under the assumption that each user is interested in only one category. In the second experiment, we use users' opinions on a set of 642 art images that were collected through a web-based survey. For both data sets, collaborative ensemble achieved excellent performance in terms of recommendation accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2497", "title": "Markov Random Walk Representations with Continuous Distributions", "text": "Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distributions. Transition probabilities are now calculated using a diffusion equation with a diffusion coefficient that inversely depends on the data density. We relate this diffusion equation to a path integral and derive the corresponding path probability measure. The framework is useful for incorporating continuous data densities and prior knowledge.", "source": "arxiv/ml"}
{"id": "arxiv:2498", "title": "Stochastic complexity of Bayesian networks", "text": "Bayesian networks are now being used in enormous fields, for example, diagnosis of a system, data mining, clustering and so on. In spite of their wide range of applications, the statistical properties have not yet been clarified, because the models are nonidentifiable and non-regular. In a Bayesian network, the set of its parameter for a smaller model is an analytic set with singularities in the space of large ones. Because of these singularities, the Fisher information matrices are not positive definite. In other words, the mathematical foundation for learning was not constructed. In recent years, however, we have developed a method to analyze non-regular models using algebraic geometry. This method revealed the relation between the models singularities and its statistical properties. In this paper, applying this method to Bayesian networks with latent variables, we clarify the order of the stochastic complexities.Our result claims that the upper bound of those is smaller than the dimension of the parameter space. This means that the Bayesian generalization error is also far smaller than that of regular model, and that Schwarzs model selection criterion BIC needs to be improved for Bayesian networks.", "source": "arxiv/ml"}
{"id": "arxiv:2499", "title": "A Generalized Mean Field Algorithm for Variational Inference in Exponential Families", "text": "The mean field methods, which entail approximating intractable probability distributions variationally with distributions from a tractable family, enjoy high efficiency, guaranteed convergence, and provide lower bounds on the true likelihood. But due to requirement for model-specific derivation of the optimization equations and unclear inference quality in various models, it is not widely used as a generic approximate inference algorithm. In this paper, we discuss a generalized mean field theory on variational approximation to a broad class of intractable distributions using a rich set of tractable distributions via constrained optimization over distribution spaces. We present a class of generalized mean field (GMF) algorithms for approximate inference in complex exponential family models, which entails limiting the optimization over the class of cluster-factorizable distributions. GMF is a generic method requiring no model-specific derivations. It factors a complex model into a set of disjoint variable clusters, and uses a set of canonical fix-point equations to iteratively update the cluster distributions, and converge to locally optimal cluster marginals that preserve the original dependency structure within each cluster, hence, fully decomposed the overall inference problem. We empirically analyzed the effect of different tractable family (clusters of different granularity) on inference quality, and compared GMF with BP on several canonical models. Possible extension to higher-order MF approximation is also discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2500", "title": "Efficient Parametric Projection Pursuit Density Estimation", "text": "Product models of low dimensional experts are a powerful way to avoid the curse of dimensionality. We present the ``under-complete product of experts' (UPoE), where each expert models a one dimensional projection of the data. The UPoE is fully tractable and may be interpreted as a parametric probabilistic model for projection pursuit. Its ML learning rules are identical to the approximate learning rules proposed before for under-complete ICA. We also derive an efficient sequential learning algorithm and discuss its relationship to projection pursuit density estimation and feature induction algorithms for additive random field models.", "source": "arxiv/ml"}
{"id": "arxiv:2501", "title": "Boltzmann Machine Learning with the Latent Maximum Entropy Principle", "text": "We present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes maximum entropy principle and from standard maximum likelihood estimation.We demonstrate the LME principle BY deriving new algorithms for Boltzmann machine parameter estimation, and show how robust and fast new variant of the EM algorithm can be developed.Our experiments show that estimation based on LME generally yields better results than maximum likelihood estimation, particularly when inferring hidden units from small amounts of data.", "source": "arxiv/ml"}
{"id": "arxiv:2502", "title": "Learning Measurement Models for Unobserved Variables", "text": "Observed associations in a database may be due in whole or part to variations in unrecorded (latent) variables. Identifying such variables and their causal relationships with one another is a principal goal in many scientific and practical domains. Previous work shows that, given a partition of observed variables such that members of a class share only a single latent common cause, standard search algorithms for causal Bayes nets can infer structural relations between latent variables. We introduce an algorithm for discovering such partitions when they exist. Uniquely among available procedures, the algorithm is (asymptotically) correct under standard assumptions in causal Bayes net search algorithms, requires no prior knowledge of the number of latent variables, and does not depend on the mathematical form of the relationships among the latent variables. We evaluate the algorithm on a variety of simulated data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2503", "title": "Learning Module Networks", "text": "Methods for learning Bayesian network structure can discover dependency structure between observed variables, and have been shown to be useful in many applications. However, in domains that involve a large number of variables, the space of possible network structures is enormous, making it difficult, for both computational and statistical reasons, to identify a good model. In this paper, we consider a solution to this problem, suitable for domains where many variables have similar behavior. Our method is based on a new class of models, which we call module networks. A module network explicitly represents the notion of a module - a set of variables that have the same parents in the network and share the same conditional probability distribution. We define the semantics of module networks, and describe an algorithm that learns a module network from data. The algorithm learns both the partitioning of the variables into modules and the dependency structure between the variables. We evaluate our algorithm on synthetic data, and on real data in the domains of gene expression and the stock market. Our results show that module networks generalize better than Bayesian networks, and that the learned module network structure reveals regularities that are obscured in learned Bayesian networks.", "source": "arxiv/ml"}
{"id": "arxiv:2504", "title": "Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs", "text": "We consider the problem of learning the structure of undirected graphical models with bounded treewidth, within the maximum likelihood framework. This is an NP-hard problem and most approaches consider local search techniques. In this paper, we pose it as a combinatorial optimization problem, which is then relaxed to a convex optimization problem that involves searching over the forest and hyperforest polytopes with special structures, independently. A supergradient method is used to solve the dual problem, with a run-time complexity of $O(k^3 n^{k+2} \\log n)$ for each iteration, where $n$ is the number of variables and $k$ is a bound on the treewidth. We compare our approach to state-of-the-art methods on synthetic datasets and classical benchmarks, showing the gains of the novel convex approach.", "source": "arxiv/ml"}
{"id": "arxiv:2505", "title": "Optimal diagnostic tests for sporadic Creutzfeldt-Jakob disease based on support vector machine classification of RT-QuIC data", "text": "In this work we study numerical construction of optimal clinical diagnostic tests for detecting sporadic Creutzfeldt-Jakob disease (sCJD). A cerebrospinal fluid sample (CSF) from a suspected sCJD patient is subjected to a process which initiates the aggregation of a protein present only in cases of sCJD. This aggregation is indirectly observed in real-time at regular intervals, so that a longitudinal set of data is constructed that is then analysed for evidence of this aggregation. The best existing test is based solely on the final value of this set of data, which is compared against a threshold to conclude whether or not aggregation, and thus sCJD, is present. This test criterion was decided upon by analysing data from a total of 108 sCJD and non-sCJD samples, but this was done subjectively and there is no supporting mathematical analysis declaring this criterion to be exploiting the available data optimally. This paper addresses this deficiency, seeking to validate or improve the test primarily via support vector machine (SVM) classification. Besides this, we address a number of additional issues such as i) early stopping of the measurement process, ii) the possibility of detecting the particular type of sCJD and iii) the incorporation of additional patient data such as age, sex, disease duration and timing of CSF sampling into the construction of the test.", "source": "arxiv/ml"}
{"id": "arxiv:2506", "title": "Joint Training of Deep Boltzmann Machines", "text": "We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2507", "title": "Bayesian one-mode projection for dynamic bipartite graphs", "text": "We propose a Bayesian methodology for one-mode projecting a bipartite network that is being observed across a series of discrete time steps. The resulting one mode network captures the uncertainty over the presence/absence of each link and provides a probability distribution over its possible weight values. Additionally, the incorporation of prior knowledge over previous states makes the resulting network less sensitive to noise and missing observations that usually take place during the data collection process. The methodology consists of computationally inexpensive update rules and is scalable to large problems, via an appropriate distributed implementation.", "source": "arxiv/ml"}
{"id": "arxiv:2508", "title": "Dictionary Subselection Using an Overcomplete Joint Sparsity Model", "text": "Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As this model is often unknown for many classes of the signals, we need to select such a model based on the domain knowledge or using some exemplar signals. This paper presents a new exemplar based approach for the linear model (called the dictionary) selection, for such sparse inverse problems. The problem of dictionary selection, which has also been called the dictionary learning in this setting, is first reformulated as a joint sparsity model. The joint sparsity model here differs from the standard joint sparsity model as it considers an overcompleteness in the representation of each signal, within the range of selected subspaces. The new dictionary selection paradigm is examined with some synthetic and realistic simulations.", "source": "arxiv/ml"}
{"id": "arxiv:2509", "title": "Cost-Sensitive Feature Selection of Data with Errors", "text": "In data mining applications, feature selection is an essential process since it reduces a model's complexity. The cost of obtaining the feature values must be taken into consideration in many domains. In this paper, we study the cost-sensitive feature selection problem on numerical data with measurement errors, test costs and misclassification costs. The major contributions of this paper are four-fold. First, a new data model is built to address test costs and misclassification costs as well as error boundaries. Second, a covering-based rough set with measurement errors is constructed. Given a confidence interval, the neighborhood is an ellipse in a two-dimension space, or an ellipsoidal in a three-dimension space, etc. Third, a new cost-sensitive feature selection problem is defined on this covering-based rough set. Fourth, both backtracking and heuristic algorithms are proposed to deal with this new problem. The algorithms are tested on six UCI (University of California - Irvine) data sets. Experimental results show that (1) the pruning techniques of the backtracking algorithm help reducing the number of operations significantly, and (2) the heuristic algorithm usually obtains optimal results. This study is a step toward realistic applications of cost-sensitive learning.", "source": "arxiv/ml"}
{"id": "arxiv:2510", "title": "Learning Sparse Low-Threshold Linear Classifiers", "text": "We consider the problem of learning a non-negative linear classifier with a $1$-norm of at most $k$, and a fixed threshold, under the hinge-loss. This problem generalizes the problem of learning a $k$-monotone disjunction. We prove that we can learn efficiently in this setting, at a rate which is linear in both $k$ and the size of the threshold, and that this is the best possible rate. We provide an efficient online learning algorithm that achieves the optimal rate, and show that in the batch case, empirical risk minimization achieves this rate as well. The rates we show are tighter than the uniform convergence rate, which grows with $k^2$.", "source": "arxiv/ml"}
{"id": "arxiv:2511", "title": "Know Your Personalization: Learning Topic level Personalization in Online Services", "text": "Online service platforms (OSPs), such as search engines, news-websites, ad-providers, etc., serve highly pe rsonalized content to the user, based on the profile extracted from his history with the OSP. Although personalization (generally) leads to a better user experience, it also raises privacy concerns for the user---he does not know what is present in his profile and more importantly, what is being used to per sonalize content for him. In this paper, we capture OSP's personalization for an user in a new data structure called the person alization vector ($\\eta$), which is a weighted vector over a set of topics, and present techniques to compute it for users of an OSP. Our approach treats OSPs as black-boxes, and extracts $\\eta$ by mining only their output, specifical ly, the personalized (for an user) and vanilla (without any user information) contents served, and the differences in these content. We formulate a new model called Latent Topic Personalization (LTP) that captures the personalization vector into a learning framework and present efficient inference algorithms for it. We do extensive experiments for search result personalization using both data from real Google users and synthetic datasets. Our results show high accuracy (R-pre = 84%) of LTP in finding personalized topics. For Google data, our qualitative results show how LTP can also identifies evidences---queries for results on a topic with high $\\eta$ value were re-ranked. Finally, we show how our approach can be used to build a new Privacy evaluation framework focused at end-user privacy on commercial OSPs.", "source": "arxiv/ml"}
{"id": "arxiv:2512", "title": "Proceedings Quantities in Formal Methods", "text": "This volume contains the proceedings of the Workshop on Quantities in Formal Methods, QFM 2012, held in Paris, France on 28 August 2012. The workshop was affiliated with the 18th Symposium on Formal Methods, FM 2012. The focus of the workshop was on quantities in modeling, verification, and synthesis. Modern applications of formal methods require to reason formally on quantities such as time, resources, or probabilities. Standard formal methods and tools have gotten very good at modeling (and verifying) qualitative properties: whether or not certain events will occur. During the last years, these methods and tools have been extended to also cover quantitative aspects, notably leading to tools like e.g. UPPAAL (for real-time systems), PRISM (for probabilistic systems), and PHAVer (for hybrid systems). A lot of work remains to be done however before these tools can be used in the industrial applications at which they are aiming.", "source": "arxiv/ml"}
{"id": "arxiv:2513", "title": "Machine Learning in Proof General: Interfacing Interfaces", "text": "We present ML4PG - a machine learning extension for Proof General. It allows users to gather proof statistics related to shapes of goals, sequences of applied tactics, and proof tree structures from the libraries of interactive higher-order proofs written in Coq and SSReflect. The gathered data is clustered using the state-of-the-art machine learning algorithms available in MATLAB and Weka. ML4PG provides automated interfacing between Proof General and MATLAB/Weka. The results of clustering are used by ML4PG to provide proof hints in the process of interactive proof development.", "source": "arxiv/ml"}
{"id": "arxiv:2514", "title": "Learning efficient sparse and low rank models", "text": "Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with parsimony-promoting terms. The inherently sequential structure and data-dependent complexity and latency of iterative optimization constitute a major limitation in many applications requiring real-time performance or involving large-scale data. Another limitation encountered by these modeling techniques is the difficulty of their inclusion in discriminative learning scenarios. In this work, we propose to move the emphasis from the model to the pursuit algorithm, and develop a process-centric view of parsimonious modeling, in which a learned deterministic fixed-complexity pursuit process is used in lieu of iterative optimization. We show a principled way to construct learnable pursuit process architectures for structured sparse and robust low rank models, derived from the iteration of proximal descent algorithms. These architectures learn to approximate the exact parsimonious representation at a fraction of the complexity of the standard optimization methods. We also show that appropriate training regimes allow to naturally extend parsimonious models to discriminative settings. State-of-the-art results are demonstrated on several challenging problems in image and audio processing with several orders of magnitude speedup compared to the exact optimization algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2515", "title": "A metric for software vulnerabilities classification", "text": "Vulnerability discovery and exploits detection are two wide areas of study in software engineering. This preliminary work tries to combine existing methods with machine learning techniques to define a metric classification of vulnerable computer programs. First a feature set has been defined and later two models have been tested against real world vulnerabilities. A relation between the classifier choice and the features has also been outlined.", "source": "arxiv/ml"}
{"id": "arxiv:2516", "title": "Biologically Inspired Spiking Neurons : Piecewise Linear Models and Digital Implementation", "text": "There has been a strong push recently to examine biological scale simulations of neuromorphic algorithms to achieve stronger inference capabilities. This paper presents a set of piecewise linear spiking neuron models, which can reproduce different behaviors, similar to the biological neuron, both for a single neuron as well as a network of neurons. The proposed models are investigated, in terms of digital implementation feasibility and costs, targeting large scale hardware implementation. Hardware synthesis and physical implementations on FPGA show that the proposed models can produce precise neural behaviors with higher performance and considerably lower implementation costs compared with the original model. Accordingly, a compact structure of the models which can be trained with supervised and unsupervised learning algorithms has been developed. Using this structure and based on a spike rate coding, a character recognition case study has been implemented and tested.", "source": "arxiv/ml"}
{"id": "arxiv:2517", "title": "Belief Propagation for Continuous State Spaces: Stochastic Message-Passing with Quantitative Guarantees", "text": "The sum-product or belief propagation (BP) algorithm is a widely used message-passing technique for computing approximate marginals in graphical models. We introduce a new technique, called stochastic orthogonal series message-passing (SOSMP), for computing the BP fixed point in models with continuous random variables. It is based on a deterministic approximation of the messages via orthogonal series expansion, and a stochastic approximation via Monte Carlo estimates of the integral updates of the basis coefficients. We prove that the SOSMP iterates converge to a \\delta-neighborhood of the unique BP fixed point for any tree-structured graph, and for any graphs with cycles in which the BP updates satisfy a contractivity condition. In addition, we demonstrate how to choose the number of basis coefficients as a function of the desired approximation accuracy \\delta and smoothness of the compatibility functions. We illustrate our theory with both simulated examples and in application to optical flow estimation.", "source": "arxiv/ml"}
{"id": "arxiv:2518", "title": "Learning Markov Decision Processes for Model Checking", "text": "Constructing an accurate system model for formal model verification can be both resource demanding and time-consuming. To alleviate this shortcoming, algorithms have been proposed for automatically learning system models based on observed system behaviors. In this paper we extend the algorithm on learning probabilistic automata to reactive systems, where the observed system behavior is in the form of alternating sequences of inputs and outputs. We propose an algorithm for automatically learning a deterministic labeled Markov decision process model from the observed behavior of a reactive system. The proposed learning algorithm is adapted from algorithms for learning deterministic probabilistic finite automata, and extended to include both probabilistic and nondeterministic transitions. The algorithm is empirically analyzed and evaluated by learning system models of slot machines. The evaluation is performed by analyzing the probabilistic linear temporal logic properties of the system as well as by analyzing the schedulers, in particular the optimal schedulers, induced by the learned models.", "source": "arxiv/ml"}
{"id": "arxiv:2519", "title": "A Tutorial on Probabilistic Latent Semantic Analysis", "text": "In this tutorial, I will discuss the details about how Probabilistic Latent Semantic Analysis (PLSA) is formalized and how different learning algorithms are proposed to learn the model.", "source": "arxiv/ml"}
{"id": "arxiv:2520", "title": "Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction", "text": "Very often data we encounter in practice is a collection of matrices rather than a single matrix. These multi-block data are naturally linked and hence often share some common features and at the same time they have their own individual features, due to the background in which they are measured and collected. In this study we proposed a new scheme of common and individual feature analysis (CIFA) that processes multi-block data in a linked way aiming at discovering and separating their common and individual features. According to whether the number of common features is given or not, two efficient algorithms were proposed to extract the common basis which is shared by all data. Then feature extraction is performed on the common and the individual spaces separately by incorporating the techniques such as dimensionality reduction and blind source separation. We also discussed how the proposed CIFA can significantly improve the performance of classification and clustering tasks by exploiting common and individual features of samples respectively. Our experimental results show some encouraging features of the proposed methods in comparison to the state-of-the-art methods on synthetic and real data.", "source": "arxiv/ml"}
{"id": "arxiv:2521", "title": "Alternating Maximization: Unifying Framework for 8 Sparse PCA Formulations and Efficient Parallel Codes", "text": "Given a multivariate data set, sparse principal component analysis (SPCA) aims to extract several linear combinations of the variables that together explain the variance in the data as much as possible, while controlling the number of nonzero loadings in these combinations. In this paper we consider 8 different optimization formulations for computing a single sparse loading vector; these are obtained by combining the following factors: we employ two norms for measuring variance (L2, L1) and two sparsity-inducing norms (L0, L1), which are used in two different ways (constraint, penalty). Three of our formulations, notably the one with L0 constraint and L1 variance, have not been considered in the literature. We give a unifying reformulation which we propose to solve via a natural alternating maximization (AM) method. We show the the AM method is nontrivially equivalent to GPower (Journ\\'{e}e et al; JMLR 11:517--553, 2010) for all our formulations. Besides this, we provide 24 efficient parallel SPCA implementations: 3 codes (multi-core, GPU and cluster) for each of the 8 problems. Parallelism in the methods is aimed at i) speeding up computations (our GPU code can be 100 times faster than an efficient serial code written in C++), ii) obtaining solutions explaining more variance and iii) dealing with big data problems (our cluster code is able to solve a 357 GB problem in about a minute).", "source": "arxiv/ml"}
{"id": "arxiv:2522", "title": "Feature Clustering for Accelerating Parallel Coordinate Descent", "text": "Large-scale L1-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. High-performance algorithms and implementations are critical to efficiently solving these problems. Building upon previous work on coordinate descent algorithms for L1-regularized problems, we introduce a novel family of algorithms called block-greedy coordinate descent that includes, as special cases, several existing algorithms such as SCD, Greedy CD, Shotgun, and Thread-Greedy. We give a unified convergence analysis for the family of block-greedy algorithms. The analysis suggests that block-greedy coordinate descent can better exploit parallelism if features are clustered so that the maximum inner product between features in different blocks is small. Our theoretical convergence analysis is supported with experimental re- sults using data from diverse real-world applications. We hope that algorithmic approaches and convergence analysis we provide will not only advance the field, but will also encourage researchers to systematically explore the design space of algorithms for solving large-scale L1-regularization problems.", "source": "arxiv/ml"}
{"id": "arxiv:2523", "title": "Bayesian Group Nonnegative Matrix Factorization for EEG Analysis", "text": "We propose a generative model of a group EEG analysis, based on appropriate kernel assumptions on EEG data. We derive the variational inference update rule using various approximation techniques. The proposed model outperforms the current state-of-the-art algorithms in terms of common pattern extraction. The validity of the proposed model is tested on the BCI competition dataset.", "source": "arxiv/ml"}
{"id": "arxiv:2524", "title": "Variational Optimization", "text": "We discuss a general technique that can be used to form a differentiable bound on the optima of non-differentiable or discrete objective functions. We form a unified description of these methods and consider under which circumstances the bound is concave. In particular we consider two concrete applications of the method, namely sparse learning and support vector classification.", "source": "arxiv/ml"}
{"id": "arxiv:2525", "title": "A Multi-View Embedding Space for Modeling Internet Images, Tags, and their Semantics", "text": "This paper investigates the problem of modeling Internet images and associated text or tags for tasks such as image-to-image search, tag-to-image search, and image-to-tag search (image annotation). We start with canonical correlation analysis (CCA), a popular and successful approach for mapping visual and textual features to the same latent space, and incorporate a third view capturing high-level image semantics, represented either by a single category or multiple non-mutually-exclusive concepts. We present two ways to train the three-view embedding: supervised, with the third view coming from ground-truth labels or search keywords; and unsupervised, with semantic themes automatically obtained by clustering the tags. To ensure high accuracy for retrieval tasks while keeping the learning process scalable, we combine multiple strong visual features and use explicit nonlinear kernel mappings to efficiently approximate kernel CCA. To perform retrieval, we use a specially designed similarity function in the embedded space, which substantially outperforms the Euclidean distance. The resulting system produces compelling qualitative results and outperforms a number of two-view baselines on retrieval tasks on three large-scale Internet image datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2526", "title": "Analysis of Large-scale Traffic Dynamics using Non-negative Tensor Factorization", "text": "In this paper, we present our work on clustering and prediction of temporal dynamics of global congestion configurations in large-scale road networks. Instead of looking into temporal traffic state variation of individual links, or of small areas, we focus on spatial congestion configurations of the whole network. In our work, we aim at describing the typical temporal dynamic patterns of this network-level traffic state and achieving long-term prediction of the large-scale traffic dynamics, in a unified data-mining framework. To this end, we formulate this joint task using Non-negative Tensor Factorization (NTF), which has been shown to be a useful decomposition tools for multivariate data sequences. Clustering and prediction are performed based on the compact tensor factorization results. Experiments on large-scale simulated data illustrate the interest of our method with promising results for long-term forecast of traffic evolution.", "source": "arxiv/ml"}
{"id": "arxiv:2527", "title": "Role Mining with Probabilistic Models", "text": "Role mining tackles the problem of finding a role-based access control (RBAC) configuration, given an access-control matrix assigning users to access permissions as input. Most role mining approaches work by constructing a large set of candidate roles and use a greedy selection strategy to iteratively pick a small subset such that the differences between the resulting RBAC configuration and the access control matrix are minimized. In this paper, we advocate an alternative approach that recasts role mining as an inference problem rather than a lossy compression problem. Instead of using combinatorial algorithms to minimize the number of roles needed to represent the access-control matrix, we derive probabilistic models to learn the RBAC configuration that most likely underlies the given matrix. Our models are generative in that they reflect the way that permissions are assigned to users in a given RBAC configuration. We additionally model how user-permission assignments that conflict with an RBAC configuration emerge and we investigate the influence of constraints on role hierarchies and on the number of assignments. In experiments with access-control matrices from real-world enterprises, we compare our proposed models with other role mining methods. Our results show that our probabilistic models infer roles that generalize well to new system users for a wide variety of data, while other models' generalization abilities depend on the dataset given.", "source": "arxiv/ml"}
{"id": "arxiv:2528", "title": "A Practical Algorithm for Topic Modeling with Provable Guarantees", "text": "Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora. Most approaches to topic model inference have been based on a maximum likelihood objective. Efficient algorithms exist that approximate this objective, but they have no provable guarantees. Recently, algorithms have been introduced that provide provable bounds, but these algorithms are not practical because they are inefficient and not robust to violations of model assumptions. In this paper we present an algorithm for topic model inference that is both provable and practical. The algorithm produces results comparable to the best MCMC implementations while running orders of magnitude faster.", "source": "arxiv/ml"}
{"id": "arxiv:2529", "title": "Maximally Informative Observables and Categorical Perception", "text": "We formulate the problem of perception in the framework of information theory, and prove that categorical perception is equivalent to the existence of an observable that has the maximum possible information on the target of perception. We call such an observable maximally informative. Regardless whether categorical perception is real, maximally informative observables can form the basis of a theory of perception. We conclude with the implications of such a theory for the problem of speech perception.", "source": "arxiv/ml"}
{"id": "arxiv:2530", "title": "Hybrid Fuzzy-ART based K-Means Clustering Methodology to Cellular Manufacturing Using Operational Time", "text": "This paper presents a new hybrid Fuzzy-ART based K-Means Clustering technique to solve the part machine grouping problem in cellular manufacturing systems considering operational time. The performance of the proposed technique is tested with problems from open literature and the results are compared to the existing clustering models such as simple K-means algorithm and modified ART1 algorithm using an efficient modified performance measure known as modified grouping efficiency (MGE) as found in the literature. The results support the better performance of the proposed algorithm. The Novelty of this study lies in the simple and efficient methodology to produce quick solutions for shop floor managers with least computational efforts and time.", "source": "arxiv/ml"}
{"id": "arxiv:2531", "title": "Nonparametric ridge estimation", "text": "We study the problem of estimating the ridges of a density function. Ridge estimation is an extension of mode finding and is useful for understanding the structure of a density. It can also be used to find hidden structure in point cloud data. We show that, under mild regularity conditions, the ridges of the kernel density estimator consistently estimate the ridges of the true density. When the data are noisy measurements of a manifold, we show that the ridges are close and topologically similar to the hidden manifold. To find the estimated ridges in practice, we adapt the modified mean-shift algorithm proposed by Ozertem and Erdogmus [J. Mach. Learn. Res. 12 (2011) 1249-1286]. Some numerical experiments verify that the algorithm is accurate.", "source": "arxiv/ml"}
{"id": "arxiv:2532", "title": "Fuzzy soft rough K-Means clustering approach for gene expression data", "text": "Clustering is one of the widely used data mining techniques for medical diagnosis. Clustering can be considered as the most important unsupervised learning technique. Most of the clustering methods group data based on distance and few methods cluster data based on similarity. The clustering algorithms classify gene expression data into clusters and the functionally related genes are grouped together in an efficient manner. The groupings are constructed such that the degree of relationship is strong among members of the same cluster and weak among members of different clusters. In this work, we focus on a similarity relationship among genes with similar expression patterns so that a consequential and simple analytical decision can be made from the proposed Fuzzy Soft Rough K-Means algorithm. The algorithm is developed based on Fuzzy Soft sets and Rough sets. Comparative analysis of the proposed work is made with bench mark algorithms like K-Means and Rough K-Means and efficiency of the proposed algorithm is illustrated in this work by using various cluster validity measures such as DB index and Xie-Beni index.", "source": "arxiv/ml"}
{"id": "arxiv:2533", "title": "Soft Set Based Feature Selection Approach for Lung Cancer Images", "text": "Lung cancer is the deadliest type of cancer for both men and women. Feature selection plays a vital role in cancer classification. This paper investigates the feature selection process in Computed Tomographic (CT) lung cancer images using soft set theory. We propose a new soft set based unsupervised feature selection algorithm. Nineteen features are extracted from the segmented lung images using gray level co-occurence matrix (GLCM) and gray level different matrix (GLDM). In this paper, an efficient Unsupervised Soft Set based Quick Reduct (SSUSQR) algorithm is presented. This method is used to select features from the data set and compared with existing rough set based unsupervised feature selection methods. Then K-Means and Self Organizing Map (SOM) clustering algorithms are used to cluster the data. The performance of the feature selection algorithms is evaluated based on performance of clustering techniques. The results show that the proposed method effectively removes redundant features.", "source": "arxiv/ml"}
{"id": "arxiv:2534", "title": "Reinforcement learning for port-Hamiltonian systems", "text": "Passivity-based control (PBC) for port-Hamiltonian systems provides an intuitive way of achieving stabilization by rendering a system passive with respect to a desired storage function. However, in most instances the control law is obtained without any performance considerations and it has to be calculated by solving a complex partial differential equation (PDE). In order to address these issues we introduce a reinforcement learning approach into the energy-balancing passivity-based control (EB-PBC) method, which is a form of PBC in which the closed-loop energy is equal to the difference between the stored and supplied energies. We propose a technique to parameterize EB-PBC that preserves the systems's PDE matching conditions, does not require the specification of a global desired Hamiltonian, includes performance criteria, and is robust to extra non-linearities such as control input saturation. The parameters of the control law are found using actor-critic reinforcement learning, enabling learning near-optimal control policies satisfying a desired closed-loop energy landscape. The advantages are that near-optimal controllers can be generated using standard energy shaping techniques and that the solutions learned can be interpreted in terms of energy shaping and damping injection, which makes it possible to numerically assess stability using passivity theory. From the reinforcement learning perspective, our proposal allows for the class of port-Hamiltonian systems to be incorporated in the actor-critic framework, speeding up the learning thanks to the resulting parameterization of the policy. The method has been successfully applied to the pendulum swing-up problem in simulations and real-life experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2535", "title": "Random Spanning Trees and the Prediction of Weighted Graphs", "text": "We investigate the problem of sequentially predicting the binary labels on the nodes of an arbitrary weighted graph. We show that, under a suitable parametrization of the problem, the optimal number of prediction mistakes can be characterized (up to logarithmic factors) by the cutsize of a random spanning tree of the graph. The cutsize is induced by the unknown adversarial labeling of the graph nodes. In deriving our characterization, we obtain a simple randomized algorithm achieving in expectation the optimal mistake bound on any polynomially connected weighted graph. Our algorithm draws a random spanning tree of the original graph and then predicts the nodes of this tree in constant expected amortized time and linear space. Experiments on real-world datasets show that our method compares well to both global (Perceptron) and local (label propagation) methods, while being generally faster in practice.", "source": "arxiv/ml"}
{"id": "arxiv:2536", "title": "ADADELTA: An Adaptive Learning Rate Method", "text": "We present a novel per-dimension learning rate method for gradient descent called ADADELTA. The method dynamically adapts over time using only first order information and has minimal computational overhead beyond vanilla stochastic gradient descent. The method requires no manual tuning of a learning rate and appears robust to noisy gradient information, different model architecture choices, various data modalities and selection of hyperparameters. We show promising results compared to other methods on the MNIST digit classification task using a single machine and on a large scale voice dataset in a distributed cluster environment.", "source": "arxiv/ml"}
{"id": "arxiv:2537", "title": "Data complexity measured by principal graphs", "text": "How to measure the complexity of a finite set of vectors embedded in a multidimensional space? This is a non-trivial question which can be approached in many different ways. Here we suggest a set of data complexity measures using universal approximators, principal cubic complexes. Principal cubic complexes generalise the notion of principal manifolds for datasets with non-trivial topologies. The type of the principal cubic complex is determined by its dimension and a grammar of elementary graph transformations. The simplest grammar produces principal trees. We introduce three natural types of data complexity: 1) geometric (deviation of the data's approximator from some \"idealized\" configuration, such as deviation from harmonicity); 2) structural (how many elements of a principal graph are needed to approximate the data), and 3) construction complexity (how many applications of elementary graph transformations are needed to construct the principal object starting from the simplest one). We compute these measures for several simulated and real-life data distributions and show them in the \"accuracy-complexity\" plots, helping to optimize the accuracy/complexity ratio. We discuss various issues connected with measuring data complexity. Software for computing data complexity measures from principal cubic complexes is provided as well.", "source": "arxiv/ml"}
{"id": "arxiv:2538", "title": "A short note on the tail bound of Wishart distribution", "text": "We study the tail bound of the emperical covariance of multivariate normal distribution. Following the work of (Gittens & Tropp, 2011), we provide a tail bound with a small constant.", "source": "arxiv/ml"}
{"id": "arxiv:2539", "title": "Distributed optimization of deeply nested systems", "text": "In science and engineering, intelligent processing of complex signals such as images, sound or language is often performed by a parameterized hierarchy of nonlinear processing layers, sometimes biologically inspired. Hierarchical systems (or, more generally, nested systems) offer a way to generate complex mappings using simple stages. Each layer performs a different operation and achieves an ever more sophisticated representation of the input, as, for example, in an deep artificial neural network, an object recognition cascade in computer vision or a speech front-end processing. Joint estimation of the parameters of all the layers and selection of an optimal architecture is widely considered to be a difficult numerical nonconvex optimization problem, difficult to parallelize for execution in a distributed computation environment, and requiring significant human expert effort, which leads to suboptimal systems in practice. We describe a general mathematical strategy to learn the parameters and, to some extent, the architecture of nested systems, called the method of auxiliary coordinates (MAC). This replaces the original problem involving a deeply nested function with a constrained problem involving a different function in an augmented space without nesting. The constrained problem may be solved with penalty-based methods using alternating optimization over the parameters and the auxiliary coordinates. MAC has provable convergence, is easy to implement reusing existing algorithms for single layers, can be parallelized trivially and massively, applies even when parameter derivatives are not available or not desirable, and is competitive with state-of-the-art nonlinear optimizers even in the serial computation setting, often providing reasonable models within a few iterations.", "source": "arxiv/ml"}
{"id": "arxiv:2540", "title": "Fully scalable online-preprocessing algorithm for short oligonucleotide microarray atlases", "text": "Accumulation of standardized data collections is opening up novel opportunities for holistic characterization of genome function. The limited scalability of current preprocessing techniques has, however, formed a bottleneck for full utilization of contemporary microarray collections. While short oligonucleotide arrays constitute a major source of genome-wide profiling data, scalable probe-level preprocessing algorithms have been available only for few measurement platforms based on pre-calculated model parameters from restricted reference training sets. To overcome these key limitations, we introduce a fully scalable online-learning algorithm that provides tools to process large microarray atlases including tens of thousands of arrays. Unlike the alternatives, the proposed algorithm scales up in linear time with respect to sample size and is readily applicable to all short oligonucleotide platforms. This is the only available preprocessing algorithm that can learn probe-level parameters based on sequential hyperparameter updates at small, consecutive batches of data, thus circumventing the extensive memory requirements of the standard approaches and opening up novel opportunities to take full advantage of contemporary microarray data collections. Moreover, using the most comprehensive data collections to estimate probe-level effects can assist in pinpointing individual probes affected by various biases and provide new tools to guide array design and quality control. The implementation is freely available in R/Bioconductor at http://www.bioconductor.org/packages/devel/bioc/html/RPA.html", "source": "arxiv/ml"}
{"id": "arxiv:2541", "title": "Exponentially Weighted Moving Average Charts for Detecting Concept Drift", "text": "Classifying streaming data requires the development of methods which are computationally efficient and able to cope with changes in the underlying distribution of the stream, a phenomenon known in the literature as concept drift. We propose a new method for detecting concept drift which uses an Exponentially Weighted Moving Average (EWMA) chart to monitor the misclassification rate of an streaming classifier. Our approach is modular and can hence be run in parallel with any underlying classifier to provide an additional layer of concept drift detection. Moreover our method is computationally efficient with overhead O(1) and works in a fully online manner with no need to store data points in memory. Unlike many existing approaches to concept drift detection, our method allows the rate of false positive detections to be controlled and kept constant over time.", "source": "arxiv/ml"}
{"id": "arxiv:2542", "title": "Tangent Bundle Manifold Learning via Grassmann&Stiefel Eigenmaps", "text": "One of the ultimate goals of Manifold Learning (ML) is to reconstruct an unknown nonlinear low-dimensional manifold embedded in a high-dimensional observation space by a given set of data points from the manifold. We derive a local lower bound for the maximum reconstruction error in a small neighborhood of an arbitrary point. The lower bound is defined in terms of the distance between tangent spaces to the original manifold and the estimated manifold at the considered point and reconstructed point, respectively. We propose an amplification of the ML, called Tangent Bundle ML, in which the proximity not only between the original manifold and its estimator but also between their tangent spaces is required. We present a new algorithm that solves this problem and gives a new solution for the ML also.", "source": "arxiv/ml"}
{"id": "arxiv:2543", "title": "Hyperplane Arrangements and Locality-Sensitive Hashing with Lift", "text": "Locality-sensitive hashing converts high-dimensional feature vectors, such as image and speech, into bit arrays and allows high-speed similarity calculation with the Hamming distance. There is a hashing scheme that maps feature vectors to bit arrays depending on the signs of the inner products between feature vectors and the normal vectors of hyperplanes placed in the feature space. This hashing can be seen as a discretization of the feature space by hyperplanes. If labels for data are given, one can determine the hyperplanes by using learning algorithms. However, many proposed learning methods do not consider the hyperplanes' offsets. Not doing so decreases the number of partitioned regions, and the correlation between Hamming distances and Euclidean distances becomes small. In this paper, we propose a lift map that converts learning algorithms without the offsets to the ones that take into account the offsets. With this method, the learning methods without the offsets give the discretizations of spaces as if it takes into account the offsets. For the proposed method, we input several high-dimensional feature data sets and studied the relationship between the statistical characteristics of data, the number of hyperplanes, and the effect of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:2544", "title": "Transfer Learning Using Logistic Regression in Credit Scoring", "text": "The credit scoring risk management is a fast growing field due to consumer's credit requests. Credit requests, of new and existing customers, are often evaluated by classical discrimination rules based on customers information. However, these kinds of strategies have serious limits and don't take into account the characteristics difference between current customers and the future ones. The aim of this paper is to measure credit worthiness for non customers borrowers and to model potential risk given a heterogeneous population formed by borrowers customers of the bank and others who are not. We hold on previous works done in generalized gaussian discrimination and transpose them into the logistic model to bring out efficient discrimination rules for non customers' subpopulation. Therefore we obtain several simple models of connection between parameters of both logistic models associated respectively to the two subpopulations. The German credit data set is selected to experiment and to compare these models. Experimental results show that the use of links between the two subpopulations improve the classification accuracy for the new loan applicants.", "source": "arxiv/ml"}
{"id": "arxiv:2545", "title": "Gaussian Process Regression with Heteroscedastic or Non-Gaussian Residuals", "text": "Gaussian Process (GP) regression models typically assume that residuals are Gaussian and have the same variance for all observations. However, applications with input-dependent noise (heteroscedastic residuals) frequently arise in practice, as do applications in which the residuals do not have a Gaussian distribution. In this paper, we propose a GP Regression model with a latent variable that serves as an additional unobserved covariate for the regression. This model (which we call GPLC) allows for heteroscedasticity since it allows the function to have a changing partial derivative with respect to this unobserved covariate. With a suitable covariance function, our GPLC model can handle (a) Gaussian residuals with input-dependent variance, or (b) non-Gaussian residuals with input-dependent variance, or (c) Gaussian residuals with constant variance. We compare our model, using synthetic datasets, with a model proposed by Goldberg, Williams and Bishop (1998), which we refer to as GPLV, which only deals with case (a), as well as a standard GP model which can handle only case (c). Markov Chain Monte Carlo methods are developed for both modelsl. Experiments show that when the data is heteroscedastic, both GPLC and GPLV give better results (smaller mean squared error and negative log-probability density) than standard GP regression. In addition, when the residual are Gaussian, our GPLC model is generally nearly as good as GPLV, while when the residuals are non-Gaussian, our GPLC model is better than GPLV.", "source": "arxiv/ml"}
{"id": "arxiv:2546", "title": "Echo State Queueing Network: a new reservoir computing learning tool", "text": "In the last decade, a new computational paradigm was introduced in the field of Machine Learning, under the name of Reservoir Computing (RC). RC models are neural networks which a recurrent part (the reservoir) that does not participate in the learning process, and the rest of the system where no recurrence (no neural circuit) occurs. This approach has grown rapidly due to its success in solving learning tasks and other computational applications. Some success was also observed with another recently proposed neural network designed using Queueing Theory, the Random Neural Network (RandNN). Both approaches have good properties and identified drawbacks. In this paper, we propose a new RC model called Echo State Queueing Network (ESQN), where we use ideas coming from RandNNs for the design of the reservoir. ESQNs consist in ESNs where the reservoir has a new dynamics inspired by recurrent RandNNs. The paper positions ESQNs in the global Machine Learning area, and provides examples of their use and performances. We show on largely used benchmarks that ESQNs are very accurate tools, and we illustrate how they compare with standard ESNs.", "source": "arxiv/ml"}
{"id": "arxiv:2547", "title": "On-line relational SOM for dissimilarity data", "text": "In some applications and in order to address real world situations better, data may be more complex than simple vectors. In some examples, they can be known through their pairwise dissimilarities only. Several variants of the Self Organizing Map algorithm were introduced to generalize the original algorithm to this framework. Whereas median SOM is based on a rough representation of the prototypes, relational SOM allows representing these prototypes by a virtual combination of all elements in the data set. However, this latter approach suffers from two main drawbacks. First, its complexity can be large. Second, only a batch version of this algorithm has been studied so far and it often provides results having a bad topographic organization. In this article, an on-line version of relational SOM is described and justified. The algorithm is tested on several datasets, including categorical data and graphs, and compared with the batch version and with other SOM algorithms for non vector data.", "source": "arxiv/ml"}
{"id": "arxiv:2548", "title": "Focus of Attention for Linear Predictors", "text": "We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a phenomenon which is characterized by the event when most of the features agree on the class of an example. By stopping the feature evaluation when encountering an easy- to-classify example, the predictor can achieve substantial gains in computation. Our method provides a natural attention mechanism for linear predictors where the predictor concentrates most of its computation on hard-to-classify examples and quickly discards easy-to-classify ones. By modifying a linear prediction algorithm such as an SVM or AdaBoost to include our attentive method we prove that the average number of features computed is O(sqrt(n log 1/sqrt(delta))) where n is the original number of features, and delta is the error rate incurred due to early stopping. We demonstrate the effectiveness of Attentive Prediction on MNIST, Real-sim, Gisette, and synthetic datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2549", "title": "Maximizing a Nonnegative, Monotone, Submodular Function Constrained to Matchings", "text": "Submodular functions have many applications. Matchings have many applications. The bitext word alignment problem can be modeled as the problem of maximizing a nonnegative, monotone, submodular function constrained to matchings in a complete bipartite graph where each vertex corresponds to a word in the two input sentences and each edge represents a potential word-to-word translation. We propose a more general problem of maximizing a nonnegative, monotone, submodular function defined on the edge set of a complete graph constrained to matchings; we call this problem the CSM-Matching problem. CSM-Matching also generalizes the maximum-weight matching problem, which has a polynomial-time algorithm; however, we show that it is NP-hard to approximate CSM-Matching within a factor of e/(e-1) by reducing the max k-cover problem to it. Our main result is a simple, greedy, 3-approximation algorithm for CSM-Matching. Then we reduce CSM-Matching to maximizing a nonnegative, monotone, submodular function over two matroids, i.e., CSM-2-Matroids. CSM-2-Matroids has a (2+epsilon)-approximation algorithm - called LSV2. We show that we can find a (4+epsilon)-approximate solution to CSM-Matching using LSV2. We extend this approach to similar problems.", "source": "arxiv/ml"}
{"id": "arxiv:2550", "title": "Training a Functional Link Neural Network Using an Artificial Bee Colony for Solving a Classification Problems", "text": "Artificial Neural Networks have emerged as an important tool for classification and have been widely used to classify a non-linear separable pattern. The most popular artificial neural networks model is a Multilayer Perceptron (MLP) as it is able to perform classification task with significant success. However due to the complexity of MLP structure and also problems such as local minima trapping, over fitting and weight interference have made neural network training difficult. Thus, the easy way to avoid these problems is to remove the hidden layers. This paper presents the ability of Functional Link Neural Network (FLNN) to overcome the complexity structure of MLP by using single layer architecture and propose an Artificial Bee Colony (ABC) optimization for training the FLNN. The proposed technique is expected to provide better learning scheme for a classifier in order to get more accurate classification result", "source": "arxiv/ml"}
{"id": "arxiv:2551", "title": "Fast Solutions to Projective Monotone Linear Complementarity Problems", "text": "We present a new interior-point potential-reduction algorithm for solving monotone linear complementarity problems (LCPs) that have a particular special structure: their matrix $M\\in{\\mathbb R}^{n\\times n}$ can be decomposed as $M=\\Phi U + \\Pi_0$, where the rank of $\\Phi$ is $k<n$, and $\\Pi_0$ denotes Euclidean projection onto the nullspace of $\\Phi^\\top$. We call such LCPs projective. Our algorithm solves a monotone projective LCP to relative accuracy $\\epsilon$ in $O(\\sqrt n \\ln(1/\\epsilon))$ iterations, with each iteration requiring $O(nk^2)$ flops. This complexity compares favorably with interior-point algorithms for general monotone LCPs: these algorithms also require $O(\\sqrt n \\ln(1/\\epsilon))$ iterations, but each iteration needs to solve an $n\\times n$ system of linear equations, a much higher cost than our algorithm when $k\\ll n$. Our algorithm works even though the solution to a projective LCP is not restricted to lie in any low-rank subspace.", "source": "arxiv/ml"}
{"id": "arxiv:2552", "title": "Bethe Bounds and Approximating the Global Optimum", "text": "Inference in general Markov random fields (MRFs) is NP-hard, though identifying the maximum a posteriori (MAP) configuration of pairwise MRFs with submodular cost functions is efficiently solvable using graph cuts. Marginal inference, however, even for this restricted class, is in #P. We prove new formulations of derivatives of the Bethe free energy, provide bounds on the derivatives and bracket the locations of stationary points, introducing a new technique called Bethe bound propagation. Several results apply to pairwise models whether associative or not. Applying these to discretized pseudo-marginals in the associative case we present a polynomial time approximation scheme for global optimization provided the maximum degree is $O(\\log n)$, and discuss several extensions.", "source": "arxiv/ml"}
{"id": "arxiv:2553", "title": "On Distributed Online Classification in the Midst of Concept Drifts", "text": "In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners and study the performance advantage that diffusion strategies have over individual non-cooperative processing. We conduct extensive simulations to illustrate the results.", "source": "arxiv/ml"}
{"id": "arxiv:2554", "title": "CloudSVM : Training an SVM Classifier in Cloud Computing Systems", "text": "In conventional method, distributed support vector machines (SVM) algorithms are trained over pre-configured intranet/internet environments to find out an optimal classifier. These methods are very complicated and costly for large datasets. Hence, we propose a method that is referred as the Cloud SVM training mechanism (CloudSVM) in a cloud computing environment with MapReduce technique for distributed machine learning applications. Accordingly, (i) SVM algorithm is trained in distributed cloud storage servers that work concurrently; (ii) merge all support vectors in every trained cloud node; and (iii) iterate these two steps until the SVM converges to the optimal classifier function. Large scale data sets are not possible to train using SVM algorithm on a single computer. The results of this study are important for training of large scale data sets for machine learning applications. We provided that iterative training of splitted data set in cloud computing environment using SVM will converge to a global optimal classifier in finite iteration size.", "source": "arxiv/ml"}
{"id": "arxiv:2555", "title": "Policy Evaluation with Variance Related Risk Criteria in Markov Decision Processes", "text": "In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose both TD(0) and LSTD(lambda) variants with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.", "source": "arxiv/ml"}
{"id": "arxiv:2556", "title": "Semi-Supervised Domain Adaptation with Non-Parametric Copulas", "text": "A new framework based on the theory of copulas is proposed to address semi- supervised domain adaptation problems. The presented method factorizes any multivariate density into a product of marginal distributions and bivariate cop- ula functions. Therefore, changes in each of these factors can be detected and corrected to adapt a density model accross different learning domains. Impor- tantly, we introduce a novel vine copula model, which allows for this factorization in a non-parametric manner. Experimental results on regression problems with real-world data illustrate the efficacy of the proposed approach when compared to state-of-the-art techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2557", "title": "A Novel Design Specification Distance(DSD) Based K-Mean Clustering Performace Evluation on Engineering Materials Database", "text": "Organizing data into semantically more meaningful is one of the fundamental modes of understanding and learning. Cluster analysis is a formal study of methods for understanding and algorithm for learning. K-mean clustering algorithm is one of the most fundamental and simple clustering algorithms. When there is no prior knowledge about the distribution of data sets, K-mean is the first choice for clustering with an initial number of clusters. In this paper a novel distance metric called Design Specification (DS) distance measure function is integrated with K-mean clustering algorithm to improve cluster accuracy. The K-means algorithm with proposed distance measure maximizes the cluster accuracy to 99.98% at P = 1.525, which is determined through the iterative procedure. The performance of Design Specification (DS) distance measure function with K - mean algorithm is compared with the performances of other standard distance functions such as Euclidian, squared Euclidean, City Block, and Chebshew similarity measures deployed with K-mean algorithm.The proposed method is evaluated on the engineering materials database. The experiments on cluster analysis and the outlier profiling show that these is an excellent improvement in the performance of the proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:2558", "title": "Follow the Leader If You Can, Hedge If You Must", "text": "Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has terrible performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We introduce the FlipFlop algorithm, which is the first method that provably combines the best of both worlds. As part of our construction, we develop AdaHedge, which is a new way of dynamically tuning the learning rate in Hedge without using the doubling trick. AdaHedge refines a method by Cesa-Bianchi, Mansour and Stoltz (2007), yielding slightly improved worst-case guarantees. By interleaving AdaHedge and FTL, the FlipFlop algorithm achieves regret within a constant factor of the FTL regret, without sacrificing AdaHedge's worst-case guarantees. AdaHedge and FlipFlop do not need to know the range of the losses in advance; moreover, unlike earlier methods, both have the intuitive property that the issued weights are invariant under rescaling and translation of the losses. The losses are also allowed to be negative, in which case they may be interpreted as gains.", "source": "arxiv/ml"}
{"id": "arxiv:2559", "title": "Learning Hierarchical Object Maps Of Non-Stationary Environments with mobile robots", "text": "Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exploits the fact that many objects found in office environments look alike (e.g., chairs, recycling bins). It does so through a two-level hierarchical representation, which links individual objects with generic shape templates of object classes. We derive an approximate EM algorithm for learning shape parameters at both levels of the hierarchy, using local occupancy grid maps for representing shape. Additionally, we develop a Bayesian model selection algorithm that enables the robot to estimate the total number of objects and object templates in the environment. Experimental results using a real robot equipped with a laser range finder indicate that our approach performs well at learning object-based maps of simple office environments. The approach outperforms a previously developed non-hierarchical algorithm that models objects but lacks class templates.", "source": "arxiv/ml"}
{"id": "arxiv:2560", "title": "Tree-dependent Component Analysis", "text": "We present a generalization of independent component analysis (ICA), where instead of looking for a linear transform that makes the data components independent, we look for a transform that makes the data components well fit by a tree-structured graphical model. Treating the problem as a semiparametric statistical problem, we show that the optimal transform is found by minimizing a contrast function based on mutual information, a function that directly extends the contrast function used for classical ICA. We provide two approximations of this contrast function, one using kernel density estimation, and another using kernel generalized variance. This tree-dependent component analysis framework leads naturally to an efficient general multivariate density estimation technique where only bivariate density estimation needs to be performed.", "source": "arxiv/ml"}
{"id": "arxiv:2561", "title": "Learning with Scope, with Application to Information Extraction and Classification", "text": "In probabilistic approaches to classification and information extraction, one typically builds a statistical model of words under the assumption that future data will exhibit the same regularities as the training data. In many data sets, however, there are scope-limited features whose predictive power is only applicable to a certain subset of the data. For example, in information extraction from web pages, word formatting may be indicative of extraction category in different ways on different web pages. The difficulty with using such features is capturing and exploiting the new regularities encountered in previously unseen data. In this paper, we propose a hierarchical probabilistic model that uses both local/scope-limited features, such as word formatting, and global features, such as word content. The local regularities are modeled as an unobserved random parameter which is drawn once for each local data set. This random parameter is estimated during the inference process and then used to perform classification with both the local and global features--- a procedure which is akin to automatically retuning the classifier to the local regularities on each newly encountered web page. Exact inference is intractable and we present approximations via point estimates and variational methods. Empirical results on large collections of web data demonstrate that this method significantly improves performance from traditional models of global features alone.", "source": "arxiv/ml"}
{"id": "arxiv:2562", "title": "Continuation Methods for Mixing Heterogenous Sources", "text": "A number of modern learning tasks involve estimation from heterogeneous information sources. This includes classification with labeled and unlabeled data as well as other problems with analogous structure such as competitive (game theoretic) problems. The associated estimation problems can be typically reduced to solving a set of fixed point equations (consistency conditions). We introduce a general method for combining a preferred information source with another in this setting by evolving continuous paths of fixed points at intermediate allocations. We explicitly identify critical points along the unique paths to either increase the stability of estimation or to ensure a significant departure from the initial source. The homotopy continuation approach is guaranteed to terminate at the second source, and involves no combinatorial effort. We illustrate the power of these ideas both in classification tasks with labeled and unlabeled data, as well as in the context of a competitive (min-max) formulation of DNA sequence motif discovery.", "source": "arxiv/ml"}
{"id": "arxiv:2563", "title": "Interpolating Conditional Density Trees", "text": "Joint distributions over many variables are frequently modeled by decomposing them into products of simpler, lower-dimensional conditional distributions, such as in sparsely connected Bayesian networks. However, automatically learning such models can be very computationally expensive when there are many datapoints and many continuous variables with complex nonlinear relationships, particularly when no good ways of decomposing the joint distribution are known a priori. In such situations, previous research has generally focused on the use of discretization techniques in which each continuous variable has a single discretization that is used throughout the entire network. \\ In this paper, we present and compare a wide variety of tree-based algorithms for learning and evaluating conditional density estimates over continuous variables. These trees can be thought of as discretizations that vary according to the particular interactions being modeled; however, the density within a given leaf of the tree need not be assumed constant, and we show that such nonuniform leaf densities lead to more accurate density estimation. We have developed Bayesian network structure-learning algorithms that employ these tree-based conditional density representations, and we show that they can be used to practically learn complex joint probability models over dozens of continuous variables from thousands of datapoints. We focus on finding models that are simultaneously accurate, fast to learn, and fast to evaluate once they are learned.", "source": "arxiv/ml"}
{"id": "arxiv:2564", "title": "An Information-Theoretic External Cluster-Validity Measure", "text": "In this paper we propose a measure of clustering quality or accuracy that is appropriate in situations where it is desirable to evaluate a clustering algorithm by somehow comparing the clusters it produces with ``ground truth' consisting of classes assigned to the patterns by manual means or some other means in whose veracity there is confidence. Such measures are refered to as ``external'. Our measure also has the characteristic of allowing clusterings with different numbers of clusters to be compared in a quantitative and principled way. Our evaluation scheme quantitatively measures how useful the cluster labels of the patterns are as predictors of their class labels. In cases where all clusterings to be compared have the same number of clusters, the measure is equivalent to the mutual information between the cluster labels and the class labels. In cases where the numbers of clusters are different, however, it computes the reduction in the number of bits that would be required to encode (compress) the class labels if both the encoder and decoder have free acccess to the cluster labels. To achieve this encoding the estimated conditional probabilities of the class labels given the cluster labels must also be encoded. These estimated probabilities can be seen as a model for the class labels and their associated code length as a model cost.", "source": "arxiv/ml"}
{"id": "arxiv:2565", "title": "The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning", "text": "Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods. Yet, there are few experiments on learning with deictic representations reported in the literature. In this paper we explore the effectiveness of two forms of deictic representation and a na\\\"{i}ve propositional representation in a simple blocks-world domain. We find, empirically, that the deictic representations actually worsen learning performance. We conclude with a discussion of possible causes of these results and strategies for more effective learning in domains with objects.", "source": "arxiv/ml"}
{"id": "arxiv:2566", "title": "Dimension Correction for Hierarchical Latent Class Models", "text": "Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When hidden variables are present, however, standard dimension might no longer be appropriate. One should instead use effective dimension (Geiger et al. 1996). This paper is concerned with the computation of effective dimension. First we present an upper bound on the effective dimension of a latent class (LC) model. This bound is tight and its computation is easy. We then consider a generalization of LC models called hierarchical latent class (HLC) models (Zhang 2002). We show that the effective dimension of an HLC model can be obtained from the effective dimensions of some related LC models. We also demonstrate empirically that using effective dimension in place of standard dimension improves the quality of models learned from data.", "source": "arxiv/ml"}
{"id": "arxiv:2567", "title": "Almost-everywhere algorithmic stability and generalization error", "text": "We explore in some detail the notion of algorithmic stability as a viable framework for analyzing the generalization error of learning algorithms. We introduce the new notion of training stability of a learning algorithm and show that, in a general setting, it is sufficient for good bounds on generalization error. In the PAC setting, training stability is both necessary and sufficient for learnability.\\ The approach based on training stability makes no reference to VC dimension or VC entropy. There is no need to prove uniform convergence, and generalization error is bounded directly via an extended McDiarmid inequality. As a result it potentially allows us to deal with a broader class of learning algorithms than Empirical Risk Minimization. \\ We also explore the relationships among VC dimension, generalization error, and various notions of stability. Several examples of learning algorithms are considered.", "source": "arxiv/ml"}
{"id": "arxiv:2568", "title": "Decayed MCMC Filtering", "text": "Filtering---estimating the state of a partially observable Markov process from a sequence of observations---is one of the most widely studied problems in control theory, AI, and computational statistics. Exact computation of the posterior distribution is generally intractable for large discrete systems and for nonlinear continuous systems, so a good deal of effort has gone into developing robust approximation algorithms. This paper describes a simple stochastic approximation algorithm for filtering called {em decayed MCMC}. The algorithm applies Markov chain Monte Carlo sampling to the space of state trajectories using a proposal distribution that favours flips of more recent state variables. The formal analysis of the algorithm involves a generalization of standard coupling arguments for MCMC convergence. We prove that for any ergodic underlying Markov process, the convergence time of decayed MCMC with inverse-polynomial decay remains bounded as the length of the observation sequence grows. We show experimentally that decayed MCMC is at least competitive with other approximation algorithms such as particle filtering.", "source": "arxiv/ml"}
{"id": "arxiv:2569", "title": "Staged Mixture Modelling and Boosting", "text": "In this paper, we introduce and evaluate a data-driven staged mixture modeling technique for building density, regression, and classification models. Our basic approach is to sequentially add components to a finite mixture model using the structural expectation maximization (SEM) algorithm. We show that our technique is qualitatively similar to boosting. This correspondence is a natural byproduct of the fact that we use the SEM algorithm to sequentially fit the mixture model. Finally, in our experimental evaluation, we demonstrate the effectiveness of our approach on a variety of prediction and density estimation tasks using real-world data.", "source": "arxiv/ml"}
{"id": "arxiv:2570", "title": "Optimal Time Bounds for Approximate Clustering", "text": "Clustering is a fundamental problem in unsupervised learning, and has been studied widely both as a problem of learning mixture models and as an optimization problem. In this paper, we study clustering with respect the emph{k-median} objective function, a natural formulation of clustering in which we attempt to minimize the average distance to cluster centers. One of the main contributions of this paper is a simple but powerful sampling technique that we call emph{successive sampling} that could be of independent interest. We show that our sampling procedure can rapidly identify a small set of points (of size just O(klog{n/k})) that summarize the input points for the purpose of clustering. Using successive sampling, we develop an algorithm for the k-median problem that runs in O(nk) time for a wide range of values of k and is guaranteed, with high probability, to return a solution with cost at most a constant factor times optimal. We also establish a lower bound of Omega(nk) on any randomized constant-factor approximation algorithm for the k-median problem that succeeds with even a negligible (say 1/100) probability. Thus we establish a tight time bound of Theta(nk) for the k-median problem for a wide range of values of k. The best previous upper bound for the problem was O(nk), where the O-notation hides polylogarithmic factors in n and k. The best previous lower bound of O(nk) applied only to deterministic k-median algorithms. While we focus our presentation on the k-median objective, all our upper bounds are valid for the k-means objective as well. In this context our algorithm compares favorably to the widely used k-means heuristic, which requires O(nk) time for just one iteration and provides no useful approximation guarantees.", "source": "arxiv/ml"}
{"id": "arxiv:2571", "title": "Expectation-Propogation for the Generative Aspect Model", "text": "The generative aspect model is an extension of the multinomial model for text that allows word probabilities to vary stochastically across documents. Previous results with aspect models have been promising, but hindered by the computational difficulty of carrying out inference and learning. This paper demonstrates that the simple variational methods of Blei et al (2001) can lead to inaccurate inferences and biased learning for the generative aspect model. We develop an alternative approach that leads to higher accuracy at comparable cost. An extension of Expectation-Propagation is used for inference and then embedded in an EM algorithm for learning. Experimental results are presented for both synthetic and real data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2572", "title": "Bayesian Network Classifiers in a High Dimensional Framework", "text": "We present a growing dimension asymptotic formalism. The perspective in this paper is classification theory and we show that it can accommodate probabilistic networks classifiers, including naive Bayes model and its augmented version. When represented as a Bayesian network these classifiers have an important advantage: The corresponding discriminant function turns out to be a specialized case of a generalized additive model, which makes it possible to get closed form expressions for the asymptotic misclassification probabilities used here as a measure of classification accuracy. Moreover, in this paper we propose a new quantity for assessing the discriminative power of a set of features which is then used to elaborate the augmented naive Bayes classifier. The result is a weighted form of the augmented naive Bayes that distributes weights among the sets of features according to their discriminative power. We derive the asymptotic distribution of the sample based discriminative power and show that it is seriously overestimated in a high dimensional case. We then apply this result to find the optimal, in a sense of minimum misclassification probability, type of weighting.", "source": "arxiv/ml"}
{"id": "arxiv:2573", "title": "Asymptotic Model Selection for Naive Bayesian Networks", "text": "We develop a closed form asymptotic formula to compute the marginal likelihood of data given a naive Bayesian network model with two hidden states and binary features. This formula deviates from the standard BIC score. Our work provides a concrete example that the BIC score is generally not valid for statistical models that belong to a stratified exponential family. This stands in contrast to linear and curved exponential families, where the BIC score has been proven to provide a correct approximation for the marginal likelihood.", "source": "arxiv/ml"}
{"id": "arxiv:2574", "title": "Advances in Boosting (Invited Talk)", "text": "Boosting is a general method of generating many simple classification rules and combining them into a single, highly accurate rule. In this talk, I will review the AdaBoost boosting algorithm and some of its underlying theory, and then look at how this theory has helped us to face some of the challenges of applying AdaBoost in two domains: In the first of these, we used boosting for predicting and modeling the uncertainty of prices in complicated, interacting auctions. The second application was to the classification of caller utterances in a telephone spoken-dialogue system where we faced two challenges: the need to incorporate prior knowledge to compensate for initially insufficient data; and a later need to filter the large stream of unlabeled examples being collected to select the ones whose labels are likely to be most informative.", "source": "arxiv/ml"}
{"id": "arxiv:2575", "title": "An MDP-based Recommender System", "text": "Typical Recommender systems adopt a static view of the recommendation process and treat it as a prediction problem. We argue that it is more appropriate to view the problem of generating recommendations as a sequential decision problem and, consequently, that Markov decision processes (MDP) provide a more appropriate model for Recommender systems. MDPs introduce two benefits: they take into account the long-term effects of each recommendation, and they take into account the expected value of each recommendation. To succeed in practice, an MDP-based Recommender system must employ a strong initial model; and the bulk of this paper is concerned with the generation of such a model. In particular, we suggest the use of an n-gram predictive model for generating the initial MDP. Our n-gram model induces a Markov-chain model of user behavior whose predictive accuracy is greater than that of existing predictive models. We describe our predictive model in detail and evaluate its performance on real data. In addition, we show how the model can be used in an MDP-based Recommender system.", "source": "arxiv/ml"}
{"id": "arxiv:2576", "title": "Reinforcement Learning with Partially Known World Dynamics", "text": "Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not provide a natural framework in which to specify knowledge about the domain dynamics. The designer must either admit to knowing nothing about the dynamics or completely specify the dynamics (thereby turning it into a planning problem). We propose a new framework called a partially known Markov decision process (PKMDP) which allows the designer to specify known dynamics while still leaving portions of the environment s dynamics unknown.The model represents NOT ONLY the environment dynamics but also the agents knowledge of the dynamics. We present a reinforcement learning algorithm for this model based on importance sampling. The algorithm incorporates planning based on the known dynamics and learning about the unknown dynamics. Our results clearly demonstrate the ability to add domain knowledge and the resulting benefits for learning.", "source": "arxiv/ml"}
{"id": "arxiv:2577", "title": "Unsupervised Active Learning in Large Domains", "text": "Active learning is a powerful approach to analyzing data effectively. We show that the feasibility of active learning depends crucially on the choice of measure with respect to which the query is being optimized. The standard information gain, for example, does not permit an accurate evaluation with a small committee, a representative subset of the model space. We propose a surrogate measure requiring only a small committee and discuss the properties of this new measure. We devise, in addition, a bootstrap approach for committee selection. The advantages of this approach are illustrated in the context of recovering (regulatory) network models.", "source": "arxiv/ml"}
{"id": "arxiv:2578", "title": "Discriminative Probabilistic Models for Relational Data", "text": "In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently, ignoring the correlations between them. Recently, Probabilistic Relational Models, a relational version of Bayesian networks, were used to define a joint probabilistic model for a collection of related entities. In this paper, we present an alternative framework that builds on (conditional) Markov networks and addresses two limitations of the previous approach. First, undirected models do not impose the acyclicity constraint that hinders representation of many important relational dependencies in directed models. Second, undirected models are well suited for discriminative training, where we optimize the conditional likelihood of the labels given the features, which generally improves classification accuracy. We show how to train these models effectively, and how to use approximate probabilistic inference over the learned model for collective classification of multiple related entities. We provide experimental results on a webpage classification task, showing that accuracy can be significantly improved by modeling relational dependencies.", "source": "arxiv/ml"}
{"id": "arxiv:2579", "title": "A New Class of Upper Bounds on the Log Partition Function", "text": "Bounds on the log partition function are important in a variety of contexts, including approximate inference, model fitting, decision theory, and large deviations analysis. We introduce a new class of upper bounds on the log partition function, based on convex combinations of distributions in the exponential domain, that is applicable to an arbitrary undirected graphical model. In the special case of convex combinations of tree-structured distributions, we obtain a family of variational problems, similar to the Bethe free energy, but distinguished by the following desirable properties: i. they are cnvex, and have a unique global minimum; and ii. the global minimum gives an upper bound on the log partition function. The global minimum is defined by stationary conditions very similar to those defining fixed points of belief propagation or tree-based reparameterization Wainwright et al., 2001. As with BP fixed points, the elements of the minimizing argument can be used as approximations to the marginals of the original model. The analysis described here can be extended to structures of higher treewidth e.g., hypertrees, thereby making connections with more advanced approximations e.g., Kikuchi and variants Yedidia et al., 2001; Minka, 2001.", "source": "arxiv/ml"}
{"id": "arxiv:2580", "title": "IPF for Discrete Chain Factor Graphs", "text": "Iterative Proportional Fitting (IPF), combined with EM, is commonly used as an algorithm for likelihood maximization in undirected graphical models. In this paper, we present two iterative algorithms that generalize upon IPF. The first one is for likelihood maximization in discrete chain factor graphs, which we define as a wide class of discrete variable models including undirected graphical models and Bayesian networks, but also chain graphs and sigmoid belief networks. The second one is for conditional likelihood maximization in standard undirected models and Bayesian networks. In both algorithms, the iteration steps are expressed in closed form. Numerical simulations show that the algorithms are competitive with state of the art methods.", "source": "arxiv/ml"}
{"id": "arxiv:2581", "title": "The Sum-over-Forests density index: identifying dense regions in a graph", "text": "This work introduces a novel nonparametric density index defined on graphs, the Sum-over-Forests (SoF) density index. It is based on a clear and intuitive idea: high-density regions in a graph are characterized by the fact that they contain a large amount of low-cost trees with high outdegrees while low-density regions contain few ones. Therefore, a Boltzmann probability distribution on the countable set of forests in the graph is defined so that large (high-cost) forests occur with a low probability while short (low-cost) forests occur with a high probability. Then, the SoF density index of a node is defined as the expected outdegree of this node in a non-trivial tree of the forest, thus providing a measure of density around that node. Following the matrix-forest theorem, and a statistical physics framework, it is shown that the SoF density index can be easily computed in closed form through a simple matrix inversion. Experiments on artificial and real data sets show that the proposed index performs well on finding dense regions, for graphs of various origins.", "source": "arxiv/ml"}
{"id": "arxiv:2582", "title": "Borrowing strengh in hierarchical Bayes: Posterior concentration of the Dirichlet base measure", "text": "This paper studies posterior concentration behavior of the base probability measure of a Dirichlet measure, given observations associated with the sampled Dirichlet processes, as the number of observations tends to infinity. The base measure itself is endowed with another Dirichlet prior, a construction known as the hierarchical Dirichlet processes (Teh et al. [J. Amer. Statist. Assoc. 101 (2006) 1566-1581]). Convergence rates are established in transportation distances (i.e., Wasserstein metrics) under various conditions on the geometry of the support of the true base measure. As a consequence of the theory, we demonstrate the benefit of \"borrowing strength\" in the inference of multiple groups of data - a powerful insight often invoked to motivate hierarchical modeling. In certain settings, the gain in efficiency due to the latent hierarchy can be dramatic, improving from a standard nonparametric rate to a parametric rate of convergence. Tools developed include transportation distances for nonparametric Bayesian hierarchies of random measures, the existence of tests for Dirichlet measures, and geometric properties of the support of Dirichlet measures.", "source": "arxiv/ml"}
{"id": "arxiv:2583", "title": "Finding the True Frequent Itemsets", "text": "Frequent Itemsets (FIs) mining is a fundamental primitive in data mining. It requires to identify all itemsets appearing in at least a fraction $\\theta$ of a transactional dataset $\\mathcal{D}$. Often though, the ultimate goal of mining $\\mathcal{D}$ is not an analysis of the dataset \\emph{per se}, but the understanding of the underlying process that generated it. Specifically, in many applications $\\mathcal{D}$ is a collection of samples obtained from an unknown probability distribution $\\pi$ on transactions, and by extracting the FIs in $\\mathcal{D}$ one attempts to infer itemsets that are frequently (i.e., with probability at least $\\theta$) generated by $\\pi$, which we call the True Frequent Itemsets (TFIs). Due to the inherently stochastic nature of the generative process, the set of FIs is only a rough approximation of the set of TFIs, as it often contains a huge number of \\emph{false positives}, i.e., spurious itemsets that are not among the TFIs. In this work we design and analyze an algorithm to identify a threshold $\\hat{\\theta}$ such that the collection of itemsets with frequency at least $\\hat{\\theta}$ in $\\mathcal{D}$ contains only TFIs with probability at least $1-\\delta$, for some user-specified $\\delta$. Our method uses results from statistical learning theory involving the (empirical) VC-dimension of the problem at hand. This allows us to identify almost all the TFIs without including any false positive. We also experimentally compare our method with the direct mining of $\\mathcal{D}$ at frequency $\\theta$ and with techniques based on widely-used standard bounds (i.e., the Chernoff bounds) of the binomial distribution, and show that our algorithm outperforms these methods and achieves even better results than what is guaranteed by the theoretical analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2584", "title": "Dynamical Models and Tracking Regret in Online Convex Programming", "text": "This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator's deviation from the best dynamical model in this family. Previous online optimization methods are designed to have a total accumulated loss comparable to that of the best comparator sequence, and existing tracking or shifting regret bounds scale with the overall variation of the comparator sequence. In many practical scenarios, however, the environment is nonstationary and comparator sequences with small variation are quite weak, resulting in large losses. The proposed Dynamic Mirror Descent method, in contrast, can yield low regret relative to highly variable comparator sequences by both tracking the best dynamical model and forming predictions based on that model. This concept is demonstrated empirically in the context of sequential compressive observations of a dynamic scene and tracking a dynamic social network.", "source": "arxiv/ml"}
{"id": "arxiv:2585", "title": "Automated Variational Inference in Probabilistic Programming", "text": "We present a new algorithm for approximate inference in probabilistic programs, based on a stochastic gradient for variational programs. This method is efficient without restrictions on the probabilistic program; it is particularly practical for distributions which are not analytically tractable, including highly structured distributions that arise in probabilistic programs. We show how to automatically derive mean-field probabilistic programs and optimize them, and demonstrate that our perspective improves inference efficiency over other algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2586", "title": "Coupled Neural Associative Memories", "text": "We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise. It is based on dividing the neurons into local clusters and parallel plains, very similar to the architecture of the visual cortex of macaque brain. The common features of our proposed architecture with those of spatially-coupled codes enable us to show that the performance of such networks in eliminating noise is drastically better than the previous approaches while maintaining the ability of learning an exponentially large number of patterns. Previous work either failed in providing good performance during the recall phase or in offering large pattern retrieval (storage) capacities. We also present computational experiments that lend additional support to the theoretical analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2587", "title": "An Efficient Algorithm for Upper Bound on the Partition Function of Nucleic Acids", "text": "It has been shown that minimum free energy structure for RNAs and RNA-RNA interaction is often incorrect due to inaccuracies in the energy parameters and inherent limitations of the energy model. In contrast, ensemble based quantities such as melting temperature and equilibrium concentrations can be more reliably predicted. Even structure prediction by sampling from the ensemble and clustering those structures by Sfold [7] has proven to be more reliable than minimum free energy structure prediction. The main obstacle for ensemble based approaches is the computational complexity of the partition function and base pairing probabilities. For instance, the space complexity of the partition function for RNA-RNA interaction is $O(n^4)$ and the time complexity is $O(n^6)$ which are prohibitively large [4,12]. Our goal in this paper is to give a fast algorithm, based on sparse folding, to calculate an upper bound on the partition function. Our work is based on the recent algorithm of Hazan and Jaakkola [10]. The space complexity of our algorithm is the same as that of sparse folding algorithms, and the time complexity of our algorithm is $O(MFE(n)\\ell)$ for single RNA and $O(MFE(m, n)\\ell)$ for RNA-RNA interaction in practice, in which $MFE$ is the running time of sparse folding and $\\ell \\leq n$ ($\\ell \\leq n + m$) is a sequence dependent parameter.", "source": "arxiv/ml"}
{"id": "arxiv:2588", "title": "The RNA Newton Polytope and Learnability of Energy Parameters", "text": "Despite nearly two scores of research on RNA secondary structure and RNA-RNA interaction prediction, the accuracy of the state-of-the-art algorithms are still far from satisfactory. Researchers have proposed increasingly complex energy models and improved parameter estimation methods in anticipation of endowing their methods with enough power to solve the problem. The output has disappointingly been only modest improvements, not matching the expectations. Even recent massively featured machine learning approaches were not able to break the barrier. In this paper, we introduce the notion of learnability of the parameters of an energy model as a measure of its inherent capability. We say that the parameters of an energy model are learnable iff there exists at least one set of such parameters that renders every known RNA structure to date the minimum free energy structure. We derive a necessary condition for the learnability and give a dynamic programming algorithm to assess it. Our algorithm computes the convex hull of the feature vectors of all feasible structures in the ensemble of a given input sequence. Interestingly, that convex hull coincides with the Newton polytope of the partition function as a polynomial in energy parameters. We demonstrated the application of our theory to a simple energy model consisting of a weighted count of A-U and C-G base pairs. Our results show that this simple energy model satisfies the necessary condition for less than one third of the input unpseudoknotted sequence-structure pairs chosen from the RNA STRAND v2.0 database. For another one third, the necessary condition is barely violated, which suggests that augmenting this simple energy model with more features such as the Turner loops may solve the problem. The necessary condition is severely violated for 8%, which provides a small set of hard cases that require further investigation.", "source": "arxiv/ml"}
{"id": "arxiv:2589", "title": "Linear Bandits in High Dimension and Recommendation Systems", "text": "A large number of online services provide automated recommendations to help users to navigate through a large collection of items. New items (products, videos, songs, advertisements) are suggested on the basis of the user's past history and --when available-- her demographic profile. Recommendations have to satisfy the dual goal of helping the user to explore the space of available items, while allowing the system to probe the user's preferences. We model this trade-off using linearly parametrized multi-armed bandits, propose a policy and prove upper and lower bounds on the cumulative \"reward\" that coincide up to constants in the data poor (high-dimensional) regime. Prior work on linear bandits has focused on the data rich (low-dimensional) regime and used cumulative \"risk\" as the figure of merit. For this data rich regime, we provide a simple modification for our policy that achieves near-optimal risk performance under more restrictive assumptions on the geometry of the problem. We test (a variation of) the scheme used for establishing achievability on the Netflix and MovieLens datasets and obtain good agreement with the qualitative predictions of the theory we develop.", "source": "arxiv/ml"}
{"id": "arxiv:2590", "title": "Risk-Aversion in Multi-armed Bandits", "text": "Stochastic multi-armed bandits solve the Exploration-Exploitation dilemma and ultimately maximize the expected reward. Nonetheless, in many practical problems, maximizing the expected reward is not the most desirable objective. In this paper, we introduce a novel setting based on the principle of risk-aversion where the objective is to compete against the arm with the best risk-return trade-off. This setting proves to be intrinsically more difficult than the standard multi-arm bandit setting due in part to an exploration risk which introduces a regret associated to the variability of an algorithm. Using variance as a measure of risk, we introduce two new algorithms, investigate their theoretical guarantees, and report preliminary empirical results.", "source": "arxiv/ml"}
{"id": "arxiv:2591", "title": "Bayesian Optimization in a Billion Dimensions via Random Embeddings", "text": "Bayesian optimization techniques have been successfully applied to robotics, planning, sensor placement, recommendation, advertising, intelligent user interfaces and automatic algorithm configuration. Despite these successes, the approach is restricted to problems of moderate dimension, and several workshops on Bayesian optimization have identified its scaling to high-dimensions as one of the holy grails of the field. In this paper, we introduce a novel random embedding idea to attack this problem. The resulting Random EMbedding Bayesian Optimization (REMBO) algorithm is very simple, has important invariance properties, and applies to domains with both categorical and continuous variables. We present a thorough theoretical analysis of REMBO. Empirical results confirm that REMBO can effectively solve problems with billions of dimensions, provided the intrinsic dimensionality is low. They also show that REMBO achieves state-of-the-art performance in optimizing the 47 discrete parameters of a popular mixed integer linear programming solver.", "source": "arxiv/ml"}
{"id": "arxiv:2592", "title": "Error Correction in Learning using SVMs", "text": "This paper is concerned with learning binary classifiers under adversarial label-noise. We introduce the problem of error-correction in learning where the goal is to recover the original clean data from a label-manipulated version of it, given (i) no constraints on the adversary other than an upper-bound on the number of errors, and (ii) some regularity properties for the original data. We present a simple and practical error-correction algorithm called SubSVMs that learns individual SVMs on several small-size (log-size), class-balanced, random subsets of the data and then reclassifies the training points using a majority vote. Our analysis reveals the need for the two main ingredients of SubSVMs, namely class-balanced sampling and subsampled bagging. Experimental results on synthetic as well as benchmark UCI data demonstrate the effectiveness of our approach. In addition to noise-tolerance, log-size subsampled bagging also yields significant run-time benefits over standard SVMs.", "source": "arxiv/ml"}
{"id": "arxiv:2593", "title": "Heteroscedastic Relevance Vector Machine", "text": "In this work we propose a heteroscedastic generalization to RVM, a fast Bayesian framework for regression, based on some recent similar works. We use variational approximation and expectation propagation to tackle the problem. The work is still under progress and we are examining the results and comparing with the previous works.", "source": "arxiv/ml"}
{"id": "arxiv:2594", "title": "Training Effective Node Classifiers for Cascade Classification", "text": "Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are a few reported methods addressing this requirement in the context of object detection, there is no principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such an algorithm here. We show that a special case of the biased minimax probability machine has the same formulation as the linear asymmetric classifier (LAC) of Wu et al (2005). We then design a new boosting algorithm that directly optimizes the cost function of LAC. The resulting totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on object detection verify the effectiveness of the proposed boosting algorithm as a node classifier in cascade object detection, and show performance better than that of the current state-of-the-art.", "source": "arxiv/ml"}
{"id": "arxiv:2595", "title": "Domain Generalization via Invariant Feature Representation", "text": "This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based optimization algorithm that learns an invariant transformation by minimizing the dissimilarity across domains, whilst preserving the functional relationship between input and output variables. A learning-theoretic analysis shows that reducing dissimilarity improves the expected generalization ability of classifiers on new domains, motivating the proposed algorithm. Experimental results on synthetic and real-world datasets demonstrate that DICA successfully learns invariant features and improves classifier performance in practice.", "source": "arxiv/ml"}
{"id": "arxiv:2596", "title": "Network-based clustering with mixtures of L1-penalized Gaussian graphical models: an empirical investigation", "text": "In many applications, multivariate samples may harbor previously unrecognized heterogeneity at the level of conditional independence or network structure. For example, in cancer biology, disease subtypes may differ with respect to subtype-specific interplay between molecular components. Then, both subtype discovery and estimation of subtype-specific networks present important and related challenges. To enable such analyses, we put forward a mixture model whose components are sparse Gaussian graphical models. This brings together model-based clustering and graphical modeling to permit simultaneous estimation of cluster assignments and cluster-specific networks. We carry out estimation within an L1-penalized framework, and investigate several specific penalization regimes. We present empirical results on simulated data and provide general recommendations for the formulation and use of mixtures of L1-penalized Gaussian graphical models.", "source": "arxiv/ml"}
{"id": "arxiv:2597", "title": "Conditions Under Which Conditional Independence and Scoring Methods Lead to Identical Selection of Bayesian Network Models", "text": "It is often stated in papers tackling the task of inferring Bayesian network structures from data that there are these two distinct approaches: (i) Apply conditional independence tests when testing for the presence or otherwise of edges; (ii) Search the model space using a scoring metric. Here I argue that for complete data and a given node ordering this division is a myth, by showing that cross entropy methods for checking conditional independence are mathematically identical to methods based upon discriminating between models by their overall goodness-of-fit logarithmic scores.", "source": "arxiv/ml"}
{"id": "arxiv:2598", "title": "Variational MCMC", "text": "We propose a new class of learning algorithms that combines variational approximation and Markov chain Monte Carlo (MCMC) simulation. Naive algorithms that use the variational approximation as proposal distribution can perform poorly because this approximation tends to underestimate the true variance and other features of the data. We solve this problem by introducing more sophisticated MCMC algorithms. One of these algorithms is a mixture of two MCMC kernels: a random walk Metropolis kernel and a blockMetropolis-Hastings (MH) kernel with a variational approximation as proposaldistribution. The MH kernel allows one to locate regions of high probability efficiently. The Metropolis kernel allows us to explore the vicinity of these regions. This algorithm outperforms variationalapproximations because it yields slightly better estimates of the mean and considerably better estimates of higher moments, such as covariances. It also outperforms standard MCMC algorithms because it locates theregions of high probability quickly, thus speeding up convergence. We demonstrate this algorithm on the problem of Bayesian parameter estimation for logistic (sigmoid) belief networks.", "source": "arxiv/ml"}
{"id": "arxiv:2599", "title": "Incorporating Expressive Graphical Models in Variational Approximations: Chain-Graphs and Hidden Variables", "text": "Global variational approximation methods in graphical models allow efficient approximate inference of complex posterior distributions by using a simpler model. The choice of the approximating model determines a tradeoff between the complexity of the approximation procedure and the quality of the approximation. In this paper, we consider variational approximations based on two classes of models that are richer than standard Bayesian networks, Markov networks or mixture models. As such, these classes allow to find better tradeoffs in the spectrum of approximations. The first class of models are chain graphs, which capture distributions that are partially directed. The second class of models are directed graphs (Bayesian networks) with additional latent variables. Both classes allow representation of multi-variable dependencies that cannot be easily represented within a Bayesian network.", "source": "arxiv/ml"}
{"id": "arxiv:2600", "title": "Learning the Dimensionality of Hidden Variables", "text": "A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. Detecting hidden variables poses two problems: determining the relations to other variables in the model and determining the number of states of the hidden variable. In this paper, we address the latter problem in the context of Bayesian networks. We describe an approach that utilizes a score-based agglomerative state-clustering. As we show, this approach allows us to efficiently evaluate models with a range of cardinalities for the hidden variable. We show how to extend this procedure to deal with multiple interacting hidden variables. We demonstrate the effectiveness of this approach by evaluating it on synthetic and real-life data. We show that our approach learns models with hidden variables that generalize better and have better structure than previous approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2601", "title": "Multivariate Information Bottleneck", "text": "The Information bottleneck method is an unsupervised non-parametric data organization technique. Given a joint distribution P(A,B), this method constructs a new variable T that extracts partitions, or clusters, over the values of A that are informative about B. The information bottleneck has already been applied to document classification, gene expression, neural code, and spectral analysis. In this paper, we introduce a general principled framework for multivariate extensions of the information bottleneck method. This allows us to consider multiple systems of data partitions that are inter-related. Our approach utilizes Bayesian networks for specifying the systems of clusters and what information each captures. We show that this construction provides insight about bottleneck variations and enables us to characterize solutions of these variations. We also present a general framework for iterative algorithms for constructing solutions, and apply it to several examples.", "source": "arxiv/ml"}
{"id": "arxiv:2602", "title": "Discovering Multiple Constraints that are Frequently Approximately Satisfied", "text": "Some high-dimensional data.sets can be modelled by assuming that there are many different linear constraints, each of which is Frequently Approximately Satisfied (FAS) by the data. The probability of a data vector under the model is then proportional to the product of the probabilities of its constraint violations. We describe three methods of learning products of constraints using a heavy-tailed probability distribution for the violations.", "source": "arxiv/ml"}
{"id": "arxiv:2603", "title": "Estimating Well-Performing Bayesian Networks using Bernoulli Mixtures", "text": "A novel method for estimating Bayesian network (BN) parameters from data is presented which provides improved performance on test data. Previous research has shown the value of representing conditional probability distributions (CPDs) via neural networks(Neal 1992), noisy-OR gates (Neal 1992, Diez 1993)and decision trees (Friedman and Goldszmidt 1996).The Bernoulli mixture network (BMN) explicitly represents the CPDs of discrete BN nodes as mixtures of local distributions,each having a different set of parents.This increases the space of possible structures which can be considered,enabling the CPDs to have finer-grained dependencies.The resulting estimation procedure induces a modelthat is better able to emulate the underlying interactions occurring in the data than conventional conditional Bernoulli network models.The results for artificially generated data indicate that overfitting is best reduced by restricting the complexity of candidate mixture substructures local to each node. Furthermore, mixtures of very simple substructures can perform almost as well as more complex ones.The BMN is also applied to data collected from an online adventure game with an application to keyhole plan recognition. The results show that the BMN-based model brings a dramatic improvement in performance over a conventional BN model.", "source": "arxiv/ml"}
{"id": "arxiv:2604", "title": "Improved learning of Bayesian networks", "text": "The search space of Bayesian Network structures is usually defined as Acyclic Directed Graphs (DAGs) and the search is done by local transformations of DAGs. But the space of Bayesian Networks is ordered by DAG Markov model inclusion and it is natural to consider that a good search policy should take this into account. First attempt to do this (Chickering 1996) was using equivalence classes of DAGs instead of DAGs itself. This approach produces better results but it is significantly slower. We present a compromise between these two approaches. It uses DAGs to search the space in such a way that the ordering by inclusion is taken into account. This is achieved by repetitive usage of local moves within the equivalence class of DAGs. We show that this new approach produces better results than the original DAGs approach without substantial change in time complexity. We present empirical results, within the framework of heuristic search and Markov Chain Monte Carlo, provided through the Alarm dataset.", "source": "arxiv/ml"}
{"id": "arxiv:2605", "title": "Classifier Learning with Supervised Marginal Likelihood", "text": "It has been argued that in supervised classification tasks, in practice it may be more sensible to perform model selection with respect to some more focused model selection score, like the supervised (conditional) marginal likelihood, than with respect to the standard marginal likelihood criterion. However, for most Bayesian network models, computing the supervised marginal likelihood score takes exponential time with respect to the amount of observed data. In this paper, we consider diagnostic Bayesian network classifiers where the significant model parameters represent conditional distributions for the class variable, given the values of the predictor variables, in which case the supervised marginal likelihood can be computed in linear time with respect to the data. As the number of model parameters grows in this case exponentially with respect to the number of predictors, we focus on simple diagnostic models where the number of relevant predictors is small, and suggest two approaches for applying this type of models in classification. The first approach is based on mixtures of simple diagnostic models, while in the second approach we apply the small predictor sets of the simple diagnostic models for augmenting the Naive Bayes classifier.", "source": "arxiv/ml"}
{"id": "arxiv:2606", "title": "Iterative Markov Chain Monte Carlo Computation of Reference Priors and Minimax Risk", "text": "We present an iterative Markov chainMonte Carlo algorithm for computingreference priors and minimax risk forgeneral parametric families. Ourapproach uses MCMC techniques based onthe Blahut-Arimoto algorithm forcomputing channel capacity ininformation theory. We give astatistical analysis of the algorithm,bounding the number of samples requiredfor the stochastic algorithm to closelyapproximate the deterministic algorithmin each iteration. Simulations arepresented for several examples fromexponential families. Although we focuson applications to reference priors andminimax risk, the methods and analysiswe develop are applicable to a muchbroader class of optimization problemsand iterative algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2607", "title": "A Bayesian Multiresolution Independence Test for Continuous Variables", "text": "In this paper we present a method ofcomputing the posterior probability ofconditional independence of two or morecontinuous variables from data,examined at several resolutions. Ourapproach is motivated by theobservation that the appearance ofcontinuous data varies widely atvarious resolutions, producing verydifferent independence estimatesbetween the variablesinvolved. Therefore, it is difficultto ascertain independence withoutexamining data at several carefullyselected resolutions. In our paper, weaccomplish this using the exactcomputation of the posteriorprobability of independence, calculatedanalytically given a resolution. Ateach examined resolution, we assume amultinomial distribution with Dirichletpriors for the discretized tableparameters, and compute the posteriorusing Bayesian integration. Acrossresolutions, we use a search procedureto approximate the Bayesian integral ofprobability over an exponential numberof possible histograms. Our methodgeneralizes to an arbitrary numbervariables in a straightforward manner.The test is suitable for Bayesiannetwork learning algorithms that useindependence tests to infer the networkstructure, in domains that contain anymix of continuous, ordinal andcategorical variables.", "source": "arxiv/ml"}
{"id": "arxiv:2608", "title": "Expectation Propagation for approximate Bayesian inference", "text": "This paper presents a new deterministic approximation technique in Bayesian networks. This method, \"Expectation Propagation\", unifies two previous techniques: assumed-density filtering, an extension of the Kalman filter, and loopy belief propagation, an extension of belief propagation in Bayesian networks. All three algorithms try to recover an approximate distribution which is close in KL divergence to the true distribution. Loopy belief propagation, because it propagates exact belief states, is useful for a limited class of belief networks, such as those which are purely discrete. Expectation Propagation approximates the belief states by only retaining certain expectations, such as mean and variance, and iterates until these expectations are consistent throughout the network. This makes it applicable to hybrid networks with discrete and continuous nodes. Expectation Propagation also extends belief propagation in the opposite direction - it can propagate richer belief states that incorporate correlations between nodes. Experiments with Gaussian mixture models show Expectation Propagation to be convincingly better than methods with similar computational cost: Laplace's method, variational Bayes, and Monte Carlo. Expectation Propagation also provides an efficient algorithm for training Bayes point machine classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:2609", "title": "Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments", "text": "Recommender systems leverage product and community information to target products to consumers. Researchers have developed collaborative recommenders, content-based recommenders, and (largely ad-hoc) hybrid systems. We propose a unified probabilistic framework for merging collaborative and content-based recommendations. We extend Hofmann's [1999] aspect model to incorporate three-way co-occurrence data among users, items, and item content. The relative influence of collaboration data versus content data is not imposed as an exogenous parameter, but rather emerges naturally from the given data sources. Global probabilistic models coupled with standard Expectation Maximization (EM) learning algorithms tend to drastically overfit in sparse-data situations, as is typical in recommendation applications. We show that secondary content information can often be used to overcome sparsity. Experiments on data from the ResearchIndex library of Computer Science publications show that appropriate mixture models incorporating secondary data produce significantly better quality recommenders than k-nearest neighbors (k-NN). Global probabilistic models also allow more general inferences than local methods like k-NN.", "source": "arxiv/ml"}
{"id": "arxiv:2610", "title": "Symmetric Collaborative Filtering Using the Noisy Sensor Model", "text": "Collaborative filtering is the process of making recommendations regarding the potential preference of a user, for example shopping on the Internet, based on the preference ratings of the user and a number of other users for various items. This paper considers collaborative filtering based on explicitmulti-valued ratings. To evaluate the algorithms, weconsider only {em pure} collaborative filtering, using ratings exclusively, and no other information about the people or items.Our approach is to predict a user's preferences regarding a particularitem by using other people who rated that item and other items ratedby the user as noisy sensors. The noisy sensor model uses Bayes' theorem to compute the probability distribution for the user'srating of a new item. We give two variant models: in one, we learn a{em classical normal linear regression} model of how users rate items; in another,we assume different users rate items the same, but the accuracy of thesensors needs to be learned. We compare these variant models withstate-of-the-art techniques and show how they are significantly better,whether a user has rated only two items or many. We reportempirical results using the EachMovie database footnote{http://research.compaq.com/SRC/eachmovie/} of movie ratings. Wealso show that by considering items similarity along with theusers similarity, the accuracy of the prediction increases.", "source": "arxiv/ml"}
{"id": "arxiv:2611", "title": "Policy Improvement for POMDPs Using Normalized Importance Sampling", "text": "We present a new method for estimating the expected return of a POMDP from experience. The method does not assume any knowledge of the POMDP and allows the experience to be gathered from an arbitrary sequence of policies. The return is estimated for any new policy of the POMDP. We motivate the estimator from function-approximation and importance sampling points-of-view and derive its theoretical properties. Although the estimator is biased, it has low variance and the bias is often irrelevant when the estimator is used for pair-wise comparisons. We conclude by extending the estimator to policies with memory and compare its performance in a greedy search algorithm to REINFORCE algorithms showing an order of magnitude reduction in the number of trials required.", "source": "arxiv/ml"}
{"id": "arxiv:2612", "title": "Maximum Likelihood Bounded Tree-Width Markov Networks", "text": "Chow and Liu (1968) studied the problem of learning a maximumlikelihood Markov tree. We generalize their work to more complexMarkov networks by considering the problem of learning a maximumlikelihood Markov network of bounded complexity. We discuss howtree-width is in many ways the appropriate measure of complexity andthus analyze the problem of learning a maximum likelihood Markovnetwork of bounded tree-width.Similar to the work of Chow and Liu, we are able to formalize thelearning problem as a combinatorial optimization problem on graphs. Weshow that learning a maximum likelihood Markov network of boundedtree-width is equivalent to finding a maximum weight hypertree. Thisequivalence gives rise to global, integer-programming based,approximation algorithms with provable performance guarantees, for thelearning problem. This contrasts with heuristic local-searchalgorithms which were previously suggested (e.g. by Malvestuto 1991).The equivalence also allows us to study the computational hardness ofthe learning problem. We show that learning a maximum likelihoodMarkov network of bounded tree-width is NP-hard, and discuss thehardness of approximation.", "source": "arxiv/ml"}
{"id": "arxiv:2613", "title": "The Optimal Reward Baseline for Gradient-Based Reinforcement Learning", "text": "There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model. However, the variance of the gradient estimator hasbeen found to be a significant practical problem. Recent approacheshave discounted future rewards, introducing a bias-variance trade-offinto the gradient estimate. We incorporate a reward baseline into thelearning system, and show that it affects variance without introducingfurther bias. In particular, as we approach the zero-bias,high-variance parameterization, the optimal (or variance minimizing)constant reward baseline is equal to the long-term average expectedreward. Modified policy-gradient algorithms are presented, and anumber of experiments demonstrate their improvement over previous work.", "source": "arxiv/ml"}
{"id": "arxiv:2614", "title": "Cross-covariance modelling via DAGs with hidden variables", "text": "DAG models with hidden variables present many difficulties that are not present when all nodes are observed. In particular, fully observed DAG models are identified and correspond to well-defined sets ofdistributions, whereas this is not true if nodes are unobserved. Inthis paper we characterize exactly the set of distributions given by a class of one-dimensional Gaussian latent variable models. These models relate two blocks of observed variables, modeling only the cross-covariance matrix. We describe the relation of this model to the singular value decomposition of the cross-covariance matrix. We show that, although the model is underidentified, useful information may be extracted. We further consider an alternative parametrization in which one latent variable is associated with each block. Our analysis leads to some novel covariance equivalence results for Gaussian hidden variable models.", "source": "arxiv/ml"}
{"id": "arxiv:2615", "title": "Belief Optimization for Binary Networks: A Stable Alternative to Loopy Belief Propagation", "text": "We present a novel inference algorithm for arbitrary, binary, undirected graphs. Unlike loopy belief propagation, which iterates fixed point equations, we directly descend on the Bethe free energy. The algorithm consists of two phases, first we update the pairwise probabilities, given the marginal probabilities at each unit,using an analytic expression. Next, we update the marginal probabilities, given the pairwise probabilities by following the negative gradient of the Bethe free energy. Both steps are guaranteed to decrease the Bethe free energy, and since it is lower bounded, the algorithm is guaranteed to converge to a local minimum. We also show that the Bethe free energy is equal to the TAP free energy up to second order in the weights. In experiments we confirm that when belief propagation converges it usually finds identical solutions as our belief optimization method. However, in cases where belief propagation fails to converge, belief optimization continues to converge to reasonable beliefs. The stable nature of belief optimization makes it ideally suited for learning graphical models from data.", "source": "arxiv/ml"}
{"id": "arxiv:2616", "title": "Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)", "text": "Automatic continuous speech recognition (CSR) is sufficiently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues. This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specifically hidden Markov models (HMMs) and N-grams. Starting from a description of the speech signal and its parameterisation, the various modelling assumptions and their consequences are discussed. It then describes various techniques by which the effects of these assumptions can be mitigated. Despite the progress that has been made, the limitations of current modelling techniques are still evident. The paper therefore concludes with a brief review of some of the more fundamental modelling work now in progress.", "source": "arxiv/ml"}
{"id": "arxiv:2617", "title": "Using Temporal Data for Making Recommendations", "text": "We treat collaborative filtering as a univariate time series estimation problem: given a user's previous votes, predict the next vote. We describe two families of methods for transforming data to encode time order in ways amenable to off-the-shelf classification and density estimation tools, and examine the results of using these approaches on several real-world data sets. The improvements in predictive accuracy we realize recommend the use of other predictive algorithms that exploit the temporal order of data.", "source": "arxiv/ml"}
{"id": "arxiv:2618", "title": "Planning by Prioritized Sweeping with Small Backups", "text": "Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibit much finer control over their planning process than traditional methods. We empirically demonstrate that this increased flexibility allows for more efficient planning by showing that an implementation of prioritized sweeping based on small backups achieves a substantial performance improvement over classical implementations.", "source": "arxiv/ml"}
{"id": "arxiv:2619", "title": "Robust subspace clustering", "text": "Subspace clustering refers to the task of finding a multi-subspace representation that best fits a collection of points taken from a high-dimensional space. This paper introduces an algorithm inspired by sparse subspace clustering (SSC) [In IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2009) 2790-2797] to cluster noisy data, and develops some novel theory demonstrating its correctness. In particular, the theory uses ideas from geometric functional analysis to show that the algorithm can accurately recover the underlying subspaces under minimal requirements on their orientation, and on the number of samples per subspace. Synthetic as well as real data experiments complement our theoretical study, illustrating our approach and demonstrating its effectiveness.", "source": "arxiv/ml"}
{"id": "arxiv:2620", "title": "Learning to Optimize Via Posterior Sampling", "text": "This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling, offers significant advantages over the popular upper confidence bound (UCB) approach, and can be applied to problems with finite or infinite action spaces and complicated relationships among action rewards. We make two theoretical contributions. The first establishes a connection between posterior sampling and UCB algorithms. This result lets us convert regret bounds developed for UCB algorithms into Bayesian regret bounds for posterior sampling. Our second theoretical contribution is a Bayesian regret bound for posterior sampling that applies broadly and can be specialized to many model classes. This bound depends on a new notion we refer to as the eluder dimension, which measures the degree of dependence among action rewards. Compared to UCB algorithm Bayesian regret bounds for specific model classes, our general bound matches the best available for linear models and is stronger than the best available for generalized linear models. Further, our analysis provides insight into performance advantages of posterior sampling, which are highlighted through simulation results that demonstrate performance surpassing recently proposed UCB algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2621", "title": "Robust Text Detection in Natural Scene Images", "text": "Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks. In this paper, we propose an accurate and robust method for detecting texts in natural scene images. A fast and effective pruning algorithm is designed to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations. Character candidates are grouped into text candidates by the ingle-link clustering algorithm, where distance weights and threshold of the clustering algorithm are learned automatically by a novel self-training distance metric learning algorithm. The posterior probabilities of text candidates corresponding to non-text are estimated with an character classifier; text candidates with high probabilities are then eliminated and finally texts are identified with a text classifier. The proposed system is evaluated on the ICDAR 2011 Robust Reading Competition dataset; the f measure is over 76% and is significantly better than the state-of-the-art performance of 71%. Experimental results on a publicly available multilingual dataset also show that our proposed method can outperform the other competitive method with the f measure increase of over 9 percent. Finally, we have setup an online demo of our proposed scene text detection system at http://kems.ustb.edu.cn/learning/yin/dtext.", "source": "arxiv/ml"}
{"id": "arxiv:2622", "title": "Functional Regularized Least Squares Classi cation with Operator-valued Kernels", "text": "Although operator-valued kernels have recently received increasing interest in various machine learning and functional data analysis problems such as multi-task learning or functional regression, little attention has been paid to the understanding of their associated feature spaces. In this paper, we explore the potential of adopting an operator-valued kernel feature space perspective for the analysis of functional data. We then extend the Regularized Least Squares Classification (RLSC) algorithm to cover situations where there are multiple functions per observation. Experiments on a sound recognition problem show that the proposed method outperforms the classical RLSC algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2623", "title": "Multiple functional regression with both discrete and continuous covariates", "text": "In this paper we present a nonparametric method for extending functional regression methodology to the situation where more than one functional covariate is used to predict a functional response. Borrowing the idea from Kadri et al. (2010a), the method, which support mixed discrete and continuous explanatory variables, is based on estimating a function-valued function in reproducing kernel Hilbert spaces by virtue of positive operator-valued kernels.", "source": "arxiv/ml"}
{"id": "arxiv:2624", "title": "A Triclustering Approach for Time Evolving Graphs", "text": "This paper introduces a novel technique to track structures in time evolving graphs. The method is based on a parameter free approach for three-dimensional co-clustering of the source vertices, the target vertices and the time. All these features are simultaneously segmented in order to build time segments and clusters of vertices whose edge distributions are similar and evolve in the same way over the time segments. The main novelty of this approach lies in that the time segments are directly inferred from the evolution of the edge distribution between the vertices, thus not requiring the user to make an a priori discretization. Experiments conducted on a synthetic dataset illustrate the good behaviour of the technique, and a study of a real-life dataset shows the potential of the proposed approach for exploratory data analysis.", "source": "arxiv/ml"}
{"id": "arxiv:2625", "title": "BliStr: The Blind Strategymaker", "text": "BliStr is a system that automatically develops strategies for E prover on a large set of problems. The main idea is to interleave (i) iterated low-timelimit local search for new strategies on small sets of similar easy problems with (ii) higher-timelimit evaluation of the new strategies on all problems. The accumulated results of the global higher-timelimit runs are used to define and evolve the notion of \"similar easy problems\", and to control the selection of the next strategy to be improved. The technique was used to significantly strengthen the set of E strategies used by the MaLARea, PS-E, E-MaLeS, and E systems in the CASC@Turing 2012 competition, particularly in the Mizar division. Similar improvement was obtained on the problems created from the Flyspeck corpus.", "source": "arxiv/ml"}
{"id": "arxiv:2626", "title": "Robust High Dimensional Sparse Regression and Matching Pursuit", "text": "We consider high dimensional sparse regression, and develop strategies able to deal with arbitrary -- possibly, severe or coordinated -- errors in the covariance matrix $X$. These may come from corrupted data, persistent experimental errors, or malicious respondents in surveys/recommender systems, etc. Such non-stochastic error-in-variables problems are notoriously difficult to treat, and as we demonstrate, the problem is particularly pronounced in high-dimensional settings where the primary goal is {\\em support recovery} of the sparse regressor. We develop algorithms for support recovery in sparse regression, when some number $n_1$ out of $n+n_1$ total covariate/response pairs are {\\it arbitrarily (possibly maliciously) corrupted}. We are interested in understanding how many outliers, $n_1$, we can tolerate, while identifying the correct support. To the best of our knowledge, neither standard outlier rejection techniques, nor recently developed robust regression algorithms (that focus only on corrupted response variables), nor recent algorithms for dealing with stochastic noise or erasures, can provide guarantees on support recovery. Perhaps surprisingly, we also show that the natural brute force algorithm that searches over all subsets of $n$ covariate/response pairs, and all subsets of possible support coordinates in order to minimize regression error, is remarkably poor, unable to correctly identify the support with even $n_1 = O(n/k)$ corrupted points, where $k$ is the sparsity. This is true even in the basic setting we consider, where all authentic measurements and noise are independent and sub-Gaussian. In this setting, we provide a simple algorithm -- no more computationally taxing than OMP -- that gives stronger performance guarantees, recovering the support with up to $n_1 = O(n/(\\sqrt{k} \\log p))$ corrupted points, where $p$ is the dimension of the signal to be recovered.", "source": "arxiv/ml"}
{"id": "arxiv:2627", "title": "A comparison of SVM and RVM for Document Classification", "text": "Document classification is a task of assigning a new unclassified document to one of the predefined set of classes. The content based document classification uses the content of the document with some weighting criteria to assign it to one of the predefined classes. It is a major task in library science, electronic document management systems and information sciences. This paper investigates document classification by using two different classification techniques (1) Support Vector Machine (SVM) and (2) Relevance Vector Machine (RVM). SVM is a supervised machine learning technique that can be used for classification task. In its basic form, SVM represents the instances of the data into space and tries to separate the distinct classes by a maximum possible wide gap (hyper plane) that separates the classes. On the other hand RVM uses probabilistic measure to define this separation space. RVM uses Bayesian inference to obtain succinct solution, thus RVM uses significantly fewer basis functions. Experimental studies on three standard text classification datasets reveal that although RVM takes more training time, its classification is much better as compared to SVM.", "source": "arxiv/ml"}
{"id": "arxiv:2628", "title": "Unsupervised Feature Learning for low-level Local Image Descriptors", "text": "Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision. Using a large amount of unlabeled data, unsupervised feature learning methods are utilized to construct high-level representations that are discriminative enough for subsequently trained supervised classification algorithms. However, it has never been \\emph{quantitatively} investigated yet how well unsupervised learning methods can find \\emph{low-level representations} for image patches without any additional supervision. In this paper we examine the performance of pure unsupervised methods on a low-level correspondence task, a problem that is central to many Computer Vision applications. We find that a special type of Restricted Boltzmann Machines (RBMs) performs comparably to hand-crafted descriptors. Additionally, a simple binarization scheme produces compact representations that perform better than several state-of-the-art descriptors.", "source": "arxiv/ml"}
{"id": "arxiv:2629", "title": "Matrix Approximation under Local Low-Rank Assumption", "text": "Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the partially observed matrix is of low-rank. We propose a new matrix approximation model where we assume instead that the matrix is only locally of low-rank, leading to a representation of the observed matrix as a weighted sum of low-rank matrices. We analyze the accuracy of the proposed local low-rank modeling. Our experiments show improvements in prediction accuracy in recommendation tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2630", "title": "Learning Graphical Model Parameters with Approximate Marginal Inference", "text": "Likelihood based-learning of graphical models faces challenges of computational-complexity and robustness to model mis-specification. This paper studies methods that fit parameters directly to maximize a measure of the accuracy of predicted marginals, taking into account both model and inference approximations at training time. Experiments on imaging problems suggest marginalization-based learning performs better than likelihood-based approximations on difficult problems where the model being fit is approximate in nature.", "source": "arxiv/ml"}
{"id": "arxiv:2631", "title": "Efficient Learning of Domain-invariant Image Representations", "text": "We present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the target (test) domain to the source (training) domain as part of training the classifier. We optimize both the transformation and classifier parameters jointly, and introduce an efficient cost function based on misclassification loss. Our method combines several features previously unavailable in a single algorithm: multi-class adaptation through representation learning, ability to map across heterogeneous feature spaces, and scalability to large datasets. We present experiments on several image datasets that demonstrate improved accuracy and computational advantages compared to previous approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2632", "title": "The Expressive Power of Word Embeddings", "text": "We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nuanced semantics even in the absence of sentence structure. Moreover, benchmarking the embeddings shows great variance in quality and characteristics of the semantics captured by the tested embeddings. Finally, we show the impact of varying the number of dimensions and the resolution of each dimension on the effective useful features captured by the embedding space. Our contributions highlight the importance of embeddings for NLP tasks and the effect of their quality on the final results.", "source": "arxiv/ml"}
{"id": "arxiv:2633", "title": "Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences", "text": "Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we propose a novel pooling method that can learn soft clustering of features from image sequences. It is trained to improve the temporal coherence of features, while keeping the information loss at minimum. Our method does not use spatial information, so it can be used with non-convolutional models too. Experiments on images extracted from natural videos showed that our method can cluster similar features together. When trained by convolutional features, auto-pooling outperformed traditional spatial pooling on an image classification task, even though it does not use the spatial topology of features.", "source": "arxiv/ml"}
{"id": "arxiv:2634", "title": "Barnes-Hut-SNE", "text": "The paper presents an O(N log N)-implementation of t-SNE -- an embedding technique that is commonly used for the visualization of high-dimensional data in scatter plots and that normally runs in O(N^2). The new implementation uses vantage-point trees to compute sparse pairwise similarities between the input data objects, and it uses a variant of the Barnes-Hut algorithm - an algorithm used by astronomers to perform N-body simulations - to approximate the forces between the corresponding points in the embedding. Our experiments show that the new algorithm, called Barnes-Hut-SNE, leads to substantial computational advantages over standard t-SNE, and that it makes it possible to learn embeddings of data sets with millions of objects.", "source": "arxiv/ml"}
{"id": "arxiv:2635", "title": "Multi-agent learning using Fictitious Play and Extended Kalman Filter", "text": "Decentralised optimisation tasks are important components of multi-agent systems. These tasks can be interpreted as n-player potential games: therefore game-theoretic learning algorithms can be used to solve decentralised optimisation tasks. Fictitious play is the canonical example of these algorithms. Nevertheless fictitious play implicitly assumes that players have stationary strategies. We present a novel variant of fictitious play where players predict their opponents' strategies using Extended Kalman filters and use their predictions to update their strategies. We show that in 2 by 2 games with at least one pure Nash equilibrium and in potential games where players have two available actions, the proposed algorithm converges to the pure Nash equilibrium. The performance of the proposed algorithm was empirically tested, in two strategic form games and an ad-hoc sensor network surveillance problem. The proposed algorithm performs better than the classic fictitious play algorithm in these games and therefore improves the performance of game-theoretical learning in decentralised optimisation.", "source": "arxiv/ml"}
{"id": "arxiv:2636", "title": "The Diagonalized Newton Algorithm for Nonnegative Matrix Factorization", "text": "Non-negative matrix factorization (NMF) has become a popular machine learning approach to many problems in text mining, speech and image processing, bio-informatics and seismic data analysis to name a few. In NMF, a matrix of non-negative data is approximated by the low-rank product of two matrices with non-negative entries. In this paper, the approximation quality is measured by the Kullback-Leibler divergence between the data and its low-rank reconstruction. The existence of the simple multiplicative update (MU) algorithm for computing the matrix factors has contributed to the success of NMF. Despite the availability of algorithms showing faster convergence, MU remains popular due to its simplicity. In this paper, a diagonalized Newton algorithm (DNA) is proposed showing faster convergence while the implementation remains simple and suitable for high-rank problems. The DNA algorithm is applied to various publicly available data sets, showing a substantial speed-up on modern hardware.", "source": "arxiv/ml"}
{"id": "arxiv:2637", "title": "Feature grouping from spatially constrained multiplicative interaction", "text": "We present a feature learning model that learns to encode relationships between images. The model is defined as a Gated Boltzmann Machine, which is constrained such that hidden units that are nearby in space can gate each other's connections. We show how frequency/orientation \"columns\" as well as topographic filter maps follow naturally from training the model on image pairs. The model also helps explain why square-pooling models yield feature groups with similar grouping properties. Experimental results on synthetic image transformations show that spatially constrained gating is an effective way to reduce the number of parameters and thereby to regularize a transformation-learning model.", "source": "arxiv/ml"}
{"id": "arxiv:2638", "title": "Factorized Topic Models", "text": "In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data. The structured parameterization separately encodes variance that is shared between classes from variance that is private to each class by the introduction of a new prior over the topic space. The approach allows for a more eff{}icient inference and provides an intuitive interpretation of the data in terms of an informative signal together with structured noise. The factorized representation is shown to enhance inference performance for image, text, and video classification.", "source": "arxiv/ml"}
{"id": "arxiv:2639", "title": "Boltzmann Machines and Denoising Autoencoders for Image Denoising", "text": "Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.", "source": "arxiv/ml"}
{"id": "arxiv:2640", "title": "Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities", "text": "Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We continue the work by firstly introducing a third transformation to normalize the scale of the outputs of each hidden neuron, and secondly by analyzing the connections to second order optimization methods. We show that the transformations make a simple stochastic gradient behave closer to second-order optimization methods and thus speed up learning. This is shown both in theory and with experiments. The experiments on the third transformation show that while it further increases the speed of learning, it can also hurt performance by converging to a worse local optimum, where both the inputs and outputs of many hidden neurons are close to zero.", "source": "arxiv/ml"}
{"id": "arxiv:2641", "title": "A Semantic Matching Energy Function for Learning with Multi-relational Data", "text": "Large-scale relational learning becomes crucial for handling the huge amounts of structured data generated daily in many application domains ranging from computational biology or information retrieval, to natural language processing. In this paper, we present a new neural network architecture designed to embed multi-relational graphs into a flexible continuous vector space in which the original data is kept and enhanced. The network is trained to encode the semantics of these graphs in order to assign high probabilities to plausible components. We empirically show that it reaches competitive performance in link prediction on standard datasets from the literature.", "source": "arxiv/ml"}
{"id": "arxiv:2642", "title": "Learnable Pooling Regions for Image Classification", "text": "Biologically inspired, from the early HMAX model to Spatial Pyramid Matching, pooling has played an important role in visual recognition pipelines. Spatial pooling, by grouping of local codes, equips these methods with a certain degree of robustness to translation and deformation yet preserving important spatial information. Despite the predominance of this approach in current recognition systems, we have seen little progress to fully adapt the pooling strategy to the task at hand. This paper proposes a model for learning task dependent pooling scheme -- including previously proposed hand-crafted pooling schemes as a particular instantiation. In our work, we investigate the role of different regularization terms showing that the smooth regularization term is crucial to achieve strong performance using the presented architecture. Finally, we propose an efficient and parallel method to train the model. Our experiments show improved performance over hand-crafted pooling schemes on the CIFAR-10 and CIFAR-100 datasets -- in particular improving the state-of-the-art to 56.29% on the latter.", "source": "arxiv/ml"}
{"id": "arxiv:2643", "title": "How good is the Electricity benchmark for evaluating concept drift adaptation", "text": "In this correspondence, we will point out a problem with testing adaptive classifiers on autocorrelated data. In such a case random change alarms may boost the accuracy figures. Hence, we cannot be sure if the adaptation is working well.", "source": "arxiv/ml"}
{"id": "arxiv:2644", "title": "Block Coordinate Descent for Sparse NMF", "text": "Nonnegative matrix factorization (NMF) has become a ubiquitous tool for data analysis. An important variant is the sparse NMF problem which arises when we explicitly require the learnt features to be sparse. A natural measure of sparsity is the L$_0$ norm, however its optimization is NP-hard. Mixed norms, such as L$_1$/L$_2$ measure, have been shown to model sparsity robustly, based on intuitive attributes that such measures need to satisfy. This is in contrast to computationally cheaper alternatives such as the plain L$_1$ norm. However, present algorithms designed for optimizing the mixed norm L$_1$/L$_2$ are slow and other formulations for sparse NMF have been proposed such as those based on L$_1$ and L$_0$ norms. Our proposed algorithm allows us to solve the mixed norm sparsity constraints while not sacrificing computation time. We present experimental evidence on real-world datasets that shows our new algorithm performs an order of magnitude faster compared to the current state-of-the-art solvers optimizing the mixed norm and is suitable for large-scale datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2645", "title": "An Efficient Sufficient Dimension Reduction Method for Identifying Genetic Variants of Clinical Significance", "text": "Fast and cheaper next generation sequencing technologies will generate unprecedentedly massive and highly-dimensional genomic and epigenomic variation data. In the near future, a routine part of medical record will include the sequenced genomes. A fundamental question is how to efficiently extract genomic and epigenomic variants of clinical utility which will provide information for optimal wellness and interference strategies. Traditional paradigm for identifying variants of clinical validity is to test association of the variants. However, significantly associated genetic variants may or may not be usefulness for diagnosis and prognosis of diseases. Alternative to association studies for finding genetic variants of predictive utility is to systematically search variants that contain sufficient information for phenotype prediction. To achieve this, we introduce concepts of sufficient dimension reduction and coordinate hypothesis which project the original high dimensional data to very low dimensional space while preserving all information on response phenotypes. We then formulate clinically significant genetic variant discovery problem into sparse SDR problem and develop algorithms that can select significant genetic variants from up to or even ten millions of predictors with the aid of dividing SDR for whole genome into a number of subSDR problems defined for genomic regions. The sparse SDR is in turn formulated as sparse optimal scoring problem, but with penalty which can remove row vectors from the basis matrix. To speed up computation, we develop the modified alternating direction method for multipliers to solve the sparse optimal scoring problem which can easily be implemented in parallel. To illustrate its application, the proposed method is applied to simulation data and the NHLBI's Exome Sequencing Project dataset", "source": "arxiv/ml"}
{"id": "arxiv:2646", "title": "The Neural Representation Benchmark and its Evaluation on Brain and Machine", "text": "A key requirement for the development of effective learning representations is their evaluation and comparison to representations we know to be effective. In natural sensory domains, the community has viewed the brain as a source of inspiration and as an implicit benchmark for success. However, it has not been possible to directly test representational learning algorithms directly against the representations contained in neural systems. Here, we propose a new benchmark for visual representations on which we have directly tested the neural representation in multiple visual cortical areas in macaque (utilizing data from [Majaj et al., 2012]), and on which any computer vision algorithm that produces a feature space can be tested. The benchmark measures the effectiveness of the neural or machine representation by computing the classification loss on the ordered eigendecomposition of a kernel matrix [Montavon et al., 2011]. In our analysis we find that the neural representation in visual area IT is superior to visual area V4. In our analysis of representational learning algorithms, we find that three-layer models approach the representational performance of V4 and the algorithm in [Le et al., 2012] surpasses the performance of V4. Impressively, we find that a recent supervised algorithm [Krizhevsky et al., 2012] achieves performance comparable to that of IT for an intermediate level of image variation difficulty, and surpasses IT at a higher difficulty level. We believe this result represents a major milestone: it is the first learning algorithm we have found that exceeds our current estimate of IT representation performance. We hope that this benchmark will assist the community in matching the representational performance of visual cortex and will serve as an initial rallying point for further correspondence between representations derived in brains and machines.", "source": "arxiv/ml"}
{"id": "arxiv:2647", "title": "Sparse Penalty in Deep Belief Networks: Using the Mixed Norm Constraint", "text": "Deep Belief Networks (DBN) have been successfully applied on popular machine learning tasks. Specifically, when applied on hand-written digit recognition, DBNs have achieved approximate accuracy rates of 98.8%. In an effort to optimize the data representation achieved by the DBN and maximize their descriptive power, recent advances have focused on inducing sparse constraints at each layer of the DBN. In this paper we present a theoretical approach for sparse constraints in the DBN using the mixed norm for both non-overlapping and overlapping groups. We explore how these constraints affect the classification accuracy for digit recognition in three different datasets (MNIST, USPS, RIMES) and provide initial estimations of their usefulness by altering different parameters such as the group size and overlap percentage.", "source": "arxiv/ml"}
{"id": "arxiv:2648", "title": "Learning Features with Structure-Adapting Multi-view Exponential Family Harmoniums", "text": "We proposea graphical model for multi-view feature extraction that automatically adapts its structure to achieve better representation of data distribution. The proposed model, structure-adapting multi-view harmonium (SA-MVH) has switch parameters that control the connection between hidden nodes and input views, and learn the switch parameter while training. Numerical experiments on synthetic and a real-world dataset demonstrate the useful behavior of the SA-MVH, compared to existing multi-view feature extraction methods.", "source": "arxiv/ml"}
{"id": "arxiv:2649", "title": "Deep Predictive Coding Networks", "text": "The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this issue, we propose deep predictive coding networks, a hierarchical generative model that empirically alters priors on the latent representations in a dynamic and context-sensitive manner. This model captures the temporal dependencies in time-varying signals and uses top-down information to modulate the representation in lower layers. The centerpiece of our model is a novel procedure to infer sparse states of a dynamic model which is used for feature extraction. We also extend this feature extraction block to introduce a pooling function that captures locally invariant representations. When applied on a natural video data, we show that our method is able to learn high-level visual features. We also demonstrate the role of the top-down connections by showing the robustness of the proposed model to structured noise.", "source": "arxiv/ml"}
{"id": "arxiv:2650", "title": "Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines", "text": "This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm belongs to the family of truncated Newton methods and exploits an efficient matrix-vector product to avoid explicitely storing the natural gradient metric $L$. This metric is shown to be the expected second derivative of the log-partition function (under the model distribution), or equivalently, the variance of the vector of partial derivatives of the energy function. We evaluate our method on the task of joint-training a 3-layer Deep Boltzmann Machine and show that MFNG does indeed have faster per-epoch convergence compared to Stochastic Maximum Likelihood with centering, though wall-clock performance is currently not competitive.", "source": "arxiv/ml"}
{"id": "arxiv:2651", "title": "Information Theoretic Learning with Infinitely Divisible Kernels", "text": "In this paper, we develop a framework for information theoretic learning based on infinitely divisible matrices. We formulate an entropy-like functional on positive definite matrices based on Renyi's axiomatic definition of entropy and examine some key properties of this functional that lead to the concept of infinite divisibility. The proposed formulation avoids the plug in estimation of density and brings along the representation power of reproducing kernel Hilbert spaces. As an application example, we derive a supervised metric learning algorithm using a matrix based analogue to conditional entropy achieving results comparable with the state of the art.", "source": "arxiv/ml"}
{"id": "arxiv:2652", "title": "Stochastic Pooling for Regularization of Deep Convolutional Neural Networks", "text": "We introduce a simple and effective method for regularizing large convolutional neural networks. We replace the conventional deterministic pooling operations with a stochastic procedure, randomly picking the activation within each pooling region according to a multinomial distribution, given by the activities within the pooling region. The approach is hyper-parameter free and can be combined with other regularization approaches, such as dropout and data augmentation. We achieve state-of-the-art performance on four image datasets, relative to other approaches that do not utilize data augmentation.", "source": "arxiv/ml"}
{"id": "arxiv:2653", "title": "Joint Training Deep Boltzmann Machines for Classification", "text": "We introduce a new method for training deep Boltzmann machines jointly. Prior methods of training DBMs require an initial learning pass that trains the model greedily, one layer at a time, or do not perform well on classification tasks. In our approach, we train all layers of the DBM simultaneously, using a novel training procedure called multi-prediction training. The resulting model can either be interpreted as a single generative model trained to maximize a variational approximation to the generalized pseudolikelihood, or as a family of recurrent networks that share parameters and may be approximately averaged together using a novel technique we call the multi-inference trick. We show that our approach performs competitively for classification and outperforms previous methods in terms of accuracy of approximate inference and classification with missing inputs.", "source": "arxiv/ml"}
{"id": "arxiv:2654", "title": "Kernelized Locality-Sensitive Hashing for Semi-Supervised Agglomerative Clustering", "text": "Large scale agglomerative clustering is hindered by computational burdens. We propose a novel scheme where exact inter-instance distance calculation is replaced by the Hamming distance between Kernelized Locality-Sensitive Hashing (KLSH) hashed values. This results in a method that drastically decreases computation time. Additionally, we take advantage of certain labeled data points via distance metric learning to achieve a competitive precision and recall comparing to K-Means but in much less computation time.", "source": "arxiv/ml"}
{"id": "arxiv:2655", "title": "Saturating Auto-Encoders", "text": "We introduce a simple new regularizer for auto-encoders whose hidden-unit activation functions contain at least one zero-gradient (saturated) region. This regularizer explicitly encourages activations in the saturated region(s) of the corresponding activation function. We call these Saturating Auto-Encoders (SATAE). We show that the saturation regularizer explicitly limits the SATAE's ability to reconstruct inputs which are not near the data manifold. Furthermore, we show that a wide variety of features can be learned when different activation functions are used. Finally, connections are established with the Contractive and Sparse Auto-Encoders.", "source": "arxiv/ml"}
{"id": "arxiv:2656", "title": "Big Neural Networks Waste Capacity", "text": "This article exposes the failure of some big neural networks to leverage added capacity to reduce underfitting. Past research suggest diminishing returns when increasing the size of neural networks. Our experiments on ImageNet LSVRC-2010 show that this may be due to the fact there are highly diminishing returns for capacity in terms of training error, leading to underfitting. This suggests that the optimization method - first order gradient descent - fails at this regime. Directly attacking this problem, either through the optimization method or the choices of parametrization, may allow to improve the generalization error on large datasets, for which a large capacity is required.", "source": "arxiv/ml"}
{"id": "arxiv:2657", "title": "Revisiting Natural Gradient for Deep Networks", "text": "We evaluate natural gradient, an algorithm originally proposed in Amari (1997), for learning deep models. The contributions of this paper are as follows. We show the connection between natural gradient and three other recently proposed methods for training deep models: Hessian-Free (Martens, 2010), Krylov Subspace Descent (Vinyals and Povey, 2012) and TONGA (Le Roux et al., 2008). We describe how one can use unlabeled data to improve the generalization error obtained by natural gradient and empirically evaluate the robustness of the algorithm to the ordering of the training set compared to stochastic gradient descent. Finally we extend natural gradient to incorporate second order information alongside the manifold information and provide a benchmark of the new algorithm using a truncated Newton approach for inverting the metric matrix instead of using a diagonal approximation of it.", "source": "arxiv/ml"}
{"id": "arxiv:2658", "title": "Deep Learning for Detecting Robotic Grasps", "text": "We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. In this work, we apply a deep learning approach to solve this problem, which avoids time-consuming hand-design of features. This presents two main challenges. First, we need to evaluate a huge number of candidate grasps. In order to make detection fast, as well as robust, we present a two-step cascaded structure with two deep networks, where the top detections from the first are re-evaluated by the second. The first network has fewer features, is faster to run, and can effectively prune out unlikely candidate grasps. The second, with more features, is slower but has to run only on the top few detections. Second, we need to handle multimodal inputs well, for which we present a method to apply structured regularization on the weights based on multimodal group regularization. We demonstrate that our method outperforms the previous state-of-the-art methods in robotic grasp detection, and can be used to successfully execute grasps on two different robotic platforms.", "source": "arxiv/ml"}
{"id": "arxiv:2659", "title": "Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks", "text": "Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved accuracy achieved by the DNNs is the result of their ability to extract discriminative internal representations that are robust to the many sources of variability in speech signals. We show that these representations become increasingly insensitive to small perturbations in the input with increasing network depth, which leads to better speech recognition performance with deeper networks. We also show that DNNs cannot extrapolate to test samples that are substantially different from the training examples. If the training data are sufficiently representative, however, internal features learned by the DNN are relatively stable with respect to speaker differences, bandwidth differences, and environment distortion. This enables DNN-based recognizers to perform as well or better than state-of-the-art systems based on GMMs or shallow networks without the need for explicit model adaptation or feature normalization.", "source": "arxiv/ml"}
{"id": "arxiv:2660", "title": "Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors", "text": "Knowledge bases provide applications with the benefit of easily accessible, systematic relational knowledge but often suffer in practice from their incompleteness and lack of knowledge of new entities and relations. Much work has focused on building or extending them by finding patterns in large unannotated text corpora. In contrast, here we mainly aim to complete a knowledge base by predicting additional true relationships between entities, based on generalizations that can be discerned in the given knowledgebase. We introduce a neural tensor network (NTN) model which predicts new relationship entries that can be added to the database. This model can be improved by initializing entity representations with word vectors learned in an unsupervised fashion from text, and when doing this, existing relations can even be queried for entities that were not present in the database. Our model generalizes and outperforms existing models for this problem, and can classify unseen relationships in WordNet with an accuracy of 75.8%.", "source": "arxiv/ml"}
{"id": "arxiv:2661", "title": "Two SVDs produce more focal deep learning representations", "text": "A key characteristic of work on deep learning and neural networks in general is that it relies on representations of the input that support generalization, robust inference, domain adaptation and other desirable functionalities. Much recent progress in the field has focused on efficient and effective methods for computing representations. In this paper, we propose an alternative method that is more efficient than prior work and produces representations that have a property we call focality -- a property we hypothesize to be important for neural network representations. The method consists of a simple application of two consecutive SVDs and is inspired by Anandkumar (2012).", "source": "arxiv/ml"}
{"id": "arxiv:2662", "title": "Behavior Pattern Recognition using A New Representation Model", "text": "We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the agents as a Markov decision process (MDP) and model the observed behavior of the agents in terms of forward planning for the MDP. We use IRL to learn reward functions and then use these reward functions as the basis for clustering or classification models. Experimental studies with GridWorld, a navigation problem, and the secretary problem, an optimal stopping problem, suggest reward vectors found from IRL can be a good basis for behavior pattern recognition problems. Empirical comparisons of our method with several existing IRL algorithms and with direct methods that use feature statistics observed in state-action space suggest it may be superior for recognition problems.", "source": "arxiv/ml"}
{"id": "arxiv:2663", "title": "Training Neural Networks with Stochastic Hessian-Free Optimization", "text": "Hessian-free (HF) optimization has been successfully used for training deep autoencoders and recurrent networks. HF uses the conjugate gradient algorithm to construct update directions through curvature-vector products that can be computed on the same order of time as gradients. In this paper we exploit this property and study stochastic HF with gradient and curvature mini-batches independent of the dataset size. We modify Martens' HF for these settings and integrate dropout, a method for preventing co-adaptation of feature detectors, to guard against overfitting. Stochastic Hessian-free optimization gives an intermediary between SGD and HF that achieves competitive performance on both classification and deep autoencoder experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2664", "title": "Regularized Discriminant Embedding for Visual Descriptor Learning", "text": "Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide changes in such environmental conditions, using training pairs of matching and non-matching local image patches that are collected under various environmental conditions. We present a regularized discriminant analysis that emphasizes two challenging categories among the given training pairs: (1) matching, but far apart pairs and (2) non-matching, but close pairs in the original feature space (e.g., SIFT feature space). Compared to existing work on metric learning and discriminant analysis, our method can better distinguish relevant images from irrelevant, but look-alike images.", "source": "arxiv/ml"}
{"id": "arxiv:2665", "title": "Zero-Shot Learning Through Cross-Modal Transfer", "text": "This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot framework distributional information in language can be seen as spanning a semantic basis for understanding what objects look like. Most previous zero-shot learning models can only differentiate between unseen classes. In contrast, our model can both obtain state of the art performance on classes that have thousands of training images and obtain reasonable performance on unseen classes. This is achieved by first using outlier detection in the semantic space and then two separate recognition models. Furthermore, our model does not require any manually defined semantic features for either words or images.", "source": "arxiv/ml"}
{"id": "arxiv:2666", "title": "The IBMAP approach for Markov networks structure learning", "text": "In this work we consider the problem of learning the structure of Markov networks from data. We present an approach for tackling this problem called IBMAP, together with an efficient instantiation of the approach: the IBMAP-HC algorithm, designed for avoiding important limitations of existing independence-based algorithms. These algorithms proceed by performing statistical independence tests on data, trusting completely the outcome of each test. In practice tests may be incorrect, resulting in potential cascading errors and the consequent reduction in the quality of the structures learned. IBMAP contemplates this uncertainty in the outcome of the tests through a probabilistic maximum-a-posteriori approach. The approach is instantiated in the IBMAP-HC algorithm, a structure selection strategy that performs a polynomial heuristic local search in the space of possible structures. We present an extensive empirical evaluation on synthetic and real data, showing that our algorithm outperforms significantly the current independence-based algorithms, in terms of data efficiency and quality of learned structures, with equivalent computational complexities. We also show the performance of IBMAP-HC in a real-world application of knowledge discovery: EDAs, which are evolutionary algorithms that use structure learning on each generation for modeling the distribution of populations. The experiments show that when IBMAP-HC is used to learn the structure, EDAs improve the convergence to the optimum.", "source": "arxiv/ml"}
{"id": "arxiv:2667", "title": "Switched linear encoding with rectified linear autoencoders", "text": "Several recent results in machine learning have established formal connections between autoencoders---artificial neural network models that attempt to reproduce their inputs---and other coding models like sparse coding and K-means. This paper explores in depth an autoencoder model that is constructed using rectified linear activations on its hidden units. Our analysis builds on recent results to further unify the world of sparse linear coding models. We provide an intuitive interpretation of the behavior of these coding models and demonstrate this intuition using small, artificial datasets with known distributions.", "source": "arxiv/ml"}
{"id": "arxiv:2668", "title": "Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients", "text": "Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on stationary problems, and permitting learning rates to grow appropriately in non-stationary tasks. Here, we extend the idea in three directions, addressing proper minibatch parallelization, including reweighted updates for sparse or orthogonal gradients, improving robustness on non-smooth loss functions, in the process replacing the diagonal Hessian estimation procedure that may not always be available by a robust finite-difference approximation. The final algorithm integrates all these components, has linear complexity and is hyper-parameter free.", "source": "arxiv/ml"}
{"id": "arxiv:2669", "title": "Discriminative Recurrent Sparse Auto-Encoders", "text": "We present the discriminative recurrent sparse auto-encoder model, comprising a recurrent encoder of rectified linear units, unrolled for a fixed number of iterations, and connected to two linear decoders that reconstruct the input and predict its supervised classification. Training via backpropagation-through-time initially minimizes an unsupervised sparse reconstruction error; the loss function is then augmented with a discriminative term on the supervised classification. The depth implicit in the temporally-unrolled form allows the system to exhibit all the power of deep networks, while substantially reducing the number of trainable parameters. From an initially unstructured network the hidden units differentiate into categorical-units, each of which represents an input prototype with a well-defined class; and part-units representing deformations of these prototypes. The learned organization of the recurrent encoder is hierarchical: part-units are driven directly by the input, whereas the activity of categorical-units builds up over time through interactions with the part-units. Even using a small number of hidden units per layer, discriminative recurrent sparse auto-encoders achieve excellent performance on MNIST.", "source": "arxiv/ml"}
{"id": "arxiv:2670", "title": "Learning Output Kernels for Multi-Task Problems", "text": "Simultaneously solving multiple related learning tasks is beneficial under a variety of circumstances, but the prior knowledge necessary to correctly model task relationships is rarely available in practice. In this paper, we develop a novel kernel-based multi-task learning technique that automatically reveals structural inter-task relationships. Building over the framework of output kernel learning (OKL), we introduce a method that jointly learns multiple functions and a low-rank multi-task kernel by solving a non-convex regularization problem. Optimization is carried out via a block coordinate descent strategy, where each subproblem is solved using suitable conjugate gradient (CG) type iterative methods for linear operator equations. The effectiveness of the proposed approach is demonstrated on pharmacological and collaborative filtering data.", "source": "arxiv/ml"}
{"id": "arxiv:2671", "title": "Reversible Jump MCMC Simulated Annealing for Neural Networks", "text": "We propose a novel reversible jump Markov chain Monte Carlo (MCMC) simulated annealing algorithm to optimize radial basis function (RBF) networks. This algorithm enables us to maximize the joint posterior distribution of the network parameters and the number of basis functions. It performs a global search in the joint space of the parameters and number of parameters, thereby surmounting the problem of local minima. We also show that by calibrating a Bayesian model, we can obtain the classical AIC, BIC and MDL model selection criteria within a penalized likelihood framework. Finally, we show theoretically and empirically that the algorithm converges to the modes of the full posterior distribution in an efficient way.", "source": "arxiv/ml"}
{"id": "arxiv:2672", "title": "Dynamic Bayesian Multinets", "text": "In this work, dynamic Bayesian multinets are introduced where a Markov chain state at time t determines conditional independence patterns between random variables lying within a local time window surrounding t. It is shown how information-theoretic criterion functions can be used to induce sparse, discriminative, and class-conditional network structures that yield an optimal approximation to the class posterior probability, and therefore are useful for the classification task. Using a new structure learning heuristic, the resulting models are tested on a medium-vocabulary isolated-word speech recognition task. It is demonstrated that these discriminatively structured dynamic Bayesian multinets, when trained in a maximum likelihood setting using EM, can outperform both HMMs and other dynamic Bayesian networks with a similar number of parameters.", "source": "arxiv/ml"}
{"id": "arxiv:2673", "title": "Variational Relevance Vector Machines", "text": "The Support Vector Machine (SVM) of Vapnik (1998) has become widely established as one of the leading approaches to pattern recognition and machine learning. It expresses predictions in terms of a linear combination of kernel functions centred on a subset of the training data, known as support vectors. Despite its widespread success, the SVM suffers from some important limitations, one of the most significant being that it makes point predictions rather than generating predictive distributions. Recently Tipping (1999) has formulated the Relevance Vector Machine (RVM), a probabilistic model whose functional form is equivalent to the SVM. It achieves comparable recognition accuracy to the SVM, yet provides a full predictive distribution, and also requires substantially fewer kernel functions. The original treatment of the RVM relied on the use of type II maximum likelihood (the `evidence framework') to provide point estimates of the hyperparameters which govern model sparsity. In this paper we show how the RVM can be formulated and solved within a completely Bayesian paradigm through the use of variational inference, thereby giving a posterior distribution over both parameters and hyperparameters. We demonstrate the practicality and performance of the variational RVM using both synthetic and real world examples.", "source": "arxiv/ml"}
{"id": "arxiv:2674", "title": "Utilities as Random Variables: Density Estimation and Structure Discovery", "text": "Decision theory does not traditionally include uncertainty over utility functions. We argue that the a person's utility value for a given outcome can be treated as we treat other domain attributes: as a random variable with a density function over its possible values. We show that we can apply statistical density estimation techniques to learn such a density function from a database of partially elicited utility functions. In particular, we define a Bayesian learning framework for this problem, assuming the distribution over utilities is a mixture of Gaussians, where the mixture components represent statistically coherent subpopulations. We can also extend our techniques to the problem of discovering generalized additivity structure in the utility functions in the population. We define a Bayesian model selection criterion for utility function structure and a search procedure over structures. The factorization of the utilities in the learned model, and the generalization obtained from density estimation, allows us to provide robust estimates of utilities using a significantly smaller number of utility elicitation questions. We experiment with our technique on synthetic utility data and on a real database of utility functions in the domain of prenatal diagnosis.", "source": "arxiv/ml"}
{"id": "arxiv:2675", "title": "Bayesian Classification and Feature Selection from Finite Data Sets", "text": "Feature selection aims to select the smallest subset of features for a specified level of performance. The optimal achievable classification performance on a feature subset is summarized by its Receiver Operating Curve (ROC). When infinite data is available, the Neyman- Pearson (NP) design procedure provides the most efficient way of obtaining this curve. In practice the design procedure is applied to density estimates from finite data sets. We perform a detailed statistical analysis of the resulting error propagation on finite alphabets. We show that the estimated performance curve (EPC) produced by the design procedure is arbitrarily accurate given sufficient data, independent of the size of the feature set. However, the underlying likelihood ranking procedure is highly sensitive to errors that reduces the probability that the EPC is in fact the ROC. In the worst case, guaranteeing that the EPC is equal to the ROC may require data sizes exponential in the size of the feature set. These results imply that in theory the NP design approach may only be valid for characterizing relatively small feature subsets, even when the performance of any given classifier can be estimated very accurately. We discuss the practical limitations for on-line methods that ensures that the NP procedure operates in a statistically valid region.", "source": "arxiv/ml"}
{"id": "arxiv:2676", "title": "Experiments with Random Projection", "text": "Recent theoretical work has identified random projection as a promising dimensionality reduction technique for learning mixtures of Gausians. Here we summarize these results and illustrate them by a wide variety of experiments on synthetic and real data.", "source": "arxiv/ml"}
{"id": "arxiv:2677", "title": "A Two-round Variant of EM for Gaussian Mixtures", "text": "Given a set of possible models (e.g., Bayesian network structures) and a data sample, in the unsupervised model selection problem the task is to choose the most accurate model with respect to the domain joint probability distribution. In contrast to this, in supervised model selection it is a priori known that the chosen model will be used in the future for prediction tasks involving more ``focused' predictive distributions. Although focused predictive distributions can be produced from the joint probability distribution by marginalization, in practice the best model in the unsupervised sense does not necessarily perform well in supervised domains. In particular, the standard marginal likelihood score is a criterion for the unsupervised task, and, although frequently used for supervised model selection also, does not perform well in such tasks. In this paper we study the performance of the marginal likelihood score empirically in supervised Bayesian network selection tasks by using a large number of publicly available classification data sets, and compare the results to those obtained by alternative model selection criteria, including empirical crossvalidation methods, an approximation of a supervised marginal likelihood measure, and a supervised version of Dawids prequential(predictive sequential) principle.The results demonstrate that the marginal likelihood score does NOT perform well FOR supervised model selection, WHILE the best results are obtained BY using Dawids prequential r napproach.", "source": "arxiv/ml"}
{"id": "arxiv:2678", "title": "Minimum Message Length Clustering Using Gibbs Sampling", "text": "The K-Mean and EM algorithms are popular in clustering and mixture modeling, due to their simplicity and ease of implementation. However, they have several significant limitations. Both coverage to a local optimum of their respective objective functions (ignoring the uncertainty in the model space), require the apriori specification of the number of classes/clsuters, and are inconsistent. In this work we overcome these limitations by using the Minimum Message Length (MML) principle and a variation to the K-Means/EM observation assignment and parameter calculation scheme. We maintain the simplicity of these approaches while constructing a Bayesian mixture modeling tool that samples/searches the model space using a Markov Chain Monte Carlo (MCMC) sampler known as a Gibbs sampler. Gibbs sampling allows us to visit each model according to its posterior probability. Therefore, if the model space is multi-modal we will visit all models and not get stuck in local optima. We call our approach multiple chains at equilibrium (MCE) MML sampling.", "source": "arxiv/ml"}
{"id": "arxiv:2679", "title": "Mix-nets: Factored Mixtures of Gaussians in Bayesian Networks With Mixed Continuous And Discrete Variables", "text": "Recently developed techniques have made it possible to quickly learn accurate probability density functions from data in low-dimensional continuous space. In particular, mixtures of Gaussians can be fitted to data very quickly using an accelerated EM algorithm that employs multiresolution kd-trees (Moore, 1999). In this paper, we propose a kind of Bayesian networks in which low-dimensional mixtures of Gaussians over different subsets of the domain's variables are combined into a coherent joint probability model over the entire domain. The network is also capable of modeling complex dependencies between discrete variables and continuous variables without requiring discretization of the continuous variables. We present efficient heuristic algorithms for automatically learning these networks from data, and perform comparative experiments illustrated how well these networks model real scientific data and synthetic data. We also briefly discuss some possible improvements to the networks, as well as possible applications.", "source": "arxiv/ml"}
{"id": "arxiv:2680", "title": "Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks", "text": "Particle filters (PFs) are powerful sampling-based inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of probability distribution, nonlinearity and non-stationarity. They have appeared in several fields under such names as \"condensation\", \"sequential Monte Carlo\" and \"survival of the fittest\". In this paper, we show how we can exploit the structure of the DBN to increase the efficiency of particle filtering, using a technique known as Rao-Blackwellisation. Essentially, this samples some of the variables, and marginalizes out the rest exactly, using the Kalman filter, HMM filter, junction tree algorithm, or any other finite dimensional optimal filter. We show that Rao-Blackwellised particle filters (RBPFs) lead to more accurate estimates than standard PFs. We demonstrate RBPFs on two problems, namely non-stationary online regression with radial basis function networks and robot localization and map building. We also discuss other potential application areas and provide references to some finite dimensional optimal filters.", "source": "arxiv/ml"}
{"id": "arxiv:2681", "title": "Learning Graphical Models of Images, Videos and Their Spatial Transformations", "text": "Mixtures of Gaussians, factor analyzers (probabilistic PCA) and hidden Markov models are staples of static and dynamic data modeling and image and video modeling in particular. We show how topographic transformations in the input, such as translation and shearing in images, can be accounted for in these models by including a discrete transformation variable. The resulting models perform clustering, dimensionality reduction and time-series analysis in a way that is invariant to transformations in the input. Using the EM algorithm, these transformation-invariant models can be fit to static data and time series. We give results on filtering microscopy images, face and facial pose clustering, handwritten digit modeling and recognition, video clustering, object tracking, and removal of distractions from video sequences.", "source": "arxiv/ml"}
{"id": "arxiv:2682", "title": "Being Bayesian about Network Structure", "text": "In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian model-selection attempts to find the MAP model and use its structure to answer these questions. However, when the amount of available data is modest, there might be many models that have non-negligible posterior. Thus, we want compute the Bayesian posterior of a feature, i.e., the total posterior probability of all models that contain it. In this paper, we propose a new approach for this task. We first show how to efficiently compute a sum over the exponential number of networks that are consistent with a fixed ordering over network variables. This allows us to compute, for a given ordering, both the marginal probability of the data and the posterior of a feature. We then use this result as the basis for an algorithm that approximates the Bayesian posterior of a feature. Our approach uses a Markov Chain Monte Carlo (MCMC) method, but over orderings rather than over network structures. The space of orderings is much smaller and more regular than the space of structures, and has a smoother posterior `landscape'. We present empirical results on synthetic and real-life datasets that compare our approach to full model averaging (when possible), to MCMC over network structures, and to a non-Bayesian bootstrap approach.", "source": "arxiv/ml"}
{"id": "arxiv:2683", "title": "Gaussian Process Networks", "text": "In this paper we address the problem of learning the structure of a Bayesian network in domains with continuous variables. This task requires a procedure for comparing different candidate structures. In the Bayesian framework, this is done by evaluating the {em marginal likelihood/} of the data given a candidate structure. This term can be computed in closed-form for standard parametric families (e.g., Gaussians), and can be approximated, at some computational cost, for some semi-parametric families (e.g., mixtures of Gaussians). We present a new family of continuous variable probabilistic networks that are based on {em Gaussian Process/} priors. These priors are semi-parametric in nature and can learn almost arbitrary noisy functional relations. Using these priors, we can directly compute marginal likelihoods for structure learning. The resulting method can discover a wide range of functional dependencies in multivariate data. We develop the Bayesian score of Gaussian Process Networks and describe how to learn them from data. We present empirical results on artificial data as well as on real-life domains with non-linear dependencies.", "source": "arxiv/ml"}
{"id": "arxiv:2684", "title": "Inference for Belief Networks Using Coupling From the Past", "text": "Inference for belief networks using Gibbs sampling produces a distribution for unobserved variables that differs from the correct distribution by a (usually) unknown error, since convergence to the right distribution occurs only asymptotically. The method of \"coupling from the past\" samples from exactly the correct distribution by (conceptually) running dependent Gibbs sampling simulations from every possible starting state from a time far enough in the past that all runs reach the same state at time t=0. Explicitly considering every possible state is intractable for large networks, however. We propose a method for layered noisy-or networks that uses a compact, but often imprecise, summary of a set of states. This method samples from exactly the correct distribution, and requires only about twice the time per step as ordinary Gibbs sampling, but it may require more simulation steps than would be needed if chains were tracked exactly.", "source": "arxiv/ml"}
{"id": "arxiv:2685", "title": "Dependency Networks for Collaborative Filtering and Data Visualization", "text": "We describe a graphical model for probabilistic relationships---an alternative to the Bayesian network---called a dependency network. The graph of a dependency network, unlike a Bayesian network, is potentially cyclic. The probability component of a dependency network, like a Bayesian network, is a set of conditional distributions, one for each node given its parents. We identify several basic properties of this representation and describe a computationally efficient procedure for learning the graph and probability components from data. We describe the application of this representation to probabilistic inference, collaborative filtering (the task of predicting preferences), and the visualization of acausal predictive relationships.", "source": "arxiv/ml"}
{"id": "arxiv:2686", "title": "Feature Selection and Dualities in Maximum Entropy Discrimination", "text": "Incorporating feature selection into a classification or regression method often carries a number of advantages. In this paper we formalize feature selection specifically from a discriminative perspective of improving classification/regression accuracy. The feature selection method is developed as an extension to the recently proposed maximum entropy discrimination (MED) framework. We describe MED as a flexible (Bayesian) regularization approach that subsumes, e.g., support vector classification, regression and exponential family models. For brevity, we restrict ourselves primarily to feature selection in the context of linear classification/regression methods and demonstrate that the proposed approach indeed carries substantial improvements in practice. Moreover, we discuss and develop various extensions of feature selection, including the problem of dealing with example specific but unobserved degrees of freedom -- alignments or invariants.", "source": "arxiv/ml"}
{"id": "arxiv:2687", "title": "Tractable Bayesian Learning of Tree Belief Networks", "text": "In this paper we present decomposable priors, a family of priors over structure and parameters of tree belief nets for which Bayesian learning with complete observations is tractable, in the sense that the posterior is also decomposable and can be completely determined analytically in polynomial time. This follows from two main results: First, we show that factored distributions over spanning trees in a graph can be integrated in closed form. Second, we examine priors over tree parameters and show that a set of assumptions similar to (Heckerman and al. 1995) constrain the tree parameter priors to be a compactly parameterized product of Dirichlet distributions. Beside allowing for exact Bayesian learning, these results permit us to formulate a new class of tractable latent variable models in which the likelihood of a data point is computed through an ensemble average over tree structures.", "source": "arxiv/ml"}
{"id": "arxiv:2688", "title": "The Anchors Hierachy: Using the triangle inequality to survive high dimensional data", "text": "This paper is about metric data structures in high-dimensional or non-Euclidean space that permit cached sufficient statistics accelerations of learning algorithms. It has recently been shown that for less than about 10 dimensions, decorating kd-trees with additional \"cached sufficient statistics\" such as first and second moments and contingency tables can provide satisfying acceleration for a very wide range of statistical learning tasks such as kernel regression, locally weighted regression, k-means clustering, mixture modeling and Bayes Net learning. In this paper, we begin by defining the anchors hierarchy - a fast data structure and algorithm for localizing data based only on a triangle-inequality-obeying distance metric. We show how this, in its own right, gives a fast and effective clustering of data. But more importantly we show how it can produce a well-balanced structure similar to a Ball-Tree (Omohundro, 1991) or a kind of metric tree (Uhlmann, 1991; Ciaccia, Patella, & Zezula, 1997) in a way that is neither \"top-down\" nor \"bottom-up\" but instead \"middle-out\". We then show how this structure, decorated with cached sufficient statistics, allows a wide variety of statistical learning algorithms to be accelerated even in thousands of dimensions.", "source": "arxiv/ml"}
{"id": "arxiv:2689", "title": "PEGASUS: A Policy Search Method for Large MDPs and POMDPs", "text": "We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model. Our approach is based on the following observation: Any (PO)MDP can be transformed into an \"equivalent\" POMDP in which all state transitions (given the current state and action) are deterministic. This reduces the general problem of policy search to one in which we need only consider POMDPs with deterministic transitions. We give a natural way of estimating the value of all policies in these transformed POMDPs. Policy search is then simply performed by searching for a policy with high estimated value. We also establish conditions under which our value estimates will be good, recovering theoretical results similar to those of Kearns, Mansour and Ng (1999), but with \"sample complexity\" bounds that have only a polynomial rather than exponential dependence on the horizon time. Our method applies to arbitrary POMDPs, including ones with infinite state and action spaces. We also present empirical results for our approach on a small discrete problem, and on a complex continuous state/continuous action problem involving learning to ride a bicycle.", "source": "arxiv/ml"}
{"id": "arxiv:2690", "title": "Adaptive Importance Sampling for Estimation in Structured Domains", "text": "Sampling is an important tool for estimating large, complex sums and integrals over high dimensional spaces. For instance, important sampling has been used as an alternative to exact methods for inference in belief networks. Ideally, we want to have a sampling distribution that provides optimal-variance estimators. In this paper, we present methods that improve the sampling distribution by systematically adapting it as we obtain information from the samples. We present a stochastic-gradient-descent method for sequentially updating the sampling distribution based on the direct minization of the variance. We also present other stochastic-gradient-descent methods based on the minimizationof typical notions of distance between the current sampling distribution and approximations of the target, optimal distribution. We finally validate and compare the different methods empirically by applying them to the problem of action evaluation in influence diagrams.", "source": "arxiv/ml"}
{"id": "arxiv:2691", "title": "Monte Carlo Inference via Greedy Importance Sampling", "text": "We present a new method for conducting Monte Carlo inference in graphical models which combines explicit search with generalized importance sampling. The idea is to reduce the variance of importance sampling by searching for significant points in the target distribution. We prove that it is possible to introduce search and still maintain unbiasedness. We then demonstrate our procedure on a few simple inference tasks and show that it can improve the inference quality of standard MCMC methods, including Gibbs sampling, Metropolis sampling, and Hybrid Monte Carlo. This paper extends previous work which showed how greedy importance sampling could be correctly realized in the one-dimensional case.", "source": "arxiv/ml"}
{"id": "arxiv:2692", "title": "Combining Feature and Prototype Pruning by Uncertainty Minimization", "text": "We focus in this paper on dataset reduction techniques for use in k-nearest neighbor classification. In such a context, feature and prototype selections have always been independently treated by the standard storage reduction algorithms. While this certifying is theoretically justified by the fact that each subproblem is NP-hard, we assume in this paper that a joint storage reduction is in fact more intuitive and can in practice provide better results than two independent processes. Moreover, it avoids a lot of distance calculations by progressively removing useless instances during the feature pruning. While standard selection algorithms often optimize the accuracy to discriminate the set of solutions, we use in this paper a criterion based on an uncertainty measure within a nearest-neighbor graph. This choice comes from recent results that have proven that accuracy is not always the suitable criterion to optimize. In our approach, a feature or an instance is removed if its deletion improves information of the graph. Numerous experiments are presented in this paper and a statistical analysis shows the relevance of our approach, and its tolerance in the presence of noise.", "source": "arxiv/ml"}
{"id": "arxiv:2693", "title": "Dynamic Trees: A Structured Variational Method Giving Efficient Propagation Rules", "text": "Dynamic trees are mixtures of tree structured belief networks. They solve some of the problems of fixed tree networks at the cost of making exact inference intractable. For this reason approximate methods such as sampling or mean field approaches have been used. However, mean field approximations assume a factorized distribution over node states. Such a distribution seems unlickely in the posterior, as nodes are highly correlated in the prior. Here a structured variational approach is used, where the posterior distribution over the non-evidential nodes is itself approximated by a dynamic tree. It turns out that this form can be used tractably and efficiently. The result is a set of update rules which can propagate information through the network to obtain both a full variational approximation, and the relevant marginals. The progagtion rules are more efficient than the mean field approach and give noticeable quantitative and qualitative improvement in the inference. The marginals calculated give better approximations to the posterior than loopy propagation on a small toy problem.", "source": "arxiv/ml"}
{"id": "arxiv:2694", "title": "An Uncertainty Framework for Classification", "text": "We define a generalized likelihood function based on uncertainty measures and show that maximizing such a likelihood function for different measures induces different types of classifiers. In the probabilistic framework, we obtain classifiers that optimize the cross-entropy function. In the possibilistic framework, we obtain classifiers that maximize the interclass margin. Furthermore, we show that the support vector machine is a sub-class of these maximum-margin classifiers.", "source": "arxiv/ml"}
{"id": "arxiv:2695", "title": "A Branch-and-Bound Algorithm for MDL Learning Bayesian Networks", "text": "This paper extends the work in [Suzuki, 1996] and presents an efficient depth-first branch-and-bound algorithm for learning Bayesian network structures, based on the minimum description length (MDL) principle, for a given (consistent) variable ordering. The algorithm exhaustively searches through all network structures and guarantees to find the network with the best MDL score. Preliminary experiments show that the algorithm is efficient, and that the time complexity grows slowly with the sample size. The algorithm is useful for empirically studying both the performance of suboptimal heuristic search algorithms and the adequacy of the MDL principle in learning Bayesian networks.", "source": "arxiv/ml"}
{"id": "arxiv:2696", "title": "Model-Based Hierarchical Clustering", "text": "We present an approach to model-based hierarchical clustering by formulating an objective function based on a Bayesian analysis. This model organizes the data into a cluster hierarchy while specifying a complex feature-set partitioning that is a key component of our model. Features can have either a unique distribution in every cluster or a common distribution over some (or even all) of the clusters. The cluster subsets over which these features have such a common distribution correspond to the nodes (clusters) of the tree representing the hierarchy. We apply this general model to the problem of document clustering for which we use a multinomial likelihood function and Dirichlet priors. Our algorithm consists of a two-stage process wherein we first perform a flat clustering followed by a modified hierarchical agglomerative merging process that includes determining the features that will have common distributions over the merged clusters. The regularization induced by using the marginal likelihood automatically determines the optimal model structure including number of clusters, the depth of the tree and the subset of features to be modeled as having a common distribution at each node. We present experimental results on both synthetic data and a real document collection.", "source": "arxiv/ml"}
{"id": "arxiv:2697", "title": "Variational Approximations between Mean Field Theory and the Junction Tree Algorithm", "text": "Recently, variational approximations such as the mean field approximation have received much interest. We extend the standard mean field method by using an approximating distribution that factorises into cluster potentials. This includes undirected graphs, directed acyclic graphs and junction trees. We derive generalized mean field equations to optimize the cluster potentials. We show that the method bridges the gap between the standard mean field approximation and the exact junction tree algorithm. In addition, we address the problem of how to choose the graphical structure of the approximating distribution. From the generalised mean field equations we derive rules to simplify the structure of the approximating distribution in advance without affecting the quality of the approximation. We also show how the method fits into some other variational approximations that are currently popular.", "source": "arxiv/ml"}
{"id": "arxiv:2698", "title": "Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration", "text": "The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the following three ideas and give a highly effective policy gradient method: (a) the policy gradients with parameter based exploration, which is a recently proposed policy search method with low variance of gradient estimates, (b) an importance sampling technique, which allows us to reuse previously gathered data in a consistent way, and (c) an optimal baseline, which minimizes the variance of gradient estimates with their unbiasedness being maintained. For the proposed method, we give theoretical analysis of the variance of gradient estimates and show its usefulness through extensive experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2699", "title": "Knowledge Matters: Importance of Prior Information for Optimization", "text": "We explore the effect of introducing prior information into the intermediate level of neural networks for a learning task on which all the state-of-the-art machine learning algorithms tested failed to learn. We motivate our work from the hypothesis that humans learn such intermediate concepts from other individuals via a form of supervision or guidance using a curriculum. The experiments we have conducted provide positive evidence in favor of this hypothesis. In our experiments, a two-tiered MLP architecture is trained on a dataset with 64x64 binary inputs images, each image with three sprites. The final task is to decide whether all the sprites are the same or one of them is different. Sprites are pentomino tetris shapes and they are placed in an image with different locations using scaling and rotation transformations. The first part of the two-tiered MLP is pre-trained with intermediate-level targets being the presence of sprites at each location, while the second part takes the output of the first part as input and predicts the final task's target binary event. The two-tiered MLP architecture, with a few tens of thousand examples, was able to learn the task perfectly, whereas all other algorithms (include unsupervised pre-training, but also traditional algorithms like SVMs, decision trees and boosting) all perform no better than chance. We hypothesize that the optimization difficulty involved when the intermediate pre-training is not performed is due to the {\\em composition} of two highly non-linear tasks. Our findings are also consistent with hypotheses on cultural learning inspired by the observations of optimization problems with deep learning, presumably because of effective local minima.", "source": "arxiv/ml"}
{"id": "arxiv:2700", "title": "On the Product Rule for Classification Problems", "text": "We discuss theoretical aspects of the product rule for classification problems in supervised machine learning for the case of combining classifiers. We show that (1) the product rule arises from the MAP classifier supposing equivalent priors and conditional independence given a class; (2) under some conditions, the product rule is equivalent to minimizing the sum of the squared distances to the respective centers of the classes related with different features, such distances being weighted by the spread of the classes; (3) observing some hypothesis, the product rule is equivalent to concatenating the vectors of features.", "source": "arxiv/ml"}
{"id": "arxiv:2701", "title": "Herded Gibbs Sampling", "text": "The Gibbs sampler is one of the most popular algorithms for inference in statistical models. In this paper, we introduce a herding variant of this algorithm, called herded Gibbs, that is entirely deterministic. We prove that herded Gibbs has an $O(1/T)$ convergence rate for models with independent variables and for fully connected probabilistic graphical models. Herded Gibbs is shown to outperform Gibbs in the tasks of image denoising with MRFs and named entity recognition with CRFs. However, the convergence for herded Gibbs for sparsely connected probabilistic graphical models is still an open problem.", "source": "arxiv/ml"}
{"id": "arxiv:2702", "title": "Affinity Weighted Embedding", "text": "Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to their linear nature, and typically underfit. We propose a new class of models which aim to provide improved performance while retaining many of the benefits of the existing class of embedding models. Our new approach works by iteratively learning a linear embedding model where the next iteration's features and labels are reweighted as a function of the previous iteration. We describe several variants of the family, and give some initial results.", "source": "arxiv/ml"}
{"id": "arxiv:2703", "title": "Latent Relation Representations for Universal Schemas", "text": "Traditional relation extraction predicts relations within some fixed and finite target schema. Machine learning approaches to this task require either manual annotation or, in the case of distant supervision, existing structured sources of the same schema. The need for existing datasets can be avoided by using a universal schema: the union of all involved schemas (surface form predicates as in OpenIE, and relations in the schemas of pre-existing databases). This schema has an almost unlimited set of relations (due to surface forms), and supports integration with existing structured data (through the relation types of existing databases). To populate a database of such schema we present a family of matrix factorization models that predict affinity between database tuples and relations. We show that this achieves substantially higher accuracy than the traditional classification approach. More importantly, by operating simultaneously on relations observed in text and in pre-existing structured DBs such as Freebase, we are able to reason about unstructured and structured data in mutually-supporting ways. By doing so our approach outperforms state-of-the-art distant supervision systems.", "source": "arxiv/ml"}
{"id": "arxiv:2704", "title": "A Linearly Convergent Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization", "text": "Linear optimization is many times algorithmically simpler than non-linear convex optimization. Linear optimization over matroid polytopes, matching polytopes and path polytopes are example of problems for which we have simple and efficient combinatorial algorithms, but whose non-linear convex counterpart is harder and admits significantly less efficient algorithms. This motivates the computational model of convex optimization, including the offline, online and stochastic settings, using a linear optimization oracle. In this computational model we give several new results that improve over the previous state-of-the-art. Our main result is a novel conditional gradient algorithm for smooth and strongly convex optimization over polyhedral sets that performs only a single linear optimization step over the domain on each iteration and enjoys a linear convergence rate. This gives an exponential improvement in convergence rate over previous results. Based on this new conditional gradient algorithm we give the first algorithms for online convex optimization over polyhedral sets that perform only a single linear optimization step over the domain while having optimal regret guarantees, answering an open question of Kalai and Vempala, and Hazan and Kale. Our online algorithms also imply conditional gradient algorithms for non-smooth and stochastic convex optimization with the same convergence rates as projected (sub)gradient methods.", "source": "arxiv/ml"}
{"id": "arxiv:2705", "title": "Cellular Tree Classifiers", "text": "The cellular tree classifier model addresses a fundamental problem in the design of classifiers for a parallel or distributed computing world: Given a data set, is it sufficient to apply a majority rule for classification, or shall one split the data into two or more parts and send each part to a potentially different computer (or cell) for further processing? At first sight, it seems impossible to define with this paradigm a consistent classifier as no cell knows the \"original data size\", $n$. However, we show that this is not so by exhibiting two different consistent classifiers. The consistency is universal but is only shown for distributions with nonatomic marginals.", "source": "arxiv/ml"}
{"id": "arxiv:2706", "title": "Pattern Matching for Self- Tuning of MapReduce Jobs", "text": "In this paper, we study CPU utilization time patterns of several MapReduce applications. After extracting running patterns of several applications, they are saved in a reference database to be later used to tweak system parameters to efficiently execute unknown applications in future. To achieve this goal, CPU utilization patterns of new applications are compared with the already known ones in the reference database to find/predict their most probable execution patterns. Because of different patterns lengths, the Dynamic Time Warping (DTW) is utilized for such comparison; a correlation analysis is then applied to DTWs outcomes to produce feasible similarity patterns. Three real applications (WordCount, Exim Mainlog parsing and Terasort) are used to evaluate our hypothesis in tweaking system parameters in executing similar applications. Results were very promising and showed effectiveness of our approach on pseudo-distributed MapReduce platforms.", "source": "arxiv/ml"}
{"id": "arxiv:2707", "title": "A Linear Time Active Learning Algorithm for Link Classification -- Full Version --", "text": "We present very efficient active learning algorithms for link classification in signed networks. Our algorithms are motivated by a stochastic model in which edge labels are obtained through perturbations of a initial sign assignment consistent with a two-clustering of the nodes. We provide a theoretical analysis within this model, showing that we can achieve an optimal (to whithin a constant factor) number of mistakes on any graph G = (V,E) such that |E| = \\Omega(|V|^{3/2}) by querying O(|V|^{3/2}) edge labels. More generally, we show an algorithm that achieves optimality to within a factor of O(k) by querying at most order of |V| + (|V|/k)^{3/2} edge labels. The running time of this algorithm is at most of order |E| + |V|\\log|V|.", "source": "arxiv/ml"}
{"id": "arxiv:2708", "title": "A Correlation Clustering Approach to Link Classification in Signed Networks -- Full Version --", "text": "Motivated by social balance theory, we develop a theory of link classification in signed networks using the correlation clustering index as measure of label regularity. We derive learning bounds in terms of correlation clustering within three fundamental transductive learning settings: online, batch and active. Our main algorithmic contribution is in the active setting, where we introduce a new family of efficient link classifiers based on covering the input graph with small circuits. These are the first active algorithms for link classification with mistake bounds that hold for arbitrary signed networks.", "source": "arxiv/ml"}
{"id": "arxiv:2709", "title": "Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots", "text": "We introduce the Self-Adaptive Goal Generation - Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsi- cally motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distribution of parameterized tasks/goals. The architecture makes the robot sample actively novel parameterized tasks in the task space, based on a measure of competence progress, each of which triggers low-level goal-directed learning of the motor policy pa- rameters that allow to solve it. For both learning and generalization, the system leverages regression techniques which allow to infer the motor policy parameters corresponding to a given novel parameterized task, and based on the previously learnt correspondences between policy and task parameters. We present experiments with high-dimensional continuous sensorimotor spaces in three different robotic setups: 1) learning the inverse kinematics in a highly-redundant robotic arm, 2) learning omnidirectional locomotion with motor primitives in a quadruped robot, 3) an arm learning to control a fishing rod with a flexible wire. We show that 1) exploration in the task space can be a lot faster than exploration in the actuator space for learning inverse models in redundant robots; 2) selecting goals maximizing competence progress creates developmental trajectories driving the robot to progressively focus on tasks of increasing complexity and is statistically significantly more efficient than selecting tasks randomly, as well as more efficient than different standard active motor babbling methods; 3) this architecture allows the robot to actively discover which parts of its task space it can learn to reach and which part it cannot.", "source": "arxiv/ml"}
{"id": "arxiv:2710", "title": "Dirichlet draws are sparse with high probability", "text": "This note provides an elementary proof of the folklore fact that draws from a Dirichlet distribution (with parameters less than 1) are typically sparse (most coordinates are small).", "source": "arxiv/ml"}
{"id": "arxiv:2711", "title": "Evaluation of a Supervised Learning Approach for Stock Market Operations", "text": "Data mining methods have been widely applied in financial markets, with the purpose of providing suitable tools for prices forecasting and automatic trading. Particularly, learning methods aim to identify patterns in time series and, based on such patterns, to recommend buy/sell operations. The objective of this work is to evaluate the performance of Random Forests, a supervised learning method based on ensembles of decision trees, for decision support in stock markets. Preliminary results indicate good rates of successful operations and good rates of return per operation, providing a strong motivation for further research in this topic.", "source": "arxiv/ml"}
{"id": "arxiv:2712", "title": "Heteroscedastic Conditional Ordinal Random Fields for Pain Intensity Estimation from Facial Images", "text": "We propose a novel method for automatic pain intensity estimation from facial images based on the framework of kernel Conditional Ordinal Random Fields (KCORF). We extend this framework to account for heteroscedasticity on the output labels(i.e., pain intensity scores) and introduce a novel dynamic features, dynamic ranks, that impose temporal ordinal constraints on the static ranks (i.e., intensity scores). Our experimental results show that the proposed approach outperforms state-of-the art methods for sequence classification with ordinal data and other ordinal regression models. The approach performs significantly better than other models in terms of Intra-Class Correlation measure, which is the most accepted evaluation measure in the tasks of facial behaviour intensity estimation.", "source": "arxiv/ml"}
{"id": "arxiv:2713", "title": "Piecewise Linear Multilayer Perceptrons and Dropout", "text": "We propose a new type of hidden layer for a multilayer perceptron, and demonstrate that it obtains the best reported performance for an MLP on the MNIST dataset.", "source": "arxiv/ml"}
{"id": "arxiv:2714", "title": "Active Learning on Trees and Graphs", "text": "We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we characterize (up to constant factors) the optimal placement of queries so to minimize the mistakes made on the non-queried nodes. Our query selection algorithm is extremely efficient, and the optimal number of mistakes on the non-queried nodes is achieved by a simple and efficient mincut classifier. Through a simple modification of the query selection algorithm we also show optimality (up to constant factors) with respect to the trade-off between number of queries and number of mistakes on non-queried nodes. By using spanning trees, our algorithms can be efficiently applied to general graphs, although the problem of finding optimal and efficient active learning algorithms for general graphs remains open. Towards this end, we provide a lower bound on the number of mistakes made on arbitrary graphs by any active learning algorithm using a number of queries which is up to a constant fraction of the graph size.", "source": "arxiv/ml"}
{"id": "arxiv:2715", "title": "See the Tree Through the Lines: The Shazoo Algorithm -- Full Version --", "text": "Predicting the nodes of a given graph is a fascinating theoretical problem with applications in several domains. Since graph sparsification via spanning trees retains enough information while making the task much easier, trees are an important special case of this problem. Although it is known how to predict the nodes of an unweighted tree in a nearly optimal way, in the weighted case a fully satisfactory algorithm is not available yet. We fill this hole and introduce an efficient node predictor, Shazoo, which is nearly optimal on any weighted tree. Moreover, we show that Shazoo can be viewed as a common nontrivial generalization of both previous approaches for unweighted trees and weighted lines. Experiments on real-world datasets confirm that Shazoo performs well in that it fully exploits the structure of the input tree, and gets very close to (and sometimes better than) less scalable energy minimization methods.", "source": "arxiv/ml"}
{"id": "arxiv:2716", "title": "Properties of the Least Squares Temporal Difference learning algorithm", "text": "This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumental variables, the linear dynamical system view as well as the limit of the TD iteration. We also give a geometric view of the algorithm as an oblique projection. Furthermore, there is an extensive comparison of the optimization problem solved by LSTD as compared to Bellman Residual Minimization (BRM). We then review several schemes for the regularization of the LSTD solution. We then proceed to treat the modification of LSTD for the case of episodic Markov Reward Processes.", "source": "arxiv/ml"}
{"id": "arxiv:2717", "title": "The connection between Bayesian estimation of a Gaussian random field and RKHS", "text": "Reconstruction of a function from noisy data is often formulated as a regularized optimization problem over an infinite-dimensional reproducing kernel Hilbert space (RKHS). The solution describes the observed data and has a small RKHS norm. When the data fit is measured using a quadratic loss, this estimator has a known statistical interpretation. Given the noisy measurements, the RKHS estimate represents the posterior mean (minimum variance estimate) of a Gaussian random field with covariance proportional to the kernel associated with the RKHS. In this paper, we provide a statistical interpretation when more general losses are used, such as absolute value, Vapnik or Huber. Specifically, for any finite set of sampling locations (including where the data were collected), the MAP estimate for the signal samples is given by the RKHS estimate evaluated at these locations.", "source": "arxiv/ml"}
{"id": "arxiv:2718", "title": "Online Learning with Pairwise Loss Functions", "text": "Efficient online learning with pairwise loss functions is a crucial component in building large-scale learning system that maximizes the area under the Receiver Operator Characteristic (ROC) curve. In this paper we investigate the generalization performance of online learning algorithms with pairwise loss functions. We show that the existing proof techniques for generalization bounds of online algorithms with a univariate loss can not be directly applied to pairwise losses. In this paper, we derive the first result providing data-dependent bounds for the average risk of the sequence of hypotheses generated by an arbitrary online learner in terms of an easily computable statistic, and show how to extract a low risk hypothesis from the sequence. We demonstrate the generality of our results by applying it to two important problems in machine learning. First, we analyze two online algorithms for bipartite ranking; one being a natural extension of the perceptron algorithm and the other using online convex optimization. Secondly, we provide an analysis for the risk bound for an online algorithm for supervised metric learning.", "source": "arxiv/ml"}
{"id": "arxiv:2719", "title": "Why Size Matters: Feature Coding as Nystrom Sampling", "text": "Recently, the computer vision and machine learning community has been in favor of feature extraction pipelines that rely on a coding step followed by a linear classifier, due to their overall simplicity, well understood properties of linear classifiers, and their computational efficiency. In this paper we propose a novel view of this pipeline based on kernel methods and Nystrom sampling. In particular, we focus on the coding of a data point with a local representation based on a dictionary with fewer elements than the number of data points, and view it as an approximation to the actual function that would compute pair-wise similarity to all data points (often too many to compute in practice), followed by a Nystrom sampling step to select a subset of all data points. Furthermore, since bounds are known on the approximation power of Nystrom sampling as a function of how many samples (i.e. dictionary size) we consider, we can derive bounds on the approximation of the exact (but expensive to compute) kernel matrix, and use it as a proxy to predict accuracy as a function of the dictionary size, which has been observed to increase but also to saturate as we increase its size. This model may help explaining the positive effect of the codebook size and justifying the need to stack more layers (often referred to as deep learning), as flat models empirically saturate as we add more complexity.", "source": "arxiv/ml"}
{"id": "arxiv:2720", "title": "Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning", "text": "This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning algorithm that enables the learning agent to query the expert for more informative demonstrations, thus leading to more sample-efficient learning. For this novel algorithm (Generalized Binary Search for Inverse Reinforcement Learning, or GBS-IRL), we provide a theoretical bound on sample complexity and illustrate its applicability on several different tasks. To our knowledge, GBS-IRL is the first active IRL algorithm with provable sample complexity bounds. We also discuss our method in light of other existing methods in the literature and its general applicability in multi-class classification problems. Finally, motivated by recent work on learning from demonstration in robots, we also discuss how different forms of human feedback can be integrated in a transparent manner in our learning framework.", "source": "arxiv/ml"}
{"id": "arxiv:2721", "title": "Regularization and nonlinearities for neural language models: when are they needed?", "text": "Neural language models (LMs) based on recurrent neural networks (RNN) are some of the most successful word and character-level LMs. Why do they work so well, in particular better than linear neural LMs? Possible explanations are that RNNs have an implicitly better regularization or that RNNs have a higher capacity for storing patterns due to their nonlinearities or both. Here we argue for the first explanation in the limit of little training data and the second explanation for large amounts of text data. We show state-of-the-art performance on the popular and small Penn dataset when RNN LMs are regularized with random dropout. Nonetheless, we show even better performance from a simplified, much less expressive linear RNN model without off-diagonal entries in the recurrent matrix. We call this model an impulse-response LM (IRLM). Using random dropout, column normalization and annealed learning rates, IRLMs develop neurons that keep a memory of up to 50 words in the past and achieve a perplexity of 102.5 on the Penn dataset. On two large datasets however, the same regularization methods are unsuccessful for both models and the RNN's expressivity allows it to overtake the IRLM by 10 and 20 percent perplexity, respectively. Despite the perplexity gap, IRLMs still outperform RNNs on the Microsoft Research Sentence Completion (MRSC) task. We develop a slightly modified IRLM that separates long-context units (LCUs) from short-context units and show that the LCUs alone achieve a state-of-the-art performance on the MRSC task of 60.8%. Our analysis indicates that a fruitful direction of research for neural LMs lies in developing more accessible internal representations, and suggests an optimization regime of very high momentum terms for effectively training such models.", "source": "arxiv/ml"}
{"id": "arxiv:2722", "title": "Transfer Topic Modeling with Ease and Scalability", "text": "The increasing volume of short texts generated on social media sites, such as Twitter or Facebook, creates a great demand for effective and efficient topic modeling approaches. While latent Dirichlet allocation (LDA) can be applied, it is not optimal due to its weakness in handling short texts with fast-changing topics and scalability concerns. In this paper, we propose a transfer learning approach that utilizes abundant labeled documents from other domains (such as Yahoo! News or Wikipedia) to improve topic modeling, with better model fitting and result interpretation. Specifically, we develop Transfer Hierarchical LDA (thLDA) model, which incorporates the label information from other domains via informative priors. In addition, we develop a parallel implementation of our model for large-scale applications. We demonstrate the effectiveness of our thLDA model on both a microblogging dataset and standard text collections including AP and RCV1 datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2723", "title": "Reinforcement learning from comparisons: Three alternatives is enough, two is not", "text": "The paper deals with the problem of finding the best alternatives on the basis of pairwise comparisons when these comparisons need not be transitive. In this setting, we study a reinforcement urn model. We prove convergence to the optimal solution when reinforcement of a winning alternative occurs each time after considering three random alternatives. The simpler process, which reinforces the winner of a random pair does not always converges: it may cycle.", "source": "arxiv/ml"}
{"id": "arxiv:2724", "title": "Phase Diagram and Approximate Message Passing for Blind Calibration and Dictionary Learning", "text": "We consider dictionary learning and blind calibration for signals and matrices created from a random ensemble. We study the mean-squared error in the limit of large signal dimension using the replica method and unveil the appearance of phase transitions delimiting impossible, possible-but-hard and possible inference regions. We also introduce an approximate message passing algorithm that asymptotically matches the theoretical performance, and show through numerical tests that it performs very well, for the calibration problem, for tractable system sizes.", "source": "arxiv/ml"}
{"id": "arxiv:2725", "title": "Recycling Proof Patterns in Coq: Case Studies", "text": "Development of Interactive Theorem Provers has led to the creation of big libraries and varied infrastructures for formal proofs. However, despite (or perhaps due to) their sophistication, the re-use of libraries by non-experts or across domains is a challenge. In this paper, we provide detailed case studies and evaluate the machine-learning tool ML4PG built to interactively data-mine the electronic libraries of proofs, and to provide user guidance on the basis of proof patterns found in the existing libraries.", "source": "arxiv/ml"}
{"id": "arxiv:2726", "title": "Weighted Last-Step Min-Max Algorithm with Improved Sub-Logarithmic Regret", "text": "In online learning the performance of an algorithm is typically compared to the performance of a fixed function from some class, with a quantity called regret. Forster proposed a last-step min-max algorithm which was somewhat simpler than the algorithm of Vovk, yet with the same regret. In fact the algorithm he analyzed assumed that the choices of the adversary are bounded, yielding artificially only the two extreme cases. We fix this problem by weighing the examples in such a way that the min-max problem will be well defined, and provide analysis with logarithmic regret that may have better multiplicative factor than both bounds of Forster and Vovk. We also derive a new bound that may be sub-logarithmic, as a recent bound of Orabona et.al, but may have better multiplicative factor. Finally, we analyze the algorithm in a weak-type of non-stationary setting, and show a bound that is sub-linear if the non-stationarity is sub-linear as well.", "source": "arxiv/ml"}
{"id": "arxiv:2727", "title": "Sample Complexity of Bayesian Optimal Dictionary Learning", "text": "We consider a learning problem of identifying a dictionary matrix D (M times N dimension) from a sample set of M dimensional vectors Y = N^{-1/2} DX, where X is a sparse matrix (N times P dimension) in which the density of non-zero entries is 0<rho< 1. In particular, we focus on the minimum sample size P_c (sample complexity) necessary for perfectly identifying D of the optimal learning scheme when D and X are independently generated from certain distributions. By using the replica method of statistical mechanics, we show that P_c=O(N) holds as long as alpha = M/N >rho is satisfied in the limit of N to infinity. Our analysis also implies that the posterior distribution given Y is condensed only at the correct dictionary D when the compression rate alpha is greater than a certain critical value alpha_M(rho). This suggests that belief propagation may allow us to learn D with a low computational complexity using O(N) samples.", "source": "arxiv/ml"}
{"id": "arxiv:2728", "title": "LA-LDA: A Limited Attention Topic Model for Social Recommendation", "text": "Social media users have finite attention which limits the number of incoming messages from friends they can process. Moreover, they pay more attention to opinions and recommendations of some friends more than others. In this paper, we propose LA-LDA, a latent topic model which incorporates limited, non-uniformly divided attention in the diffusion process by which opinions and information spread on the social network. We show that our proposed model is able to learn more accurate user models from users' social network and item adoption behavior than models which do not take limited attention into account. We analyze voting on news items on the social news aggregator Digg and show that our proposed model is better able to predict held out votes than alternative models. Our study demonstrates that psycho-socially motivated models have better ability to describe and predict observed behavior than models which only consider topics.", "source": "arxiv/ml"}
{"id": "arxiv:2729", "title": "Equitability Analysis of the Maximal Information Coefficient, with Comparisons", "text": "A measure of dependence is said to be equitable if it gives similar scores to equally noisy relationships of different types. Equitability is important in data exploration when the goal is to identify a relatively small set of strongest associations within a dataset as opposed to finding as many non-zero associations as possible, which often are too many to sift through. Thus an equitable statistic, such as the maximal information coefficient (MIC), can be useful for analyzing high-dimensional data sets. Here, we explore both equitability and the properties of MIC, and discuss several aspects of the theory and practice of MIC. We begin by presenting an intuition behind the equitability of MIC through the exploration of the maximization and normalization steps in its definition. We then examine the speed and optimality of the approximation algorithm used to compute MIC, and suggest some directions for improving both. Finally, we demonstrate in a range of noise models and sample sizes that MIC is more equitable than natural alternatives, such as mutual information estimation and distance correlation.", "source": "arxiv/ml"}
{"id": "arxiv:2730", "title": "Hierarchical Data Representation Model - Multi-layer NMF", "text": "In this paper, we propose a data representation model that demonstrates hierarchical feature learning using nsNMF. We extend unit algorithm into several layers. Experiments with document and image data successfully discovered feature hierarchies. We also prove that proposed method results in much better classification and reconstruction performance, especially for small number of features. feature hierarchies.", "source": "arxiv/ml"}
{"id": "arxiv:2731", "title": "An improvement to k-nearest neighbor classifier", "text": "K-Nearest neighbor classifier (k-NNC) is simple to use and has little design time like finding k values in k-nearest neighbor classifier, hence these are suitable to work with dynamically varying data-sets. There exists some fundamental improvements over the basic k-NNC, like weighted k-nearest neighbors classifier (where weights to nearest neighbors are given based on linear interpolation), using artificially generated training set called bootstrapped training set, etc. These improvements are orthogonal to space reduction and classification time reduction techniques, hence can be coupled with any of them. The paper proposes another improvement to the basic k-NNC where the weights to nearest neighbors are given based on Gaussian distribution (instead of linear interpolation as done in weighted k-NNC) which is also independent of any space reduction and classification time reduction technique. We formally show that our proposed method is closely related to non-parametric density estimation using a Gaussian kernel. We experimentally demonstrate using various standard data-sets that the proposed method is better than the existing ones in most cases.", "source": "arxiv/ml"}
{"id": "arxiv:2732", "title": "Discriminative Feature Selection for Uncertain Graph Classification", "text": "Mining discriminative features for graph data has attracted much attention in recent years due to its important role in constructing graph classifiers, generating graph indices, etc. Most measurement of interestingness of discriminative subgraph features are defined on certain graphs, where the structure of graph objects are certain, and the binary edges within each graph represent the \"presence\" of linkages among the nodes. In many real-world applications, however, the linkage structure of the graphs is inherently uncertain. Therefore, existing measurements of interestingness based upon certain graphs are unable to capture the structural uncertainty in these applications effectively. In this paper, we study the problem of discriminative subgraph feature selection from uncertain graphs. This problem is challenging and different from conventional subgraph mining problems because both the structure of the graph objects and the discrimination score of each subgraph feature are uncertain. To address these challenges, we propose a novel discriminative subgraph feature selection method, DUG, which can find discriminative subgraph features in uncertain graphs based upon different statistical measures including expectation, median, mode and phi-probability. We first compute the probability distribution of the discrimination scores for each subgraph feature based on dynamic programming. Then a branch-and-bound algorithm is proposed to search for discriminative subgraphs efficiently. Extensive experiments on various neuroimaging applications (i.e., Alzheimer's Disease, ADHD and HIV) have been performed to analyze the gain in performance by taking into account structural uncertainties in identifying discriminative subgraph features for graph classification.", "source": "arxiv/ml"}
{"id": "arxiv:2733", "title": "Political Disaffection: a case study on the Italian Twitter community", "text": "In our work we analyse the political disaffection or \"the subjective feeling of powerlessness, cynicism, and lack of confidence in the political process, politicians, and democratic institutions, but with no questioning of the political regime\" by exploiting Twitter data through machine learning techniques. In order to validate the quality of the time-series generated by the Twitter data, we highlight the relations of these data with political disaffection as measured by means of public opinion surveys. Moreover, we show that important political news of Italian newspapers are often correlated with the highest peaks of the produced time-series.", "source": "arxiv/ml"}
{"id": "arxiv:2734", "title": "Clustering-Based Matrix Factorization", "text": "Recommender systems are emerging technologies that nowadays can be found in many applications such as Amazon, Netflix, and so on. These systems help users to find relevant information, recommendations, and their preferred items. Slightly improvement of the accuracy of these recommenders can highly affect the quality of recommendations. Matrix Factorization is a popular method in Recommendation Systems showing promising results in accuracy and complexity. In this paper we propose an extension of matrix factorization which adds general neighborhood information on the recommendation model. Users and items are clustered into different categories to see how these categories share preferences. We then employ these shared interests of categories in a fusion by Biased Matrix Factorization to achieve more accurate recommendations. This is a complement for the current neighborhood aware matrix factorization models which rely on using direct neighborhood information of users and items. The proposed model is tested on two well-known recommendation system datasets: Movielens100k and Netflix. Our experiment shows applying the general latent features of categories into factorized recommender models improves the accuracy of recommendations. The current neighborhood-aware models need a great number of neighbors to acheive good accuracies. To the best of our knowledge, the proposed model is better than or comparable with the current neighborhood-aware models when they consider fewer number of neighbors.", "source": "arxiv/ml"}
{"id": "arxiv:2735", "title": "Inferring Parameters and Structure of Latent Variable Models by Variational Bayes", "text": "Current methods for learning graphical models with latent variables and a fixed structure estimate optimal values for the model parameters. Whereas this approach usually produces overfitting and suboptimal generalization performance, carrying out the Bayesian program of computing the full posterior distributions over the parameters remains a difficult problem. Moreover, learning the structure of models with latent variables, for which the Bayesian approach is crucial, is yet a harder problem. In this paper I present the Variational Bayes framework, which provides a solution to these problems. This approach approximates full posterior distributions over model parameters and structures, as well as latent variables, in an analytical manner without resorting to sampling methods. Unlike in the Laplace approximation, these posteriors are generally non-Gaussian and no Hessian needs to be computed. The resulting algorithm generalizes the standard Expectation Maximization algorithm, and its convergence is guaranteed. I demonstrate that this algorithm can be applied to a large class of models in several domains, including unsupervised clustering and blind source separation.", "source": "arxiv/ml"}
{"id": "arxiv:2736", "title": "Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributions", "text": "We consider on-line density estimation with a parameterized density from the exponential family. The on-line algorithm receives one example at a time and maintains a parameter that is essentially an average of the past examples. After receiving an example the algorithm incurs a loss which is the negative log-likelihood of the example w.r.t. the past parameter of the algorithm. An off-line algorithm can choose the best parameter based on all the examples. We prove bounds on the additional total loss of the on-line algorithm over the total loss of the off-line algorithm. These relative loss bounds hold for an arbitrary sequence of examples. The goal is to design algorithms with the best possible relative loss bounds. We use a certain divergence to derive and analyze the algorithms. This divergence is a relative entropy between two exponential distributions.", "source": "arxiv/ml"}
{"id": "arxiv:2737", "title": "Discovering the Hidden Structure of Complex Dynamic Systems", "text": "Dynamic Bayesian networks provide a compact and natural representation for complex dynamic systems. However, in many cases, there is no expert available from whom a model can be elicited. Learning provides an alternative approach for constructing models of dynamic systems. In this paper, we address some of the crucial computational aspects of learning the structure of dynamic systems, particularly those where some relevant variables are partially observed or even entirely unknown. Our approach is based on the Structural Expectation Maximization (SEM) algorithm. The main computational cost of the SEM algorithm is the gathering of expected sufficient statistics. We propose a novel approximation scheme that allows these sufficient statistics to be computed efficiently. We also investigate the fundamental problem of discovering the existence of hidden variables without exhaustive and expensive search. Our approach is based on the observation that, in dynamic systems, ignoring a hidden variable typically results in a violation of the Markov property. Thus, our algorithm searches for such violations in the data, and introduces hidden variables to explain them. We provide empirical results showing that the algorithm is able to learn the dynamics of complex systems in a computationally tractable way.", "source": "arxiv/ml"}
{"id": "arxiv:2738", "title": "Comparing Bayesian Network Classifiers", "text": "In this paper, we empirically evaluate algorithms for learning four types of Bayesian network (BN) classifiers - Naive-Bayes, tree augmented Naive-Bayes, BN augmented Naive-Bayes and general BNs, where the latter two are learned using two variants of a conditional-independence (CI) based BN-learning algorithm. Experimental results show the obtained classifiers, learned using the CI based algorithms, are competitive with (or superior to) the best known classifiers, based on both Bayesian networks and other formalisms; and that the computational time for learning and using these classifiers is relatively small. Moreover, these results also suggest a way to learn yet more effective classifiers; we demonstrate empirically that this new algorithm does work as expected. Collectively, these results argue that BN classifiers deserve more attention in machine learning and data mining communities.", "source": "arxiv/ml"}
{"id": "arxiv:2739", "title": "Fast Learning from Sparse Data", "text": "We describe two techniques that significantly improve the running time of several standard machine-learning algorithms when data is sparse. The first technique is an algorithm that effeciently extracts one-way and two-way counts--either real or expected-- from discrete data. Extracting such counts is a fundamental step in learning algorithms for constructing a variety of models including decision trees, decision graphs, Bayesian networks, and naive-Bayes clustering models. The second technique is an algorithm that efficiently performs the E-step of the EM algorithm (i.e. inference) when applied to a naive-Bayes clustering model. Using real-world data sets, we demonstrate a dramatic decrease in running time for algorithms that incorporate these techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2740", "title": "Learning Polytrees", "text": "We consider the task of learning the maximum-likelihood polytree from data. Our first result is a performance guarantee establishing that the optimal branching (or Chow-Liu tree), which can be computed very easily, constitutes a good approximation to the best polytree. We then show that it is not possible to do very much better, since the learning problem is NP-hard even to approximately solve within some constant factor.", "source": "arxiv/ml"}
{"id": "arxiv:2741", "title": "Model-Based Bayesian Exploration", "text": "Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of Information - the expected improvement in future decision quality arising from the information acquired by exploration. Estimating this quantity requires an assessment of the agent's uncertainty about its current value estimates for states. In this paper we investigate ways of representing and reasoning about this uncertainty in algorithms where the system attempts to learn a model of its environment. We explicitly represent uncertainty about the parameters of the model and build probability distributions over Q-values based on these. These distributions are used to compute a myopic approximation to the value of information for each action and hence to select the action that best balances exploration and exploitation.", "source": "arxiv/ml"}
{"id": "arxiv:2742", "title": "Data Analysis with Bayesian Networks: A Bootstrap Approach", "text": "In recent years there has been significant progress in algorithms and methods for inducing Bayesian networks from data. However, in complex data analysis problems, we need to go beyond being satisfied with inducing networks with high scores. We need to provide confidence measures on features of these networks: Is the existence of an edge between two nodes warranted? Is the Markov blanket of a given node robust? Can we say something about the ordering of the variables? We should be able to address these questions, even when the amount of data is not enough to induce a high scoring network. In this paper we propose Efron's Bootstrap as a computationally efficient approach for answering these questions. In addition, we propose to use these confidence measures to induce better structures from the data, and to detect the presence of latent variables.", "source": "arxiv/ml"}
{"id": "arxiv:2743", "title": "Learning Bayesian Network Structure from Massive Datasets: The \"Sparse Candidate\" Algorithm", "text": "Learning Bayesian networks is often cast as an optimization problem, where the computational task is to find a structure that maximizes a statistically motivated score. By and large, existing learning tools address this optimization problem using standard heuristic search techniques. Since the search space is extremely large, such search procedures can spend most of the time examining candidates that are extremely unreasonable. This problem becomes critical when we deal with data sets that are large either in the number of instances, or the number of attributes. In this paper, we introduce an algorithm that achieves faster learning by restricting the search space. This iterative algorithm restricts the parents of each variable to belong to a small subset of candidates. We then search for a network that satisfies these constraints. The learned network is then used for selecting better candidates for the next iteration. We evaluate this algorithm both on synthetic and real-life data. Our results show that it is significantly faster than alternative search procedures without loss of quality in the learned structures.", "source": "arxiv/ml"}
{"id": "arxiv:2744", "title": "Parameter Priors for Directed Acyclic Graphical Models and the Characterization of Several Probability Distributions", "text": "We show that the only parameter prior for complete Gaussian DAG models that satisfies global parameter independence, complete model equivalence, and some weak regularity assumptions, is the normal-Wishart distribution. Our analysis is based on the following new characterization of the Wishart distribution: let W be an n x n, n >= 3, positive-definite symmetric matrix of random variables and f(W) be a pdf of W. Then, f(W) is a Wishart distribution if and only if W_{11}-W_{12}W_{22}^{-1}W_{12}' is independent of {W_{12}, W_{22}} for every block partitioning W_{11}, W_{12}, W_{12}', W_{22} of W. Similar characterizations of the normal and normal-Wishart distributions are provided as well. We also show how to construct a prior for every DAG model over X from the prior of a single regression model.", "source": "arxiv/ml"}
{"id": "arxiv:2745", "title": "Probabilistic Latent Semantic Analysis", "text": "Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which stems from linear algebra and performs a Singular Value Decomposition of co-occurrence tables, the proposed method is based on a mixture decomposition derived from a latent class model. This results in a more principled approach which has a solid foundation in statistics. In order to avoid overfitting, we propose a widely applicable generalization of maximum likelihood model fitting by tempered EM. Our approach yields substantial and consistent improvements over Latent Semantic Analysis in a number of experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2746", "title": "On Supervised Selection of Bayesian Networks", "text": "Given a set of possible models (e.g., Bayesian network structures) and a data sample, in the unsupervised model selection problem the task is to choose the most accurate model with respect to the domain joint probability distribution. In contrast to this, in supervised model selection it is a priori known that the chosen model will be used in the future for prediction tasks involving more ``focused' predictive distributions. Although focused predictive distributions can be produced from the joint probability distribution by marginalization, in practice the best model in the unsupervised sense does not necessarily perform well in supervised domains. In particular, the standard marginal likelihood score is a criterion for the unsupervised task, and, although frequently used for supervised model selection also, does not perform well in such tasks. In this paper we study the performance of the marginal likelihood score empirically in supervised Bayesian network selection tasks by using a large number of publicly available classification data sets, and compare the results to those obtained by alternative model selection criteria, including empirical crossvalidation methods, an approximation of a supervised marginal likelihood measure, and a supervised version of Dawids prequential(predictive sequential) principle.The results demonstrate that the marginal likelihood score does NOT perform well FOR supervised model selection, WHILE the best results are obtained BY using Dawids prequential r napproach.", "source": "arxiv/ml"}
{"id": "arxiv:2747", "title": "A Bayesian Network Classifier that Combines a Finite Mixture Model and a Naive Bayes Model", "text": "In this paper we present a new Bayesian network model for classification that combines the naive-Bayes (NB) classifier and the finite-mixture (FM) classifier. The resulting classifier aims at relaxing the strong assumptions on which the two component models are based, in an attempt to improve on their classification performance, both in terms of accuracy and in terms of calibration of the estimated probabilities. The proposed classifier is obtained by superimposing a finite mixture model on the set of feature variables of a naive Bayes model. We present experimental results that compare the predictive performance on real datasets of the new classifier with the predictive performance of the NB classifier and the FM classifier.", "source": "arxiv/ml"}
{"id": "arxiv:2748", "title": "A Variational Approximation for Bayesian Networks with Discrete and Continuous Latent Variables", "text": "We show how to use a variational approximation to the logistic function to perform approximate inference in Bayesian networks containing discrete nodes with continuous parents. Essentially, we convert the logistic function to a Gaussian, which facilitates exact inference, and then iteratively adjust the variational parameters to improve the quality of the approximation. We demonstrate experimentally that this approximation is faster and potentially more accurate than sampling. We also introduce a simple new technique for handling evidence, which allows us to handle arbitrary distributions on observed nodes, as well as achieving a significant speedup in networks with discrete variables of large cardinality.", "source": "arxiv/ml"}
{"id": "arxiv:2749", "title": "Loopy Belief Propagation for Approximate Inference: An Empirical Study", "text": "Recently, researchers have demonstrated that loopy belief propagation - the use of Pearls polytree algorithm IN a Bayesian network WITH loops OF error- correcting codes.The most dramatic instance OF this IS the near Shannon - limit performance OF Turbo Codes codes whose decoding algorithm IS equivalent TO loopy belief propagation IN a chain - structured Bayesian network. IN this paper we ask : IS there something special about the error - correcting code context, OR does loopy propagation WORK AS an approximate inference schemeIN a more general setting? We compare the marginals computed using loopy propagation TO the exact ones IN four Bayesian network architectures, including two real - world networks : ALARM AND QMR.We find that the loopy beliefs often converge AND WHEN they do, they give a good approximation TO the correct marginals.However,ON the QMR network, the loopy beliefs oscillated AND had no obvious relationship TO the correct posteriors. We present SOME initial investigations INTO the cause OF these oscillations, AND show that SOME simple methods OF preventing them lead TO the wrong results.", "source": "arxiv/ml"}
{"id": "arxiv:2750", "title": "Learning Bayesian Networks from Incomplete Data with Stochastic Search Algorithms", "text": "This paper describes stochastic search approaches, including a new stochastic algorithm and an adaptive mutation operator, for learning Bayesian networks from incomplete data. This problem is characterized by a huge solution space with a highly multimodal landscape. State-of-the-art approaches all involve using deterministic approaches such as the expectation-maximization algorithm. These approaches are guaranteed to find local maxima, but do not explore the landscape for other modes. Our approach evolves structure and the missing data. We compare our stochastic algorithms and show they all produce accurate results.", "source": "arxiv/ml"}
{"id": "arxiv:2751", "title": "Learning Bayesian Networks with Restricted Causal Interactions", "text": "A major problem for the learning of Bayesian networks (BNs) is the exponential number of parameters needed for conditional probability tables. Recent research reduces this complexity by modeling local structure in the probability tables. We examine the use of log-linear local models. While log-linear models in this context are not new (Whittaker, 1990; Buntine, 1991; Neal, 1992; Heckerman and Meek, 1997), for structure learning they are generally subsumed under a naive Bayes model. We describe an alternative interpretation, and use a Minimum Message Length (MML) (Wallace, 1987) metric for structure learning of networks exhibiting causal independence, which we term first-order networks (FONs). We also investigate local model selection on a node-by-node basis.", "source": "arxiv/ml"}
{"id": "arxiv:2752", "title": "Accelerating EM: An Empirical Study", "text": "Many applications require that we learn the parameters of a model from data. EM is a method used to learn the parameters of probabilistic models for which the data for some of the variables in the models is either missing or hidden. There are instances in which this method is slow to converge. Therefore, several accelerations have been proposed to improve the method. None of the proposed acceleration methods are theoretically dominant and experimental comparisons are lacking. In this paper, we present the different proposed accelerations and try to compare them experimentally. From the results of the experiments, we argue that some acceleration of EM is always possible, but that which acceleration is superior depends on properties of the problem.", "source": "arxiv/ml"}
{"id": "arxiv:2753", "title": "Variational Learning in Mixed-State Dynamic Graphical Models", "text": "Many real-valued stochastic time-series are locally linear (Gassian), but globally non-linear. For example, the trajectory of a human hand gesture can be viewed as a linear dynamic system driven by a nonlinear dynamic system that represents muscle actions. We present a mixed-state dynamic graphical model in which a hidden Markov model drives a linear dynamic system. This combination allows us to model both the discrete and continuous causes of trajectories such as human gestures. The number of computations needed for exact inference is exponential in the sequence length, so we derive an approximate variational inference technique that can also be used to learn the parameters of the discrete and continuous models. We show how the mixed-state model and the variational technique can be used to classify human hand gestures made with a computer mouse.", "source": "arxiv/ml"}
{"id": "arxiv:2754", "title": "Approximate Learning in Complex Dynamic Bayesian Networks", "text": "In this paper we extend the work of Smith and Papamichail (1999) and present fast approximate Bayesian algorithms for learning in complex scenarios where at any time frame, the relationships between explanatory state space variables can be described by a Bayesian network that evolve dynamically over time and the observations taken are not necessarily Gaussian. It uses recent developments in approximate Bayesian forecasting methods in combination with more familiar Gaussian propagation algorithms on junction trees. The procedure for learning state parameters from data is given explicitly for common sampling distributions and the methodology is illustrated through a real application. The efficiency of the dynamic approximation is explored by using the Hellinger divergence measure and theoretical bounds for the efficacy of such a procedure are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2755", "title": "An alternative text representation to TF-IDF and Bag-of-Words", "text": "In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polysemy. Especially when labeled data is limited (e.g. in document classification), or the text documents are short (e.g. emails or abstracts), many features are rarely observed within the training corpus. This leads to overfitting and reduced generalization accuracy. In this paper we propose Dense Cohort of Terms (dCoT), an unsupervised algorithm to learn improved sBoW document features. dCoT explicitly models absent words by removing and reconstructing random sub-sets of words in the unlabeled corpus. With this approach, dCoT learns to reconstruct frequent words from co-occurring infrequent words and maps the high dimensional sparse sBoW vectors into a low-dimensional dense representation. We show that the feature removal can be marginalized out and that the reconstruction can be solved for in closed-form. We demonstrate empirically, on several benchmark datasets, that dCoT features significantly improve the classification accuracy across several document classification tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2756", "title": "Guarantees of Total Variation Minimization for Signal Recovery", "text": "In this paper, we consider using total variation minimization to recover signals whose gradients have a sparse support, from a small number of measurements. We establish the proof for the performance guarantee of total variation (TV) minimization in recovering \\emph{one-dimensional} signal with sparse gradient support. This partially answers the open problem of proving the fidelity of total variation minimization in such a setting \\cite{TVMulti}. In particular, we have shown that the recoverable gradient sparsity can grow linearly with the signal dimension when TV minimization is used. Recoverable sparsity thresholds of TV minimization are explicitly computed for 1-dimensional signal by using the Grassmann angle framework. We also extend our results to TV minimization for multidimensional signals. Stability of recovering signal itself using 1-D TV minimization has also been established through a property called \"almost Euclidean property for 1-dimensional TV norm\". We further give a lower bound on the number of random Gaussian measurements for recovering 1-dimensional signal vectors with $N$ elements and $K$-sparse gradients. Interestingly, the number of needed measurements is lower bounded by $\\Omega((NK)^{\\frac{1}{2}})$, rather than the $O(K\\log(N/K))$ bound frequently appearing in recovering $K$-sparse signal vectors.", "source": "arxiv/ml"}
{"id": "arxiv:2757", "title": "Multi-Step Regression Learning for Compositional Distributional Semantics", "text": "We present a model for compositional distributional semantics related to the framework of Coecke et al. (2010), and emulating formal semantics by representing functions as tensors and arguments as vectors. We introduce a new learning method for tensors, generalising the approach of Baroni and Zamparelli (2010). We evaluate it on two benchmark data sets, and find it to outperform existing leading methods. We argue in our analysis that the nature of this learning method also renders it suitable for solving more subtle problems compositional distributional models might face.", "source": "arxiv/ml"}
{"id": "arxiv:2758", "title": "On the Consistency of the Bootstrap Approach for Support Vector Machines and Related Kernel Based Methods", "text": "It is shown that bootstrap approximations of support vector machines (SVMs) based on a general convex and smooth loss function and on a general kernel are consistent. This result is useful to approximate the unknown finite sample distribution of SVMs by the bootstrap approach.", "source": "arxiv/ml"}
{"id": "arxiv:2759", "title": "Link prediction for partially observed networks", "text": "Link prediction is one of the fundamental problems in network analysis. In many applications, notably in genetics, a partially observed network may not contain any negative examples of absent edges, which creates a difficulty for many existing supervised learning approaches. We develop a new method which treats the observed network as a sample of the true network with different sampling rates for positive and negative examples. We obtain a relative ranking of potential links by their probabilities, utilizing information on node covariates as well as on network topology. Empirically, the method performs well under many settings, including when the observed network is sparse. We apply the method to a protein-protein interaction network and a school friendship network.", "source": "arxiv/ml"}
{"id": "arxiv:2760", "title": "Empirical Analysis of Predictive Algorithms for Collaborative Filtering", "text": "Collaborative filtering or recommender systems use a database about user preferences to predict additional topics or products a new user might like. In this paper we describe several algorithms designed for this task, including techniques based on correlation coefficients, vector-based similarity calculations, and statistical Bayesian methods. We compare the predictive accuracy of the various methods in a set of representative problem domains. We use two basic classes of evaluation metrics. The first characterizes accuracy over a set of individual predictions in terms of average absolute deviation. The second estimates the utility of a ranked list of suggested items. This metric uses an estimate of the probability that a user will see a recommendation in an ordered list. Experiments were run for datasets associated with 3 application areas, 4 experimental protocols, and the 2 evaluation metrics for the various algorithms. Results indicate that for a wide range of conditions, Bayesian networks with decision trees at each node and correlation methods outperform Bayesian-clustering and vector-similarity methods. Between correlation and Bayesian networks, the preferred method depends on the nature of the dataset, nature of the application (ranked versus one-by-one presentation), and the availability of votes with which to make predictions. Other considerations include the size of database, speed of predictions, and learning time.", "source": "arxiv/ml"}
{"id": "arxiv:2761", "title": "The Bayesian Structural EM Algorithm", "text": "In recent years there has been a flurry of works on learning Bayesian networks from data. One of the hard problems in this area is how to effectively learn the structure of a belief network from incomplete data- that is, in the presence of missing values or hidden variables. In a recent paper, I introduced an algorithm called Structural EM that combines the standard Expectation Maximization (EM) algorithm, which optimizes parameters, with structure search for model selection. That algorithm learns networks based on penalized likelihood scores, which include the BIC/MDL score and various approximations to the Bayesian score. In this paper, I extend Structural EM to deal directly with Bayesian model selection. I prove the convergence of the resulting algorithm and show how to apply it for learning a large class of probabilistic models, including Bayesian networks and some variants thereof.", "source": "arxiv/ml"}
{"id": "arxiv:2762", "title": "Learning the Structure of Dynamic Probabilistic Networks", "text": "Dynamic probabilistic networks are a compact representation of complex stochastic processes. In this paper we examine how to learn the structure of a DPN from data. We extend structure scoring rules for standard probabilistic networks to the dynamic case, and show how to search for structure when some of the variables are hidden. Finally, we examine two applications where such a technology might be useful: predicting and classifying dynamic behaviors, and learning causal orderings in biological processes. We provide empirical results that demonstrate the applicability of our methods in both domains.", "source": "arxiv/ml"}
{"id": "arxiv:2763", "title": "Learning by Transduction", "text": "We describe a method for predicting a classification of an object given classifications of the objects in the training set, assuming that the pairs object/classification are generated by an i.i.d. process from a continuous probability distribution. Our method is a modification of Vapnik's support-vector machine; its main novelty is that it gives not only the prediction itself but also a practicable measure of the evidence found in support of that prediction. We also describe a procedure for assigning degrees of confidence to predictions made by the support vector machine. Some experimental results are presented, and possible extensions of the algorithms are discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2764", "title": "Graphical Models and Exponential Families", "text": "We provide a classification of graphical models according to their representation as subfamilies of exponential families. Undirected graphical models with no hidden variables are linear exponential families (LEFs), directed acyclic graphical models and chain graphs with no hidden variables, including Bayesian networks with several families of local distributions, are curved exponential families (CEFs) and graphical models with hidden variables are stratified exponential families (SEFs). An SEF is a finite union of CEFs satisfying a frontier condition. In addition, we illustrate how one can automatically generate independence and non-independence constraints on the distributions over the observable variables implied by a Bayesian network with hidden variables. The relevance of these results for model selection is examined.", "source": "arxiv/ml"}
{"id": "arxiv:2765", "title": "Minimum Encoding Approaches for Predictive Modeling", "text": "We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we present two revised versions of MML: a pointwise estimator which gives the MML-optimal single parameter model, and a volumewise estimator which gives the MML-optimal region in the parameter space. Our empirical results suggest that with small data sets, the MDL approach yields more accurate predictions than the MML estimators. The empirical results also demonstrate that the revised MML estimators introduced here perform better than the original MML estimator suggested by Wallace and Freeman.", "source": "arxiv/ml"}
{"id": "arxiv:2766", "title": "Hierarchical Mixtures-of-Experts for Exponential Family Regression Models with Generalized Linear Mean Functions: A Survey of Approximation and Consistency Results", "text": "We investigate a class of hierarchical mixtures-of-experts (HME) models where exponential family regression models with generalized linear mean functions of the form psi(ga+fx^Tfgb) are mixed. Here psi(...) is the inverse link function. Suppose the true response y follows an exponential family regression model with mean function belonging to a class of smooth functions of the form psi(h(fx)) where h(...)in W_2^infty (a Sobolev class over [0,1]^{s}). It is shown that the HME probability density functions can approximate the true density, at a rate of O(m^{-2/s}) in L_p norm, and at a rate of O(m^{-4/s}) in Kullback-Leibler divergence. These rates can be achieved within the family of HME structures with no more than s-layers, where s is the dimension of the predictor fx. It is also shown that likelihood-based inference based on HME is consistent in recovering the truth, in the sense that as the sample size n and the number of experts m both increase, the mean square error of the predicted mean response goes to zero. Conditions for such results to hold are stated and discussed.", "source": "arxiv/ml"}
{"id": "arxiv:2767", "title": "Large Deviation Methods for Approximate Probabilistic Inference", "text": "We study two-layer belief networks of binary random variables in which the conditional probabilities Pr[childlparents] depend monotonically on weighted sums of the parents. In large networks where exact probabilistic inference is intractable, we show how to compute upper and lower bounds on many probabilities of interest. In particular, using methods from large deviation theory, we derive rigorous bounds on marginal probabilities such as Pr[children] and prove rates of convergence for the accuracy of our bounds as a function of network size. Our results apply to networks with generic transfer function parameterizations of the conditional probability tables, such as sigmoid and noisy-OR. They also explicitly illustrate the types of averaging behavior that can simplify the problem of inference in large networks.", "source": "arxiv/ml"}
{"id": "arxiv:2768", "title": "Mixture Representations for Inference and Learning in Boltzmann Machines", "text": "Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states. They have been widely studied in the neural computing literature, although their practical applicability has been limited by the difficulty of finding an effective learning algorithm. One well-established approach, known as mean field theory, represents the stochastic distribution using a factorized approximation. However, the corresponding learning algorithm often fails to find a good solution. We conjecture that this is due to the implicit uni-modality of the mean field approximation which is therefore unable to capture multi-modality in the true distribution. In this paper we use variational methods to approximate the stochastic distribution using multi-modal mixtures of factorized distributions. We present results for both inference and learning to demonstrate the effectiveness of this approach.", "source": "arxiv/ml"}
{"id": "arxiv:2769", "title": "An Experimental Comparison of Several Clustering and Initialization Methods", "text": "We examine methods for clustering in high dimensions. In the first part of the paper, we perform an experimental comparison between three batch clustering algorithms: the Expectation-Maximization (EM) algorithm, a winner take all version of the EM algorithm reminiscent of the K-means algorithm, and model-based hierarchical agglomerative clustering. We learn naive-Bayes models with a hidden root node, using high-dimensional discrete-variable data sets (both real and synthetic). We find that the EM algorithm significantly outperforms the other methods, and proceed to investigate the effect of various initialization schemes on the final solution produced by the EM algorithm. The initializations that we consider are (1) parameters sampled from an uninformative prior, (2) random perturbations of the marginal distribution of the data, and (3) the output of hierarchical agglomerative clustering. Although the methods are substantially different, they lead to learned models that are strikingly similar in quality.", "source": "arxiv/ml"}
{"id": "arxiv:2770", "title": "A Multivariate Discretization Method for Learning Bayesian Networks from Mixed Data", "text": "In this paper we address the problem of discretization in the context of learning Bayesian networks (BNs) from data containing both continuous and discrete variables. We describe a new technique for <EM>multivariate</EM> discretization, whereby each continuous variable is discretized while taking into account its interaction with the other variables. The technique is based on the use of a Bayesian scoring metric that scores the discretization policy for a continuous variable given a BN structure and the observed data. Since the metric is relative to the BN structure currently being evaluated, the discretization of a variable needs to be dynamically adjusted as the BN structure changes.", "source": "arxiv/ml"}
{"id": "arxiv:2771", "title": "On the Geometry of Bayesian Graphical Models with Hidden Variables", "text": "In this paper we investigate the geometry of the likelihood of the unknown parameters in a simple class of Bayesian directed graphs with hidden variables. This enables us, before any numerical algorithms are employed, to obtain certain insights in the nature of the unidentifiability inherent in such models, the way posterior densities will be sensitive to prior densities and the typical geometrical form these posterior densities might take. Many of these insights carry over into more complicated Bayesian networks with systematic missing data.", "source": "arxiv/ml"}
{"id": "arxiv:2772", "title": "Learning Mixtures of DAG Models", "text": "We describe computationally efficient methods for learning mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs). We argue that simple search-and-score algorithms are infeasible for a variety of problems, and introduce a feasible approach in which parameter and structure search is interleaved and expected data is treated as real data. Our approach can be viewed as a combination of (1) the Cheeseman--Stutz asymptotic approximation for model posterior probability and (2) the Expectation--Maximization algorithm. We evaluate our procedure for selecting among MDAGs on synthetic and real examples.", "source": "arxiv/ml"}
{"id": "arxiv:2773", "title": "Information driven self-organization of complex robotic behaviors", "text": "Information theory is a powerful tool to express principles to drive autonomous systems because it is domain invariant and allows for an intuitive interpretation. This paper studies the use of the predictive information (PI), also called excess entropy or effective measure complexity, of the sensorimotor process as a driving force to generate behavior. We study nonlinear and nonstationary systems and introduce the time-local predicting information (TiPI) which allows us to derive exact results together with explicit update rules for the parameters of the controller in the dynamical systems framework. In this way the information principle, formulated at the level of behavior, is translated to the dynamics of the synapses. We underpin our results with a number of case studies with high-dimensional robotic systems. We show the spontaneous cooperativity in a complex physical system with decentralized control. Moreover, a jointly controlled humanoid robot develops a high behavioral variety depending on its physics and the environment it is dynamically embedded into. The behavior can be decomposed into a succession of low-dimensional modes that increasingly explore the behavior space. This is a promising way to avoid the curse of dimensionality which hinders learning systems to scale well.", "source": "arxiv/ml"}
{"id": "arxiv:2774", "title": "Rank regularization and Bayesian inference for tensor completion and extrapolation", "text": "A novel regularizer of the PARAFAC decomposition factors capturing the tensor's rank is proposed in this paper, as the key enabler for completion of three-way data arrays with missing entries. Set in a Bayesian framework, the tensor completion method incorporates prior information to enhance its smoothing and prediction capabilities. This probabilistic approach can naturally accommodate general models for the data distribution, lending itself to various fitting criteria that yield optimum estimates in the maximum-a-posteriori sense. In particular, two algorithms are devised for Gaussian- and Poisson-distributed data, that minimize the rank-regularized least-squares error and Kullback-Leibler divergence, respectively. The proposed technique is able to recover the \"ground-truth'' tensor rank when tested on synthetic data, and to complete brain imaging and yeast gene expression datasets with 50% and 15% of missing entries respectively, resulting in recovery errors at -10dB and -15dB.", "source": "arxiv/ml"}
{"id": "arxiv:2775", "title": "Axiomatic Construction of Hierarchical Clustering in Asymmetric Networks", "text": "This paper considers networks where relationships between nodes are represented by directed dissimilarities. The goal is to study methods for the determination of hierarchical clusters, i.e., a family of nested partitions indexed by a connectivity parameter, induced by the given dissimilarity structures. Our construction of hierarchical clustering methods is based on defining admissible methods to be those methods that abide by the axioms of value - nodes in a network with two nodes are clustered together at the maximum of the two dissimilarities between them - and transformation - when dissimilarities are reduced, the network may become more clustered but not less. Several admissible methods are constructed and two particular methods, termed reciprocal and nonreciprocal clustering, are shown to provide upper and lower bounds in the space of admissible methods. Alternative clustering methodologies and axioms are further considered. Allowing the outcome of hierarchical clustering to be asymmetric, so that it matches the asymmetry of the original data, leads to the inception of quasi-clustering methods. The existence of a unique quasi-clustering method is shown. Allowing clustering in a two-node network to proceed at the minimum of the two dissimilarities generates an alternative axiomatic construction. There is a unique clustering method in this case too. The paper also develops algorithms for the computation of hierarchical clusters using matrix powers on a min-max dioid algebra and studies the stability of the methods proposed. We proved that most of the methods introduced in this paper are such that similar networks yield similar hierarchical clustering results. Algorithms are exemplified through their application to networks describing internal migration within states of the United States (U.S.) and the interrelation between sectors of the U.S. economy.", "source": "arxiv/ml"}
{"id": "arxiv:2776", "title": "Distribution-Free Distribution Regression", "text": "`Distribution regression' refers to the situation where a response Y depends on a covariate P where P is a probability distribution. The model is Y=f(P) + mu where f is an unknown regression function and mu is a random error. Typically, we do not observe P directly, but rather, we observe a sample from P. In this paper we develop theory and methods for distribution-free versions of distribution regression. This means that we do not make distributional assumptions about the error term mu and covariate P. We prove that when the effective dimension is small enough (as measured by the doubling dimension), then the excess prediction risk converges to zero with a polynomial rate.", "source": "arxiv/ml"}
{"id": "arxiv:2777", "title": "Sparse Multiple Kernel Learning with Geometric Convergence Rate", "text": "In this paper, we study the problem of sparse multiple kernel learning (MKL), where the goal is to efficiently learn a combination of a fixed small number of kernels from a large pool that could lead to a kernel classifier with a small prediction error. We develop an efficient algorithm based on the greedy coordinate descent algorithm, that is able to achieve a geometric convergence rate under appropriate conditions. The convergence rate is achieved by measuring the size of functional gradients by an empirical $\\ell_2$ norm that depends on the empirical data distribution. This is in contrast to previous algorithms that use a functional norm to measure the size of gradients, which is independent from the data samples. We also establish a generalization error bound of the learned sparse kernel classifier using the technique of local Rademacher complexity.", "source": "arxiv/ml"}
{"id": "arxiv:2778", "title": "Fast Damage Recovery in Robotics with the T-Resilience Algorithm", "text": "Damage recovery is critical for autonomous robots that need to operate for a long time without assistance. Most current methods are complex and costly because they require anticipating each potential damage in order to have a contingency plan ready. As an alternative, we introduce the T-resilience algorithm, a new algorithm that allows robots to quickly and autonomously discover compensatory behaviors in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behaviors by learning to avoid those that perform differently in the self-model and in reality. Our algorithm thus does not identify the damaged parts but it implicitly searches for efficient behaviors that do not use them. We evaluate the T-Resilience algorithm on a hexapod robot that needs to adapt to leg removal, broken legs and motor failures; we compare it to stochastic local search, policy gradient and the self-modeling algorithm proposed by Bongard et al. The behavior of the robot is assessed on-board thanks to a RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 minutes, T-Resilience consistently leads to substantially better results than the other approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2779", "title": "Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning", "text": "We present generalization bounds for the TS-MKL framework for two stage multiple kernel learning. We also present bounds for sparse kernel learning formulations within the TS-MKL framework.", "source": "arxiv/ml"}
{"id": "arxiv:2780", "title": "Parallel D2-Clustering: Large-Scale Clustering of Discrete Distributions", "text": "The discrete distribution clustering algorithm, namely D2-clustering, has demonstrated its usefulness in image classification and annotation where each object is represented by a bag of weighed vectors. The high computational complexity of the algorithm, however, limits its applications to large-scale problems. We present a parallel D2-clustering algorithm with substantially improved scalability. A hierarchical structure for parallel computing is devised to achieve a balance between the individual-node computation and the integration process of the algorithm. Additionally, it is shown that even with a single CPU, the hierarchical structure results in significant speed-up. Experiments on real-world large-scale image data, Youtube video data, and protein sequence data demonstrate the efficiency and wide applicability of the parallel D2-clustering algorithm. The loss in clustering accuracy is minor in comparison with the original sequential algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2781", "title": "A game-theoretic framework for classifier ensembles using weighted majority voting with local accuracy estimates", "text": "In this paper, a novel approach for the optimal combination of binary classifiers is proposed. The classifier combination problem is approached from a Game Theory perspective. The proposed framework of adapted weighted majority rules (WMR) is tested against common rank-based, Bayesian and simple majority models, as well as two soft-output averaging rules. Experiments with ensembles of Support Vector Machines (SVM), Ordinary Binary Tree Classifiers (OBTC) and weighted k-nearest-neighbor (w/k-NN) models on benchmark datasets indicate that this new adaptive WMR model, employing local accuracy estimators and the analytically computed optimal weights outperform all the other simple combination rules.", "source": "arxiv/ml"}
{"id": "arxiv:2782", "title": "Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithms", "text": "A key problem of robotic environmental sensing and monitoring is that of active sensing: How can a team of robots plan the most informative observation paths to minimize the uncertainty in modeling and predicting an environmental phenomenon? This paper presents two principled approaches to efficient information-theoretic path planning based on entropy and mutual information criteria for in situ active sensing of an important broad class of widely-occurring environmental phenomena called anisotropic fields. Our proposed algorithms are novel in addressing a trade-off between active sensing performance and time efficiency. An important practical consequence is that our algorithms can exploit the spatial correlation structure of Gaussian process-based anisotropic fields to improve time efficiency while preserving near-optimal active sensing performance. We analyze the time complexity of our algorithms and prove analytically that they scale better than state-of-the-art algorithms with increasing planning horizon length. We provide theoretical guarantees on the active sensing performance of our algorithms for a class of exploration tasks called transect sampling, which, in particular, can be improved with longer planning time and/or lower spatial correlation along the transect. Empirical evaluation on real-world anisotropic field data shows that our algorithms can perform better or at least as well as the state-of-the-art algorithms while often incurring a few orders of magnitude less computational time, even when the field conditions are less favorable.", "source": "arxiv/ml"}
{"id": "arxiv:2783", "title": "Exact Sparse Recovery with L0 Projections", "text": "Many applications concern sparse signals, for example, detecting anomalies from the differences between consecutive images taken by surveillance cameras. This paper focuses on the problem of recovering a K-sparse signal x in N dimensions. In the mainstream framework of compressed sensing (CS), the vector x is recovered from M non-adaptive linear measurements y = xS, where S (of size N x M) is typically a Gaussian (or Gaussian-like) design matrix, through some optimization procedure such as linear programming (LP). In our proposed method, the design matrix S is generated from an $\\alpha$-stable distribution with $\\alpha\\approx 0$. Our decoding algorithm mainly requires one linear scan of the coordinates, followed by a few iterations on a small number of coordinates which are \"undetermined\" in the previous iteration. Comparisons with two strong baselines, linear programming (LP) and orthogonal matching pursuit (OMP), demonstrate that our algorithm can be significantly faster in decoding speed and more accurate in recovery quality, for the task of exact spare recovery. Our procedure is robust against measurement noise. Even when there are no sufficient measurements, our algorithm can still reliably recover a significant portion of the nonzero coordinates. To provide the intuition for understanding our method, we also analyze the procedure by assuming an idealistic setting. Interestingly, when K=2, the \"idealized\" algorithm achieves exact recovery with merely 3 measurements, regardless of N. For general K, the required sample size of the \"idealized\" algorithm is about 5K.", "source": "arxiv/ml"}
{"id": "arxiv:2784", "title": "Improved Accuracy of PSO and DE using Normalization: an Application to Stock Price Prediction", "text": "Data Mining is being actively applied to stock market since 1980s. It has been used to predict stock prices, stock indexes, for portfolio management, trend detection and for developing recommender systems. The various algorithms which have been used for the same include ANN, SVM, ARIMA, GARCH etc. Different hybrid models have been developed by combining these algorithms with other algorithms like roughest, fuzzy logic, GA, PSO, DE, ACO etc. to improve the efficiency. This paper proposes DE-SVM model (Differential EvolutionSupport vector Machine) for stock price prediction. DE has been used to select best free parameters combination for SVM to improve results. The paper also compares the results of prediction with the outputs of SVM alone and PSO-SVM model (Particle Swarm Optimization). The effect of normalization of data on the accuracy of prediction has also been studied.", "source": "arxiv/ml"}
{"id": "arxiv:2785", "title": "RandomBoost: Simplified Multi-class Boosting through Randomization", "text": "We propose a novel boosting approach to multi-class classification problems, in which multiple classes are distinguished by a set of random projection matrices in essence. The approach uses random projections to alleviate the proliferation of binary classifiers typically required to perform multi-class classification. The result is a multi-class classifier with a single vector-valued parameter, irrespective of the number of classes involved. Two variants of this approach are proposed. The first method randomly projects the original data into new spaces, while the second method randomly projects the outputs of learned weak classifiers. These methods are not only conceptually simple but also effective and easy to implement. A series of experiments on synthetic, machine learning and visual recognition data sets demonstrate that our proposed methods compare favorably to existing multi-class boosting algorithms in terms of both the convergence rate and classification accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2786", "title": "A Comparison of Relaxations of Multiset Cannonical Correlation Analysis and Applications", "text": "Canonical correlation analysis is a statistical technique that is used to find relations between two sets of variables. An important extension in pattern analysis is to consider more than two sets of variables. This problem can be expressed as a quadratically constrained quadratic program (QCQP), commonly referred to Multi-set Canonical Correlation Analysis (MCCA). This is a non-convex problem and so greedy algorithms converge to local optima without any guarantees on global optimality. In this paper, we show that despite being highly structured, finding the optimal solution is NP-Hard. This motivates our relaxation of the QCQP to a semidefinite program (SDP). The SDP is convex, can be solved reasonably efficiently and comes with both absolute and output-sensitive approximation quality. In addition to theoretical guarantees, we do an extensive comparison of the QCQP method and the SDP relaxation on a variety of synthetic and real world data. Finally, we present two useful extensions: we incorporate kernel methods and computing multiple sets of canonical vectors.", "source": "arxiv/ml"}
{"id": "arxiv:2787", "title": "The price of bandit information in multiclass online classification", "text": "We consider two scenarios of multiclass online learning of a hypothesis class $H\\subseteq Y^X$. In the {\\em full information} scenario, the learner is exposed to instances together with their labels. In the {\\em bandit} scenario, the true label is not exposed, but rather an indication whether the learner's prediction is correct or not. We show that the ratio between the error rates in the two scenarios is at most $8\\cdot|Y|\\cdot \\log(|Y|)$ in the realizable case, and $\\tilde{O}(\\sqrt{|Y|})$ in the agnostic case. The results are tight up to a logarithmic factor and essentially answer an open question from (Daniely et. al. - Multiclass learnability and the erm principle). We apply these results to the class of $\\gamma$-margin multiclass linear classifiers in $\\reals^d$. We show that the bandit error rate of this class is $\\tilde{\\Theta}(\\frac{|Y|}{\\gamma^2})$ in the realizable case and $\\tilde{\\Theta}(\\frac{1}{\\gamma}\\sqrt{|Y|T})$ in the agnostic case. This resolves an open question from (Kakade et. al. - Efficient bandit algorithms for online multiclass prediction).", "source": "arxiv/ml"}
{"id": "arxiv:2788", "title": "When are the most informative components for inference also the principal components?", "text": "Which components of the singular value decomposition of a signal-plus-noise data matrix are most informative for the inferential task of detecting or estimating an embedded low-rank signal matrix? Principal component analysis ascribes greater importance to the components that capture the greatest variation, i.e., the singular vectors associated with the largest singular values. This choice is often justified by invoking the Eckart-Young theorem even though that work addresses the problem of how to best represent a signal-plus-noise matrix using a low-rank approximation and not how to best_infer_ the underlying low-rank signal component. Here we take a first-principles approach in which we start with a signal-plus-noise data matrix and show how the spectrum of the noise-only component governs whether the principal or the middle components of the singular value decomposition of the data matrix will be the informative components for inference. Simply put, if the noise spectrum is supported on a connected interval, in a sense we make precise, then the use of the principal components is justified. When the noise spectrum is supported on multiple intervals, then the middle components might be more informative than the principal components. The end result is a proper justification of the use of principal components in the setting where the noise matrix is i.i.d. Gaussian and the identification of scenarios, generically involving heterogeneous noise models such as mixtures of Gaussians, where the middle components might be more informative than the principal components so that they may be exploited to extract additional processing gain. Our results show how the blind use of principal components can lead to suboptimal or even faulty inference because of phase transitions that separate a regime where the principal components are informative from a regime where they are uninformative.", "source": "arxiv/ml"}
{"id": "arxiv:2789", "title": "A Polynomial Time Algorithm for Lossy Population Recovery", "text": "We give a polynomial time algorithm for the lossy population recovery problem. In this problem, the goal is to approximately learn an unknown distribution on binary strings of length $n$ from lossy samples: for some parameter $\\mu$ each coordinate of the sample is preserved with probability $\\mu$ and otherwise is replaced by a `?'. The running time and number of samples needed for our algorithm is polynomial in $n$ and $1/\\varepsilon$ for each fixed $\\mu>0$. This improves on algorithm of Wigderson and Yehudayoff that runs in quasi-polynomial time for any $\\mu > 0$ and the polynomial time algorithm of Dvir et al which was shown to work for $\\mu \\gtrapprox 0.30$ by Batman et al. In fact, our algorithm also works in the more general framework of Batman et al. in which there is no a priori bound on the size of the support of the distribution. The algorithm we analyze is implicit in previous work; our main contribution is to analyze the algorithm by showing (via linear programming duality and connections to complex analysis) that a certain matrix associated with the problem has a robust local inverse even though its condition number is exponentially small. A corollary of our result is the first polynomial time algorithm for learning DNFs in the restriction access model of Dvir et al.", "source": "arxiv/ml"}
{"id": "arxiv:2790", "title": "Update Rules for Parameter Estimation in Bayesian Networks", "text": "This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [Kivinen & Warmuth, 1994]. We provide a unified framework for parameter estimation that encompasses both on-line learning, where the model is continuously adapted to new data cases as they arrive, and the more traditional batch learning, where a pre-accumulated set of samples is used in a one-time model selection process. In the batch case, our framework encompasses both the gradient projection algorithm and the EM algorithm for Bayesian networks. The framework also leads to new on-line and batch parameter update schemes, including a parameterized version of EM. We provide both empirical and theoretical results indicating that parameterized EM allows faster convergence to the maximum likelihood parameters than does standard EM.", "source": "arxiv/ml"}
{"id": "arxiv:2791", "title": "A Bayesian Approach to Learning Bayesian Networks with Local Structure", "text": "Recently several researchers have investigated techniques for using data to learn Bayesian networks containing compact representations for the conditional probability distributions (CPDs) stored at each node. The majority of this work has concentrated on using decision-tree representations for the CPDs. In addition, researchers typically apply non-Bayesian (or asymptotically Bayesian) scoring functions such as MDL to evaluate the goodness-of-fit of networks to the data. In this paper we investigate a Bayesian approach to learning Bayesian networks that contain the more general decision-graph representations of the CPDs. First, we describe how to evaluate the posterior probability that is, the Bayesian score of such a network, given a database of observed cases. Second, we describe various search spaces that can be used, in conjunction with a scoring function and a search procedure, to identify one or more high-scoring networks. Finally, we present an experimental evaluation of the search spaces, using a greedy algorithm and a Bayesian scoring function.", "source": "arxiv/ml"}
{"id": "arxiv:2792", "title": "Exploring Parallelism in Learning Belief Networks", "text": "It has been shown that a class of probabilistic domain models cannot be learned correctly by several existing algorithms which employ a single-link look ahead search. When a multi-link look ahead search is used, the computational complexity of the learning algorithm increases. We study how to use parallelism to tackle the increased complexity in learning such models and to speed up learning in large domains. An algorithm is proposed to decompose the learning task for parallel processing. A further task decomposition is used to balance load among processors and to increase the speed-up and efficiency. For learning from very large datasets, we present a regrouping of the available processors such that slow data access through file can be replaced by fast memory access. Our implementation in a parallel computer demonstrates the effectiveness of the algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2793", "title": "Sequential Update of Bayesian Network Structure", "text": "There is an obvious need for improving the performance and accuracy of a Bayesian network as new data is observed. Because of errors in model construction and changes in the dynamics of the domains, we cannot afford to ignore the information in new data. While sequential update of parameters for a fixed structure can be accomplished using standard techniques, sequential update of network structure is still an open problem. In this paper, we investigate sequential update of Bayesian networks were both parameters and structure are expected to change. We introduce a new approach that allows for the flexible manipulation of the tradeoff between the quality of the learned networks and the amount of information that is maintained about past observations. We formally describe our approach including the necessary modifications to the scoring functions for learning Bayesian networks, evaluate its effectiveness through an empirical study, and extend it to the case of missing data.", "source": "arxiv/ml"}
{"id": "arxiv:2794", "title": "Learning Bayesian Nets that Perform Well", "text": "A Bayesian net (BN) is more than a succinct way to encode a probabilistic distribution; it also corresponds to a function used to answer queries. A BN can therefore be evaluated by the accuracy of the answers it returns. Many algorithms for learning BNs, however, attempt to optimize another criterion (usually likelihood, possibly augmented with a regularizing term), which is independent of the distribution of queries that are posed. This paper takes the \"performance criteria\" seriously, and considers the challenge of computing the BN whose performance - read \"accuracy over the distribution of queries\" - is optimal. We show that many aspects of this learning task are more difficult than the corresponding subtasks in the standard model.", "source": "arxiv/ml"}
{"id": "arxiv:2795", "title": "Models and Selection Criteria for Regression and Classification", "text": "When performing regression or classification, we are interested in the conditional probability distribution for an outcome or class variable Y given a set of explanatoryor input variables X. We consider Bayesian models for this task. In particular, we examine a special class of models, which we call Bayesian regression/classification (BRC) models, that can be factored into independent conditional (y|x) and input (x) models. These models are convenient, because the conditional model (the portion of the full model that we care about) can be analyzed by itself. We examine the practice of transforming arbitrary Bayesian models to BRC models, and argue that this practice is often inappropriate because it ignores prior knowledge that may be important for learning. In addition, we examine Bayesian methods for learning models from data. We discuss two criteria for Bayesian model selection that are appropriate for repression/classification: one described by Spiegelhalter et al. (1993), and another by Buntine (1993). We contrast these two criteria using the prequential framework of Dawid (1984), and give sufficient conditions under which the criteria agree.", "source": "arxiv/ml"}
{"id": "arxiv:2796", "title": "Learning Belief Networks in Domains with Recursively Embedded Pseudo Independent Submodels", "text": "A pseudo independent (PI) model is a probabilistic domain model (PDM) where proper subsets of a set of collectively dependent variables display marginal independence. PI models cannot be learned correctly by many algorithms that rely on a single link search. Earlier work on learning PI models has suggested a straightforward multi-link search algorithm. However, when a domain contains recursively embedded PI submodels, it may escape the detection of such an algorithm. In this paper, we propose an improved algorithm that ensures the learning of all embedded PI submodels whose sizes are upper bounded by a predetermined parameter. We show that this improved learning capability only increases the complexity slightly beyond that of the previous algorithm. The performance of the new algorithm is demonstrated through experiment.", "source": "arxiv/ml"}
{"id": "arxiv:2797", "title": "An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering", "text": "Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms. In this work, we study several different methods of assignment, including the \"hard\" assignments used by K-means and the ?soft' assignments used by EM. While it is known that K-means minimizes the distortion on the data and EM maximizes the likelihood, little is known about the systematic differences of behavior between the two algorithms. Here we shed light on these differences via an information-theoretic analysis. The cornerstone of our results is a simple decomposition of the expected distortion, showing that K-means (and its extension for inferring general parametric densities from unlabeled sample data) must implicitly manage a trade-off between how similar the data assigned to each cluster are, and how the data are balanced among the clusters. How well the data are balanced is measured by the entropy of the partition defined by the hard assignments. In addition to letting us predict and verify systematic differences between K-means and EM on specific examples, the decomposition allows us to give a rather general argument showing that K ?means will consistently find densities with less \"overlap\" than EM. We also study a third natural assignment method that we call posterior assignment, that is close in spirit to the soft assignments of EM, but leads to a surprisingly different algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2798", "title": "Structure and Parameter Learning for Causal Independence and Causal Interaction Models", "text": "This paper discusses causal independence models and a generalization of these models called causal interaction models. Causal interaction models are models that have independent mechanisms where a mechanism can have several causes. In addition to introducing several particular types of causal interaction models, we show how we can apply the Bayesian approach to learning causal interaction models obtaining approximate posterior distributions for the models and obtain MAP and ML estimates for the parameters. We illustrate the approach with a simulation study of learning model posteriors.", "source": "arxiv/ml"}
{"id": "arxiv:2799", "title": "Learning Bayesian Networks from Incomplete Databases", "text": "Bayesian approaches to learn the graphical structure of Bayesian Belief Networks (BBNs) from databases share the assumption that the database is complete, that is, no entry is reported as unknown. Attempts to relax this assumption involve the use of expensive iterative methods to discriminate among different structures. This paper introduces a deterministic method to learn the graphical structure of a BBN from a possibly incomplete database. Experimental evaluations show a significant robustness of this method and a remarkable independence of its execution time from the number of missing data.", "source": "arxiv/ml"}
{"id": "arxiv:2800", "title": "Bounded regret in stochastic multi-armed bandits", "text": "We study the stochastic multi-armed bandit problem when one knows the value $\\mu^{(\\star)}$ of an optimal arm, as a well as a positive lower bound on the smallest positive gap $\\Delta$. We propose a new randomized policy that attains a regret {\\em uniformly bounded over time} in this setting. We also prove several lower bounds, which show in particular that bounded regret is not possible if one only knows $\\Delta$, and bounded regret of order $1/\\Delta$ is not possible if one only knows $\\mu^{(\\star)}$", "source": "arxiv/ml"}
{"id": "arxiv:2801", "title": "Feature Selection for Microarray Gene Expression Data using Simulated Annealing guided by the Multivariate Joint Entropy", "text": "In this work a new way to calculate the multivariate joint entropy is presented. This measure is the basis for a fast information-theoretic based evaluation of gene relevance in a Microarray Gene Expression data context. Its low complexity is based on the reuse of previous computations to calculate current feature relevance. The mu-TAFS algorithm --named as such to differentiate it from previous TAFS algorithms-- implements a simulated annealing technique specially designed for feature subset selection. The algorithm is applied to the maximization of gene subset relevance in several public-domain microarray data sets. The experimental results show a notoriously high classification performance and low size subsets formed by biologically meaningful genes.", "source": "arxiv/ml"}
{"id": "arxiv:2802", "title": "An ANN-based Method for Detecting Vocal Fold Pathology", "text": "There are different algorithms for vocal fold pathology diagnosis. These algorithms usually have three stages which are Feature Extraction, Feature Reduction and Classification. While the third stage implies a choice of a variety of machine learning methods, the first and second stages play a critical role in performance and accuracy of the classification system. In this paper we present initial study of feature extraction and feature reduction in the task of vocal fold pathology diagnosis. A new type of feature vector, based on wavelet packet decomposition and Mel-Frequency-Cepstral-Coefficients (MFCCs), is proposed. Also Principal Component Analysis (PCA) is used for feature reduction. An Artificial Neural Network is used as a classifier for evaluating the performance of our proposed method.", "source": "arxiv/ml"}
{"id": "arxiv:2803", "title": "Passive Learning with Target Risk", "text": "In this paper we consider learning in passive setting but with a slight modification. We assume that the target expected loss, also referred to as target risk, is provided in advance for learner as prior knowledge. Unlike most studies in the learning theory that only incorporate the prior knowledge into the generalization bounds, we are able to explicitly utilize the target risk in the learning process. Our analysis reveals a surprising result on the sample complexity of learning: by exploiting the target risk in the learning algorithm, we show that when the loss function is both strongly convex and smooth, the sample complexity reduces to $\\O(\\log (\\frac{1}{\\epsilon}))$, an exponential improvement compared to the sample complexity $\\O(\\frac{1}{\\epsilon})$ for learning with strongly convex loss functions. Furthermore, our proof is constructive and is based on a computationally efficient stochastic optimization algorithm for such settings which demonstrate that the proposed algorithm is practically useful.", "source": "arxiv/ml"}
{"id": "arxiv:2804", "title": "Minimax Optimal Algorithms for Unconstrained Linear Optimization", "text": "We design and analyze minimax-optimal algorithms for online linear optimization games where the player's choice is unconstrained. The player strives to minimize regret, the difference between his loss and the loss of a post-hoc benchmark strategy. The standard benchmark is the loss of the best strategy chosen from a bounded comparator set. When the the comparison set and the adversary's gradients satisfy L_infinity bounds, we give the value of the game in closed form and prove it approaches sqrt(2T/pi) as T -> infinity. Interesting algorithms result when we consider soft constraints on the comparator, rather than restricting it to a bounded set. As a warmup, we analyze the game with a quadratic penalty. The value of this game is exactly T/2, and this value is achieved by perhaps the simplest online algorithm of all: unprojected gradient descent with a constant learning rate. We then derive a minimax-optimal algorithm for a much softer penalty function. This algorithm achieves good bounds under the standard notion of regret for any comparator point, without needing to specify the comparator set in advance. The value of this game converges to sqrt{e} as T ->infinity; we give a closed-form for the exact value as a function of T. The resulting algorithm is natural in unconstrained investment or betting scenarios, since it guarantees at worst constant loss, while allowing for exponential reward against an \"easy\" adversary.", "source": "arxiv/ml"}
{"id": "arxiv:2805", "title": "Learning Universally Quantified Invariants of Linear Data Structures", "text": "We propose a new automaton model, called quantified data automata over words, that can model quantified invariants over linear data structures, and build poly-time active learning algorithms for them, where the learner is allowed to query the teacher with membership and equivalence queries. In order to express invariants in decidable logics, we invent a decidable subclass of QDAs, called elastic QDAs, and prove that every QDA has a unique minimally-over-approximating elastic QDA. We then give an application of these theoretically sound and efficient active learning algorithms in a passive learning framework and show that we can efficiently learn quantified linear data structure invariants from samples obtained from dynamic runs for a large class of programs.", "source": "arxiv/ml"}
{"id": "arxiv:2806", "title": "A Time Series Forest for Classification and Feature Extraction", "text": "We propose a tree ensemble method, referred to as time series forest (TSF), for time series classification. TSF employs a combination of the entropy gain and a distance measure, referred to as the Entrance (entropy and distance) gain, for evaluating the splits. Experimental studies show that the Entrance gain criterion improves the accuracy of TSF. TSF randomly samples features at each tree node and has a computational complexity linear in the length of a time series and can be built using parallel computing techniques such as multi-core computing used here. The temporal importance curve is also proposed to capture the important temporal characteristics useful for classification. Experimental studies show that TSF using simple features such as mean, deviation and slope outperforms strong competitors such as one-nearest-neighbor classifiers with dynamic time warping, is computationally efficient, and can provide insights into the temporal characteristics.", "source": "arxiv/ml"}
{"id": "arxiv:2807", "title": "Extracting useful rules through improved decision tree induction using information entropy", "text": "Classification is widely used technique in the data mining domain, where scalability and efficiency are the immediate problems in classification algorithms for large databases. We suggest improvements to the existing C4.5 decision tree algorithm. In this paper attribute oriented induction (AOI) and relevance analysis are incorporated with concept hierarchys knowledge and HeightBalancePriority algorithm for construction of decision tree along with Multi level mining. The assignment of priorities to attributes is done by evaluating information entropy, at different levels of abstraction for building decision tree using HeightBalancePriority algorithm. Modified DMQL queries are used to understand and explore the shortcomings of the decision trees generated by C4.5 classifier for education dataset and the results are compared with the proposed approach.", "source": "arxiv/ml"}
{"id": "arxiv:2808", "title": "Online Regret Bounds for Undiscounted Continuous Reinforcement Learning", "text": "We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds for implementing optimism in the face of uncertainty. Beside the existence of an optimal policy which satisfies the Poisson equation, the only assumptions made are Holder continuity of rewards and transition probabilities.", "source": "arxiv/ml"}
{"id": "arxiv:2809", "title": "Selecting the State-Representation in Reinforcement Learning", "text": "The problem of selecting the right state-representation in a reinforcement learning problem is considered. Several models (functions mapping past observations to a finite set) of the observations are given, and it is known that for at least one of these models the resulting state dynamics are indeed Markovian. Without knowing neither which of the models is the correct one, nor what are the probabilistic characteristics of the resulting MDP, it is required to obtain as much reward as the optimal policy for the correct model (or for the best of the correct models, if there are several). We propose an algorithm that achieves that, with a regret of order T^{2/3} where T is the horizon time.", "source": "arxiv/ml"}
{"id": "arxiv:2810", "title": "Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning", "text": "We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order $O(T^{2/3})$ with an additive term constant yet exponential in some characteristics of the optimal MDP. We propose an algorithm whose regret after $T$ time steps is $O(\\sqrt{T})$, with all constants reasonably small. This is optimal in $T$ since $O(\\sqrt{T})$ is the optimal regret in the setting of learning in a (single discrete) MDP.", "source": "arxiv/ml"}
{"id": "arxiv:2811", "title": "The trace norm constrained matrix-variate Gaussian process for multitask bipartite ranking", "text": "We propose a novel hierarchical model for multitask bipartite ranking. The proposed approach combines a matrix-variate Gaussian process with a generative model for task-wise bipartite ranking. In addition, we employ a novel trace constrained variational inference approach to impose low rank structure on the posterior matrix-variate Gaussian process. The resulting posterior covariance function is derived in closed form, and the posterior mean function is the solution to a matrix-variate regression with a novel spectral elastic net regularizer. Further, we show that variational inference for the trace constrained matrix-variate Gaussian process combined with maximum likelihood parameter estimation for the bipartite ranking model is jointly convex. Our motivating application is the prioritization of candidate disease genes. The goal of this task is to aid the identification of unobserved associations between human genes and diseases using a small set of observed associations as well as kernels induced by gene-gene interaction networks and disease ontologies. Our experimental results illustrate the performance of the proposed model on real world datasets. Moreover, we find that the resulting low rank solution improves the computational scalability of training and testing as compared to baseline models.", "source": "arxiv/ml"}
{"id": "arxiv:2812", "title": "Geometrical complexity of data approximators", "text": "There are many methods developed to approximate a cloud of vectors embedded in high-dimensional space by simpler objects: starting from principal points and linear manifolds to self-organizing maps, neural gas, elastic maps, various types of principal curves and principal trees, and so on. For each type of approximators the measure of the approximator complexity was developed too. These measures are necessary to find the balance between accuracy and complexity and to define the optimal approximations of a given type. We propose a measure of complexity (geometrical complexity) which is applicable to approximators of several types and which allows comparing data approximations of different types.", "source": "arxiv/ml"}
{"id": "arxiv:2813", "title": "Latent Self-Exciting Point Process Model for Spatial-Temporal Networks", "text": "We propose a latent self-exciting point process model that describes geographically distributed interactions between pairs of entities. In contrast to most existing approaches that assume fully observable interactions, here we consider a scenario where certain interaction events lack information about participants. Instead, this information needs to be inferred from the available observations. We develop an efficient approximate algorithm based on variational expectation-maximization to infer unknown participants in an event given the location and the time of the event. We validate the model on synthetic as well as real-world data, and obtain very promising results on the identity-inference task. We also use our model to predict the timing and participants of future events, and demonstrate that it compares favorably with baseline approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2814", "title": "Competing With Strategies", "text": "We study the problem of online learning with a notion of regret defined with respect to a set of strategies. We develop tools for analyzing the minimax rates and for deriving regret-minimization algorithms in this scenario. While the standard methods for minimizing the usual notion of regret fail, through our analysis we demonstrate existence of regret-minimization methods that compete with such sets of strategies as: autoregressive algorithms, strategies based on statistical models, regularized least squares, and follow the regularized leader strategies. In several cases we also derive efficient learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2815", "title": "A Tensor Approach to Learning Mixed Membership Community Models", "text": "Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of probabilistic network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g. singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.", "source": "arxiv/ml"}
{"id": "arxiv:2816", "title": "Adaptive Metric Dimensionality Reduction", "text": "We study adaptive data-dependent dimensionality reduction in the context of supervised learning in general metric spaces. Our main statistical contribution is a generalization bound for Lipschitz functions in metric spaces that are doubling, or nearly doubling. On the algorithmic front, we describe an analogue of PCA for metric spaces: namely an efficient procedure that approximates the data's intrinsic dimension, which is often much lower than the ambient dimension. Our approach thus leverages the dual benefits of low dimensionality: (1) more efficient algorithms, e.g., for proximity search, and (2) more optimistic generalization bounds.", "source": "arxiv/ml"}
{"id": "arxiv:2817", "title": "Coherence and sufficient sampling densities for reconstruction in compressed sensing", "text": "We give a new, very general, formulation of the compressed sensing problem in terms of coordinate projections of an analytic variety, and derive sufficient sampling rates for signal reconstruction. Our bounds are linear in the coherence of the signal space, a geometric parameter independent of the specific signal and measurement, and logarithmic in the ambient dimension where the signal is presented. We exemplify our approach by deriving sufficient sampling densities for low-rank matrix completion and distance matrix completion which are independent of the true matrix.", "source": "arxiv/ml"}
{"id": "arxiv:2818", "title": "An Efficient Dual Approach to Distance Metric Learning", "text": "Distance metric learning is of fundamental interest in machine learning because the distance metric employed can significantly affect the performance of many learning methods. Quadratic Mahalanobis metric learning is a popular approach to the problem, but typically requires solving a semidefinite programming (SDP) problem, which is computationally expensive. Standard interior-point SDP solvers typically have a complexity of $O(D^{6.5})$ (with $D$ the dimension of input data), and can thus only practically solve problems exhibiting less than a few thousand variables. Since the number of variables is $D (D+1) / 2 $, this implies a limit upon the size of problem that can practically be solved of around a few hundred dimensions. The complexity of the popular quadratic Mahalanobis metric learning approach thus limits the size of problem to which metric learning can be applied. Here we propose a significantly more efficient approach to the metric learning problem based on the Lagrange dual formulation of the problem. The proposed formulation is much simpler to implement, and therefore allows much larger Mahalanobis metric learning problems to be solved. The time complexity of the proposed method is $O (D ^ 3) $, which is significantly lower than that of the SDP approach. Experiments on a variety of datasets demonstrate that the proposed method achieves an accuracy comparable to the state-of-the-art, but is applicable to significantly larger problems. We also show that the proposed method can be applied to solve more general Frobenius-norm regularized SDP problems approximately.", "source": "arxiv/ml"}
{"id": "arxiv:2819", "title": "Adaptive Crowdsourcing Algorithms for the Bandit Survey Problem", "text": "Very recently crowdsourcing has become the de facto platform for distributing and collecting human computation for a wide range of tasks and applications such as information retrieval, natural language processing and machine learning. Current crowdsourcing platforms have some limitations in the area of quality control. Most of the effort to ensure good quality has to be done by the experimenter who has to manage the number of workers needed to reach good results. We propose a simple model for adaptive quality control in crowdsourced multiple-choice tasks which we call the \\emph{bandit survey problem}. This model is related to, but technically different from the well-known multi-armed bandit problem. We present several algorithms for this problem, and support them with analysis and simulations. Our approach is based in our experience conducting relevance evaluation for a large commercial search engine.", "source": "arxiv/ml"}
{"id": "arxiv:2820", "title": "StructBoost: Boosting Methods for Predicting Structured Output Variables", "text": "Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost. StructBoost supports nonlinear structured learning by combining a set of weak structured learners. As SSVM generalizes SVM, our StructBoost generalizes standard boosting approaches such as AdaBoost, or LPBoost to structured learning. The resulting optimization problem of StructBoost is more challenging than SSVM in the sense that it may involve exponentially many variables and constraints. In contrast, for SSVM one usually has an exponential number of constraints and a cutting-plane method is used. In order to efficiently solve StructBoost, we formulate an equivalent $ 1 $-slack formulation and solve it using a combination of cutting planes and column generation. We show the versatility and usefulness of StructBoost on a range of problems such as optimizing the tree loss for hierarchical multi-class classification, optimizing the Pascal overlap criterion for robust visual tracking and learning conditional random field parameters for image segmentation.", "source": "arxiv/ml"}
{"id": "arxiv:2821", "title": "A consistent clustering-based approach to estimating the number of change-points in highly dependent time-series", "text": "The problem of change-point estimation is considered under a general framework where the data are generated by unknown stationary ergodic process distributions. In this context, the consistent estimation of the number of change-points is provably impossible. However, it is shown that a consistent clustering method may be used to estimate the number of change points, under the additional constraint that the correct number of process distributions that generate the data is provided. This additional parameter has a natural interpretation in many real-world applications. An algorithm is proposed that estimates the number of change-points and locates the changes. The proposed algorithm is shown to be asymptotically consistent; its empirical evaluations are provided.", "source": "arxiv/ml"}
{"id": "arxiv:2822", "title": "Exact Methods for Multistage Estimation of a Binomial Proportion", "text": "We first review existing sequential methods for estimating a binomial proportion. Afterward, we propose a new family of group sequential sampling schemes for estimating a binomial proportion with prescribed margin of error and confidence level. In particular, we establish the uniform controllability of coverage probability and the asymptotic optimality for such a family of sampling schemes. Our theoretical results establish the possibility that the parameters of this family of sampling schemes can be determined so that the prescribed level of confidence is guaranteed with little waste of samples. Analytic bounds for the cumulative distribution functions and expectations of sample numbers are derived. Moreover, we discuss the inherent connection of various sampling schemes. Numerical issues are addressed for improving the accuracy and efficiency of computation. Computational experiments are conducted for comparing sampling schemes. Illustrative examples are given for applications in clinical trials.", "source": "arxiv/ml"}
{"id": "arxiv:2823", "title": "Learning Equivalence Classes of Bayesian Networks Structures", "text": "Approaches to learning Bayesian networks from data typically combine a scoring function with a heuristic search procedure. Given a Bayesian network structure, many of the scoring functions derived in the literature return a score for the entire equivalence class to which the structure belongs. When using such a scoring function, it is appropriate for the heuristic search algorithm to search over equivalence classes of Bayesian networks as opposed to individual structures. We present the general formulation of a search space for which the states of the search correspond to equivalence classes of structures. Using this space, any one of a number of heuristic search algorithms can easily be applied. We compare greedy search performance in the proposed search space to greedy search performance in a search space for which the states correspond to individual Bayesian network structures.", "source": "arxiv/ml"}
{"id": "arxiv:2824", "title": "Efficient Approximations for the Marginal Likelihood of Incomplete Data Given a Bayesian Network", "text": "We discuss Bayesian methods for learning Bayesian networks when data sets are incomplete. In particular, we examine asymptotic approximations for the marginal likelihood of incomplete data given a Bayesian network. We consider the Laplace approximation and the less accurate but more efficient BIC/MDL approximation. We also consider approximations proposed by Draper (1993) and Cheeseman and Stutz (1995). These approximations are as efficient as BIC/MDL, but their accuracy has not been studied in any depth. We compare the accuracy of these approximations under the assumption that the Laplace approximation is the most accurate. In experiments using synthetic data generated from discrete naive-Bayes models having a hidden root node, we find that the CS measure is the most accurate.", "source": "arxiv/ml"}
{"id": "arxiv:2825", "title": "Learning Bayesian Networks with Local Structure", "text": "In this paper we examine a novel addition to the known methods for learning Bayesian networks from data that improves the quality of the learned networks. Our approach explicitly represents and learns the local structure in the conditional probability tables (CPTs), that quantify these networks. This increases the space of possible models, enabling the representation of CPTs with a variable number of parameters that depends on the learned local structures. The resulting learning procedure is capable of inducing models that better emulate the real complexity of the interactions present in the data. We describe the theoretical foundations and practical aspects of learning local structures, as well as an empirical evaluation of the proposed method. This evaluation indicates that learning curves characterizing the procedure that exploits the local structure converge faster than these of the standard procedure. Our results also show that networks learned with local structure tend to be more complex (in terms of arcs), yet require less parameters.", "source": "arxiv/ml"}
{"id": "arxiv:2826", "title": "On the Sample Complexity of Learning Bayesian Networks", "text": "In recent years there has been an increasing interest in learning Bayesian networks from data. One of the most effective methods for learning such networks is based on the minimum description length (MDL) principle. Previous work has shown that this learning procedure is asymptotically successful: with probability one, it will converge to the target distribution, given a sufficient number of samples. However, the rate of this convergence has been hitherto unknown. In this work we examine the sample complexity of MDL based learning procedures for Bayesian networks. We show that the number of samples needed to learn an epsilon-close approximation (in terms of entropy distance) with confidence delta is O((1/epsilon)^(4/3)log(1/epsilon)log(1/delta)loglog (1/delta)). This means that the sample complexity is a low-order polynomial in the error threshold and sub-linear in the confidence bound. We also discuss how the constants in this term depend on the complexity of the target distribution. Finally, we address questions of asymptotic minimality and propose a method for using the sample complexity results to speed up the learning process.", "source": "arxiv/ml"}
{"id": "arxiv:2827", "title": "Asymptotic Model Selection for Directed Networks with Hidden Variables", "text": "We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables. This approximation can be used to select models given large samples of data. The standard BIC as well as our extension punishes the complexity of a model according to the dimension of its parameters. We argue that the dimension of a Bayesian network with hidden variables is the rank of the Jacobian matrix of the transformation between the parameters of the network and the parameters of the observable variables. We compute the dimensions of several networks including the naive Bayes model with a hidden root node.", "source": "arxiv/ml"}
{"id": "arxiv:2828", "title": "Bayesian Learning of Loglinear Models for Neural Connectivity", "text": "This paper presents a Bayesian approach to learning the connectivity structure of a group of neurons from data on configuration frequencies. A major objective of the research is to provide statistical tools for detecting changes in firing patterns with changing stimuli. Our framework is not restricted to the well-understood case of pair interactions, but generalizes the Boltzmann machine model to allow for higher order interactions. The paper applies a Markov Chain Monte Carlo Model Composition (MC3) algorithm to search over connectivity structures and uses Laplace's method to approximate posterior probabilities of structures. Performance of the methods was tested on synthetic data. The models were also applied to data obtained by Vaadia on multi-unit recordings of several neurons in the visual cortex of a rhesus monkey in two different attentional states. Results confirmed the experimenters' conjecture that different attentional states were associated with different interaction structures.", "source": "arxiv/ml"}
{"id": "arxiv:2829", "title": "A Latent Source Model for Nonparametric Time Series Classification", "text": "For classifying time series, a nearest-neighbor approach is widely used in practice with performance often competitive with or better than more elaborate methods such as neural networks, decision trees, and support vector machines. We develop theoretical justification for the effectiveness of nearest-neighbor-like classification of time series. Our guiding hypothesis is that in many applications, such as forecasting which topics will become trends on Twitter, there aren't actually that many prototypical time series to begin with, relative to the number of time series we have access to, e.g., topics become trends on Twitter only in a few distinct manners whereas we can collect massive amounts of Twitter data. To operationalize this hypothesis, we propose a latent source model for time series, which naturally leads to a \"weighted majority voting\" classification rule that can be approximated by a nearest-neighbor classifier. We establish nonasymptotic performance guarantees of both weighted majority voting and nearest-neighbor classification under our model accounting for how much of the time series we observe and the model complexity. Experimental results on synthetic data show weighted majority voting achieving the same misclassification rate as nearest-neighbor classification while observing less of the time series. We then use weighted majority to forecast which news topics on Twitter become trends, where we are able to detect such \"trending topics\" in advance of Twitter 79% of the time, with a mean early advantage of 1 hour and 26 minutes, a true positive rate of 95%, and a false positive rate of 4%.", "source": "arxiv/ml"}
{"id": "arxiv:2830", "title": "Bio-inspired data mining: Treating malware signatures as biosequences", "text": "The application of machine learning to bioinformatics problems is well established. Less well understood is the application of bioinformatics techniques to machine learning and, in particular, the representation of non-biological data as biosequences. The aim of this paper is to explore the effects of giving amino acid representation to problematic machine learning data and to evaluate the benefits of supplementing traditional machine learning with bioinformatics tools and techniques. The signatures of 60 computer viruses and 60 computer worms were converted into amino acid representations and first multiply aligned separately to identify conserved regions across different families within each class (virus and worm). This was followed by a second alignment of all 120 aligned signatures together so that non-conserved regions were identified prior to input to a number of machine learning techniques. Differences in length between virus and worm signatures after the first alignment were resolved by the second alignment. Our first set of experiments indicates that representing computer malware signatures as amino acid sequences followed by alignment leads to greater classification and prediction accuracy. Our second set of experiments indicates that checking the results of data mining from artificial virus and worm data against known proteins can lead to generalizations being made from the domain of naturally occurring proteins to malware signatures. However, further work is needed to determine the advantages and disadvantages of different representations and sequence alignment methods for handling problematic machine learning data.", "source": "arxiv/ml"}
{"id": "arxiv:2831", "title": "Density Ratio Hidden Markov Models", "text": "Hidden Markov models and their variants are the predominant sequential classification method in such domains as speech recognition, bioinformatics and natural language processing. Being generative rather than discriminative models, however, their classification performance is a drawback. In this paper we apply ideas from the field of density ratio estimation to bypass the difficult step of learning likelihood functions in HMMs. By reformulating inference and model fitting in terms of density ratios and applying a fast kernel-based estimation method, we show that it is possible to obtain a striking increase in discriminative performance while retaining the probabilistic qualities of the HMM. We demonstrate experimentally that this formulation makes more efficient use of training data than alternative approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2832", "title": "Thompson Sampling in Switching Environments with Bayesian Online Change Point Detection", "text": "Thompson Sampling has recently been shown to be optimal in the Bernoulli Multi-Armed Bandit setting[Kaufmann et al., 2012]. This bandit problem assumes stationary distributions for the rewards. It is often unrealistic to model the real world as a stationary distribution. In this paper we derive and evaluate algorithms using Thompson Sampling for a Switching Multi-Armed Bandit Problem. We propose a Thompson Sampling strategy equipped with a Bayesian change point mechanism to tackle this problem. We develop algorithms for a variety of cases with constant switching rate: when switching occurs all arms change (Global Switching), switching occurs independently for each arm (Per-Arm Switching), when the switching rate is known and when it must be inferred from data. This leads to a family of algorithms we collectively term Change-Point Thompson Sampling (CTS). We show empirical results of the algorithm in 4 artificial environments, and 2 derived from real world data; news click-through[Yahoo!, 2011] and foreign exchange data[Dukascopy, 2012], comparing them to some other bandit algorithms. In real world data CTS is the most effective.", "source": "arxiv/ml"}
{"id": "arxiv:2833", "title": "Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle", "text": "Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data. In this paper, we consider the dimensionality reduction in parameter spaces of binary multivariate distributions. We propose a general Confident-Information-First (CIF) principle to maximally preserve parameters with confident estimates and rule out unreliable or noisy parameters. Formally, the confidence of a parameter can be assessed by its Fisher information, which establishes a connection with the inverse variance of any unbiased estimate for the parameter via the Cram\\'{e}r-Rao bound. We then revisit Boltzmann machines (BM) and theoretically show that both single-layer BM without hidden units (SBM) and restricted BM (RBM) can be solidly derived using the CIF principle. This can not only help us uncover and formalize the essential parts of the target density that SBM and RBM capture, but also suggest that the deep neural network consisting of several layers of RBM can be seen as the layer-wise application of CIF. Guided by the theoretical analysis, we develop a sample-specific CIF-based contrastive divergence (CD-CIF) algorithm for SBM and a CIF-based iterative projection procedure (IP) for RBM. Both CD-CIF and IP are studied in a series of density estimation experiments.", "source": "arxiv/ml"}
{"id": "arxiv:2834", "title": "Clustering validity based on the most similarity", "text": "One basic requirement of many studies is the necessity of classifying data. Clustering is a proposed method for summarizing networks. Clustering methods can be divided into two categories named model-based approaches and algorithmic approaches. Since the most of clustering methods depend on their input parameters, it is important to evaluate the result of a clustering algorithm with its different input parameters, to choose the most appropriate one. There are several clustering validity techniques based on inner density and outer density of clusters that represent different metrics to choose the most appropriate clustering independent of the input parameters. According to dependency of previous methods on the input parameters, one challenge in facing with large systems, is to complete data incrementally that effects on the final choice of the most appropriate clustering. Those methods define the existence of high intensity in a cluster, and low intensity among different clusters as the measure of choosing the optimal clustering. This measure has a tremendous problem, not availing all data at the first stage. In this paper, we introduce an efficient measure in which maximum number of repetitions for various initial values occurs.", "source": "arxiv/ml"}
{"id": "arxiv:2835", "title": "Canonical dual solutions to nonconvex radial basis neural network optimization problem", "text": "Radial Basis Functions Neural Networks (RBFNNs) are tools widely used in regression problems. One of their principal drawbacks is that the formulation corresponding to the training with the supervision of both the centers and the weights is a highly non-convex optimization problem, which leads to some fundamentally difficulties for traditional optimization theory and methods. This paper presents a generalized canonical duality theory for solving this challenging problem. We demonstrate that by sequential canonical dual transformations, the nonconvex optimization problem of the RBFNN can be reformulated as a canonical dual problem (without duality gap). Both global optimal solution and local extrema can be classified. Several applications to one of the most used Radial Basis Functions, the Gaussian function, are illustrated. Our results show that even for one-dimensional case, the global minimizer of the nonconvex problem may not be the best solution to the RBFNNs, and the canonical dual theory is a promising tool for solving general neural networks training problems.", "source": "arxiv/ml"}
{"id": "arxiv:2836", "title": "Metrics for Multivariate Dictionaries", "text": "Overcomplete representations and dictionary learning algorithms kept attracting a growing interest in the machine learning community. This paper addresses the emerging problem of comparing multivariate overcomplete representations. Despite a recurrent need to rely on a distance for learning or assessing multivariate overcomplete representations, no metrics in their underlying spaces have yet been proposed. Henceforth we propose to study overcomplete representations from the perspective of frame theory and matrix manifolds. We consider distances between multivariate dictionaries as distances between their spans which reveal to be elements of a Grassmannian manifold. We introduce Wasserstein-like set-metrics defined on Grassmannian spaces and study their properties both theoretically and numerically. Indeed a deep experimental study based on tailored synthetic datasetsand real EEG signals for Brain-Computer Interfaces (BCI) have been conducted. In particular, the introduced metrics have been embedded in clustering algorithm and applied to BCI Competition IV-2a for dataset quality assessment. Besides, a principled connection is made between three close but still disjoint research fields, namely, Grassmannian packing, dictionary learning and compressed sensing.", "source": "arxiv/ml"}
{"id": "arxiv:2837", "title": "Feature Multi-Selection among Subjective Features", "text": "When dealing with subjective, noisy, or otherwise nebulous features, the \"wisdom of crowds\" suggests that one may benefit from multiple judgments of the same feature on the same object. We give theoretically-motivated `feature multi-selection' algorithms that choose, among a large set of candidate features, not only which features to judge but how many times to judge each one. We demonstrate the effectiveness of this approach for linear regression on a crowdsourced learning task of predicting people's height and weight from photos, using features such as 'gender' and 'estimated weight' as well as culturally fraught ones such as 'attractive'.", "source": "arxiv/ml"}
{"id": "arxiv:2838", "title": "On Translation Invariant Kernels and Screw Functions", "text": "We explore the connection between Hilbertian metrics and positive definite kernels on the real line. In particular, we look at a well-known characterization of translation invariant Hilbertian metrics on the real line by von Neumann and Schoenberg (1941). Using this result we are able to give an alternate proof of Bochner's theorem for translation invariant positive definite kernels on the real line (Rudin, 1962).", "source": "arxiv/ml"}
{"id": "arxiv:2839", "title": "Online Learning with Switching Costs and Other Adaptive Adversaries", "text": "We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We measure the player's performance using a new notion of regret, also known as policy regret, which better captures the adversary's adaptiveness to the player's behavior. In a setting where losses are allowed to drift, we characterize ---in a nearly complete manner--- the power of adaptive adversaries with bounded memories and switching costs. In particular, we show that with switching costs, the attainable rate with bandit feedback is $\\widetilde{\\Theta}(T^{2/3})$. Interestingly, this rate is significantly worse than the $\\Theta(\\sqrt{T})$ rate attainable with switching costs in the full-information case. Via a novel reduction from experts to bandits, we also show that a bounded memory adversary can force $\\widetilde{\\Theta}(T^{2/3})$ regret even in the full information case, proving that switching costs are easier to control than bounded memory adversaries. Our lower bounds rely on a new stochastic adversary strategy that generates loss processes with strong dependencies.", "source": "arxiv/ml"}
{"id": "arxiv:2840", "title": "Maxout Networks", "text": "We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.", "source": "arxiv/ml"}
{"id": "arxiv:2841", "title": "Breaking the Small Cluster Barrier of Graph Clustering", "text": "This paper investigates graph clustering in the planted cluster model in the presence of {\\em small clusters}. Traditional results dictate that for an algorithm to provably correctly recover the clusters, {\\em all} clusters must be sufficiently large (in particular, $\\tilde{\\Omega}(\\sqrt{n})$ where $n$ is the number of nodes of the graph). We show that this is not really a restriction: by a more refined analysis of the trace-norm based recovery approach proposed in Jalali et al. (2011) and Chen et al. (2012), we prove that small clusters, under certain mild assumptions, do not hinder recovery of large ones. Based on this result, we further devise an iterative algorithm to recover {\\em almost all clusters} via a \"peeling strategy\", i.e., recover large clusters first, leading to a reduced problem, and repeat this procedure. These results are extended to the {\\em partial observation} setting, in which only a (chosen) part of the graph is observed.The peeling strategy gives rise to an active learning algorithm, in which edges adjacent to smaller clusters are queried more often as large clusters are learned (and removed). From a high level, this paper sheds novel insights on high-dimensional statistics and learning structured data, by presenting a structured matrix learning problem for which a one shot convex relaxation approach necessarily fails, but a carefully constructed sequence of convex relaxationsdoes the job.", "source": "arxiv/ml"}
{"id": "arxiv:2842", "title": "Optimal Discriminant Functions Based On Sampled Distribution Distance for Modulation Classification", "text": "In this letter, we derive the optimal discriminant functions for modulation classification based on the sampled distribution distance. The proposed method classifies various candidate constellations using a low complexity approach based on the distribution distance at specific testpoints along the cumulative distribution function. This method, based on the Bayesian decision criteria, asymptotically provides the minimum classification error possible given a set of testpoints. Testpoint locations are also optimized to improve classification performance. The method provides significant gains over existing approaches that also use the distribution of the signal features.", "source": "arxiv/ml"}
{"id": "arxiv:2843", "title": "A Labeled Graph Kernel for Relationship Extraction", "text": "In this paper, we propose an approach for Relationship Extraction (RE) based on labeled graph kernels. The kernel we propose is a particularization of a random walk kernel that exploits two properties previously studied in the RE literature: (i) the words between the candidate entities or connecting them in a syntactic representation are particularly likely to carry information regarding the relationship; and (ii) combining information from distinct sources in a kernel may help the RE system make better decisions. We performed experiments on a dataset of protein-protein interactions and the results show that our approach obtains effectiveness values that are comparable with the state-of-the art kernel methods. Moreover, our approach is able to outperform the state-of-the-art kernels when combined with other kernel methods.", "source": "arxiv/ml"}
{"id": "arxiv:2844", "title": "Fast methods for denoising matrix completion formulations, with applications to robust seismic data interpolation", "text": "Recent SVD-free matrix factorization formulations have enabled rank minimization for systems with millions of rows and columns, paving the way for matrix completion in extremely large-scale applications, such as seismic data interpolation. In this paper, we consider matrix completion formulations designed to hit a target data-fitting error level provided by the user, and propose an algorithm called LR-BPDN that is able to exploit factorized formulations to solve the corresponding optimization problem. Since practitioners typically have strong prior knowledge about target error level, this innovation makes it easy to apply the algorithm in practice, leaving only the factor rank to be determined. Within the established framework, we propose two extensions that are highly relevant to solving practical challenges of data interpolation. First, we propose a weighted extension that allows known subspace information to improve the results of matrix completion formulations. We show how this weighting can be used in the context of frequency continuation, an essential aspect to seismic data interpolation. Second, we propose matrix completion formulations that are robust to large measurement errors in the available data. We illustrate the advantages of LR-BPDN on the collaborative filtering problem using the MovieLens 1M, 10M, and Netflix 100M datasets. Then, we use the new method, along with its robust and subspace re-weighted extensions, to obtain high-quality reconstructions for large scale seismic interpolation problems with real data, even in the presence of data contamination.", "source": "arxiv/ml"}
{"id": "arxiv:2845", "title": "Structure Discovery in Nonparametric Regression through Compositional Kernel Search", "text": "Despite its importance, choosing the structural form of the kernel in nonparametric regression remains a black art. We define a space of kernel structures which are built compositionally by adding and multiplying a small number of base kernels. We present a method for searching over this space of structures which mirrors the scientific discovery process. The learned structures can often decompose functions into interpretable components and enable long-range extrapolation on time-series datasets. Our structure search method outperforms many widely used kernels and kernel combination methods on a variety of prediction tasks.", "source": "arxiv/ml"}
{"id": "arxiv:2846", "title": "A Characterization of the Dirichlet Distribution with Application to Learning Bayesian Networks", "text": "We provide a new characterization of the Dirichlet distribution. This characterization implies that under assumptions made by several previous authors for learning belief networks, a Dirichlet prior on the parameters is inevitable.", "source": "arxiv/ml"}
{"id": "arxiv:2847", "title": "Estimating Continuous Distributions in Bayesian Classifiers", "text": "When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated by a single Gaussian. In this paper we abandon the normality assumption and instead use statistical methods for nonparametric density estimation. For a naive Bayesian classifier, we present experimental results on a variety of natural and artificial domains, comparing two methods of density estimation: assuming normality and modeling each conditional distribution with a single Gaussian; and using nonparametric kernel density estimation. We observe large reductions in error on several natural and artificial data sets, which suggests that kernel estimation is a useful tool for learning Bayesian models.", "source": "arxiv/ml"}
{"id": "arxiv:2848", "title": "Matching Pursuit LASSO Part II: Applications and Sparse Recovery over Batch Signals", "text": "Matching Pursuit LASSIn Part I \\cite{TanPMLPart1}, a Matching Pursuit LASSO ({MPL}) algorithm has been presented for solving large-scale sparse recovery (SR) problems. In this paper, we present a subspace search to further improve the performance of MPL, and then continue to address another major challenge of SR -- batch SR with many signals, a consideration which is absent from most of previous $\\ell_1$-norm methods. As a result, a batch-mode {MPL} is developed to vastly speed up sparse recovery of many signals simultaneously. Comprehensive numerical experiments on compressive sensing and face recognition tasks demonstrate the superior performance of MPL and BMPL over other methods considered in this paper, in terms of sparse recovery ability and efficiency. In particular, BMPL is up to 400 times faster than existing $\\ell_1$-norm methods considered to be state-of-the-art.O Part II: Applications and Sparse Recovery over Batch Signals", "source": "arxiv/ml"}
{"id": "arxiv:2849", "title": "Pooling-Invariant Image Feature Learning", "text": "Unsupervised dictionary learning has been a key component in state-of-the-art computer vision recognition architectures. While highly effective methods exist for patch-based dictionary learning, these methods may learn redundant features after the pooling stage in a given early vision architecture. In this paper, we offer a novel dictionary learning scheme to efficiently take into account the invariance of learned features after the spatial pooling stage. The algorithm is built on simple clustering, and thus enjoys efficiency and scalability. We discuss the underlying mechanism that justifies the use of clustering algorithms, and empirically show that the algorithm finds better dictionaries than patch-based methods with the same dictionary size.", "source": "arxiv/ml"}
{"id": "arxiv:2850", "title": "High-Dimensional Probability Estimation with Deep Density Models", "text": "One of the fundamental problems in machine learning is the estimation of a probability distribution from data. Many techniques have been proposed to study the structure of data, most often building around the assumption that observations lie on a lower-dimensional manifold of high probability. It has been more difficult, however, to exploit this insight to build explicit, tractable density models for high-dimensional data. In this paper, we introduce the deep density model (DDM), a new approach to density estimation. We exploit insights from deep learning to construct a bijective map to a representation space, under which the transformation of the distribution of the data is approximately factorized and has identical and known marginal densities. The simplicity of the latent distribution under the model allows us to feasibly explore it, and the invertibility of the map to characterize contraction of measure across it. This enables us to compute normalized densities for out-of-sample data. This combination of tractability and flexibility allows us to tackle a variety of probabilistic tasks on high-dimensional datasets, including: rapid computation of normalized densities at test-time without evaluating a partition function; generation of samples without MCMC; and characterization of the joint entropy of the data.", "source": "arxiv/ml"}
{"id": "arxiv:2851", "title": "Prediction and Clustering in Signed Networks: A Local to Global Perspective", "text": "The study of social networks is a burgeoning research area. However, most existing work deals with networks that simply encode whether relationships exist or not. In contrast, relationships in signed networks can be positive (\"like\", \"trust\") or negative (\"dislike\", \"distrust\"). The theory of social balance shows that signed networks tend to conform to some local patterns that, in turn, induce certain global characteristics. In this paper, we exploit both local as well as global aspects of social balance theory for two fundamental problems in the analysis of signed networks: sign prediction and clustering. Motivated by local patterns of social balance, we first propose two families of sign prediction methods: measures of social imbalance (MOIs), and supervised learning using high order cycles (HOCs). These methods predict signs of edges based on triangles and \\ell-cycles for relatively small values of \\ell. Interestingly, by examining measures of social imbalance, we show that the classic Katz measure, which is used widely in unsigned link prediction, actually has a balance theoretic interpretation when applied to signed networks. Furthermore, motivated by the global structure of balanced networks, we propose an effective low rank modeling approach for both sign prediction and clustering. For the low rank modeling approach, we provide theoretical performance guarantees via convex relaxations, scale it up to large problem sizes using a matrix factorization based algorithm, and provide extensive experimental validation including comparisons with local approaches. Our experimental results indicate that, by adopting a more global viewpoint of balance structure, we get significant performance and computational gains in prediction and clustering tasks on signed networks. Our work therefore highlights the usefulness of the global aspect of balance theory for the analysis of signed networks.", "source": "arxiv/ml"}
{"id": "arxiv:2852", "title": "Graph-based Generalization Bounds for Learning Binary Relations", "text": "We investigate the generalizability of learned binary relations: functions that map pairs of instances to a logical indicator. This problem has application in numerous areas of machine learning, such as ranking, entity resolution and link prediction. Our learning framework incorporates an example labeler that, given a sequence $X$ of $n$ instances and a desired training size $m$, subsamples $m$ pairs from $X \\times X$ without replacement. The challenge in analyzing this learning scenario is that pairwise combinations of random variables are inherently dependent, which prevents us from using traditional learning-theoretic arguments. We present a unified, graph-based analysis, which allows us to analyze this dependence using well-known graph identities. We are then able to bound the generalization error of learned binary relations using Rademacher complexity and algorithmic stability. The rate of uniform convergence is partially determined by the labeler's subsampling process. We thus examine how various assumptions about subsampling affect generalization; under a natural random subsampling process, our bounds guarantee $\\tilde{O}(1/\\sqrt{n})$ uniform convergence.", "source": "arxiv/ml"}
{"id": "arxiv:2853", "title": "Nonparametric Basis Pursuit via Sparse Kernel-based Learning", "text": "Signal processing tasks as fundamental as sampling, reconstruction, minimum mean-square error interpolation and prediction can be viewed under the prism of reproducing kernel Hilbert spaces. Endowing this vantage point with contemporary advances in sparsity-aware modeling and processing, promotes the nonparametric basis pursuit advocated in this paper as the overarching framework for the confluence of kernel-based learning (KBL) approaches leveraging sparse linear regression, nuclear-norm regularization, and dictionary learning. The novel sparse KBL toolbox goes beyond translating sparse parametric approaches to their nonparametric counterparts, to incorporate new possibilities such as multi-kernel selection and matrix smoothing. The impact of sparse KBL to signal processing applications is illustrated through test cases from cognitive radio sensing, microarray data imputation, and network traffic prediction.", "source": "arxiv/ml"}
{"id": "arxiv:2854", "title": "The Importance of Clipping in Neurocontrol by Direct Gradient Descent on the Cost-to-Go Function and in Adaptive Dynamic Programming", "text": "In adaptive dynamic programming, neurocontrol and reinforcement learning, the objective is for an agent to learn to choose actions so as to minimise a total cost function. In this paper we show that when discretized time is used to model the motion of the agent, it can be very important to do \"clipping\" on the motion of the agent in the final time step of the trajectory. By clipping we mean that the final time step of the trajectory is to be truncated such that the agent stops exactly at the first terminal state reached, and no distance further. We demonstrate that when clipping is omitted, learning performance can fail to reach the optimum; and when clipping is done properly, learning performance can improve significantly. The clipping problem we describe affects algorithms which use explicit derivatives of the model functions of the environment to calculate a learning gradient. These include Backpropagation Through Time for Control, and methods based on Dual Heuristic Dynamic Programming. However the clipping problem does not significantly affect methods based on Heuristic Dynamic Programming, Temporal Differences or Policy Gradient Learning algorithms. Similarly, the clipping problem does not affect fixed-length finite-horizon problems.", "source": "arxiv/ml"}
{"id": "arxiv:2855", "title": "Accelerated Linear SVM Training with Adaptive Variable Selection Frequencies", "text": "Support vector machine (SVM) training is an active research area since the dawn of the method. In recent years there has been increasing interest in specialized solvers for the important case of linear models. The algorithm presented by Hsieh et al., probably best known under the name of the \"liblinear\" implementation, marks a major breakthrough. The method is analog to established dual decomposition algorithms for training of non-linear SVMs, but with greatly reduced computational complexity per update step. This comes at the cost of not keeping track of the gradient of the objective any more, which excludes the application of highly developed working set selection algorithms. We present an algorithmic improvement to this method. We replace uniform working set selection with an online adaptation of selection frequencies. The adaptation criterion is inspired by modern second order working set selection methods. The same mechanism replaces the shrinking heuristic. This novel technique speeds up training in some cases by more than an order of magnitude.", "source": "arxiv/ml"}
{"id": "arxiv:2856", "title": "Sparse Signal Estimation by Maximally Sparse Convex Optimization", "text": "This paper addresses the problem of sparsity penalized least squares for applications in sparse signal processing, e.g. sparse deconvolution. This paper aims to induce sparsity more strongly than L1 norm regularization, while avoiding non-convex optimization. For this purpose, this paper describes the design and use of non-convex penalty functions (regularizers) constrained so as to ensure the convexity of the total cost function, F, to be minimized. The method is based on parametric penalty functions, the parameters of which are constrained to ensure convexity of F. It is shown that optimal parameters can be obtained by semidefinite programming (SDP). This maximally sparse convex (MSC) approach yields maximally non-convex sparsity-inducing penalty functions constrained such that the total cost function, F, is convex. It is demonstrated that iterative MSC (IMSC) can yield solutions substantially more sparse than the standard convex sparsity-inducing approach, i.e., L1 norm minimization.", "source": "arxiv/ml"}
{"id": "arxiv:2857", "title": "Prediction by Random-Walk Perturbation", "text": "We propose a version of the follow-the-perturbed-leader online prediction algorithm in which the cumulative losses are perturbed by independent symmetric random walks. The forecaster is shown to achieve an expected regret of the optimal order O(sqrt(n log N)) where n is the time horizon and N is the number of experts. More importantly, it is shown that the forecaster changes its prediction at most O(sqrt(n log N)) times, in expectation. We also extend the analysis to online combinatorial optimization and show that even in this more general setting, the forecaster rarely switches between experts while having a regret of near-optimal order.", "source": "arxiv/ml"}
{"id": "arxiv:2858", "title": "On learning parametric-output HMMs", "text": "We present a novel approach for learning an HMM whose outputs are distributed according to a parametric family. This is done by {\\em decoupling} the learning task into two steps: first estimating the output parameters, and then estimating the hidden states transition probabilities. The first step is accomplished by fitting a mixture model to the output stationary distribution. Given the parameters of this mixture model, the second step is formulated as the solution of an easily solvable convex quadratic program. We provide an error analysis for the estimated transition probabilities and show they are robust to small perturbations in the estimates of the mixture parameters. Finally, we support our analysis with some encouraging empirical results.", "source": "arxiv/ml"}
{"id": "arxiv:2859", "title": "Phoneme discrimination using $KS$-algebra II", "text": "$KS$-algebra consists of expressions constructed with four kinds operations, the minimum, maximum, difference and additively homogeneous generalized means. Five families of $Z$-classifiers are investigated on binary classification tasks between English phonemes. It is shown that the classifiers are able to reflect well known formant characteristics of vowels, while having very small Kolmogoroff's complexity.", "source": "arxiv/ml"}
{"id": "arxiv:2860", "title": "A Homogeneous Ensemble of Artificial Neural Networks for Time Series Forecasting", "text": "Enhancing the robustness and accuracy of time series forecasting models is an active area of research. Recently, Artificial Neural Networks (ANNs) have found extensive applications in many practical forecasting problems. However, the standard backpropagation ANN training algorithm has some critical issues, e.g. it has a slow convergence rate and often converges to a local minimum, the complex pattern of error surfaces, lack of proper training parameters selection methods, etc. To overcome these drawbacks, various improved training methods have been developed in literature; but, still none of them can be guaranteed as the best for all problems. In this paper, we propose a novel weighted ensemble scheme which intelligently combines multiple training algorithms to increase the ANN forecast accuracies. The weight for each training algorithm is determined from the performance of the corresponding ANN model on the validation dataset. Experimental results on four important time series depicts that our proposed technique reduces the mentioned shortcomings of individual ANN training algorithms to a great extent. Also it achieves significantly better forecast accuracies than two other popular statistical models.", "source": "arxiv/ml"}
{"id": "arxiv:2861", "title": "Rate-Distortion Bounds for an Epsilon-Insensitive Distortion Measure", "text": "Direct evaluation of the rate-distortion function has rarely been achieved when it is strictly greater than its Shannon lower bound. In this paper, we consider the rate-distortion function for the distortion measure defined by an epsilon-insensitive loss function. We first present the Shannon lower bound applicable to any source distribution with finite differential entropy. Then, focusing on the Laplacian and Gaussian sources, we prove that the rate-distortion functions of these sources are strictly greater than their Shannon lower bounds and obtain analytically evaluable upper bounds for the rate-distortion functions. Small distortion limit and numerical evaluation of the bounds suggest that the Shannon lower bound provides a good approximation to the rate-distortion function for the epsilon-insensitive distortion measure.", "source": "arxiv/ml"}
{"id": "arxiv:2862", "title": "The adaptive Gril estimator with a diverging number of parameters", "text": "We consider the problem of variables selection and estimation in linear regression model in situations where the number of parameters diverges with the sample size. We propose the adaptive Generalized Ridge-Lasso (\\mbox{AdaGril}) which is an extension of the the adaptive Elastic Net. AdaGril incorporates information redundancy among correlated variables for model selection and estimation. It combines the strengths of the quadratic regularization and the adaptively weighted Lasso shrinkage. In this paper, we highlight the grouped selection property for AdaCnet method (one type of AdaGril) in the equal correlation case. Under weak conditions, we establish the oracle property of AdaGril which ensures the optimal large performance when the dimension is high. Consequently, it achieves both goals of handling the problem of collinearity in high dimension and enjoys the oracle property. Moreover, we show that AdaGril estimator achieves a Sparsity Inequality, i. e., a bound in terms of the number of non-zero components of the 'true' regression coefficient. This bound is obtained under a similar weak Restricted Eigenvalue (RE) condition used for Lasso. Simulations studies show that some particular cases of AdaGril outperform its competitors.", "source": "arxiv/ml"}
{"id": "arxiv:2863", "title": "ML4PG in Computer Algebra verification", "text": "ML4PG is a machine-learning extension that provides statistical proof hints during the process of Coq/SSReflect proof development. In this paper, we use ML4PG to find proof patterns in the CoqEAL library -- a library that was devised to verify the correctness of Computer Algebra algorithms. In particular, we use ML4PG to help us in the formalisation of an efficient algorithm to compute the inverse of triangular matrices.", "source": "arxiv/ml"}
{"id": "arxiv:2864", "title": "A Conformal Prediction Approach to Explore Functional Data", "text": "This paper applies conformal prediction techniques to compute simultaneous prediction bands and clustering trees for functional data. These tools can be used to detect outliers and clusters. Both our prediction bands and clustering trees provide prediction sets for the underlying stochastic process with a guaranteed finite sample behavior, under no distributional assumptions. The prediction sets are also informative in that they correspond to the high density region of the underlying process. While ordinary conformal prediction has high computational cost for functional data, we use the inductive conformal predictor, together with several novel choices of conformity scores, to simplify the computation. Our methods are illustrated on some real data examples.", "source": "arxiv/ml"}
{"id": "arxiv:2865", "title": "Sparse Frequency Analysis with Sparse-Derivative Instantaneous Amplitude and Phase Functions", "text": "This paper addresses the problem of expressing a signal as a sum of frequency components (sinusoids) wherein each sinusoid may exhibit abrupt changes in its amplitude and/or phase. The Fourier transform of a narrow-band signal, with a discontinuous amplitude and/or phase function, exhibits spectral and temporal spreading. The proposed method aims to avoid such spreading by explicitly modeling the signal of interest as a sum of sinusoids with time-varying amplitudes. So as to accommodate abrupt changes, it is further assumed that the amplitude/phase functions are approximately piecewise constant (i.e., their time-derivatives are sparse). The proposed method is based on a convex variational (optimization) approach wherein the total variation (TV) of the amplitude functions are regularized subject to a perfect (or approximate) reconstruction constraint. A computationally efficient algorithm is derived based on convex optimization techniques. The proposed technique can be used to perform band-pass filtering that is relatively insensitive to narrow-band amplitude/phase jumps present in data, which normally pose a challenge (due to transients, leakage, etc.). The method is illustrated using both synthetic signals and human EEG data for the purpose of band-pass filtering and the estimation of phase synchrony indexes.", "source": "arxiv/ml"}
{"id": "arxiv:2867", "title": "An Introductory Study on Time Series Modeling and Forecasting", "text": "Time series modeling and forecasting has fundamental importance to various practical domains. Thus a lot of active research works is going on in this subject during several years. Many important models have been proposed in literature for improving the accuracy and effectiveness of time series forecasting. The aim of this dissertation work is to present a concise description of some popular time series forecasting models used in practice, with their salient features. In this thesis, we have described three important classes of time series models, viz. the stochastic, neural networks and SVM based models, together with their inherent forecasting strengths and weaknesses. We have also discussed about the basic issues related to time series modeling, such as stationarity, parsimony, overfitting, etc. Our discussion about different time series models is supported by giving the experimental forecast results, performed on six real time series datasets. While fitting a model to a dataset, special care is taken to select the most parsimonious one. To evaluate forecast accuracy as well as to compare among different models fitted to a time series, we have used the five performance measures, viz. MSE, MAD, RMSE, MAPE and Theil's U-statistics. For each of the six datasets, we have shown the obtained forecast diagram which graphically depicts the closeness between the original and forecasted observations. To have authenticity as well as clarity in our discussion about time series modeling and forecasting, we have taken the help of various published research works from reputed journals and some standard books.", "source": "arxiv/ml"}
{"id": "arxiv:2868", "title": "Arriving on time: estimating travel time distributions on large-scale road networks", "text": "Most optimal routing problems focus on minimizing travel time or distance traveled. Oftentimes, a more useful objective is to maximize the probability of on-time arrival, which requires statistical distributions of travel times, rather than just mean values. We propose a method to estimate travel time distributions on large-scale road networks, using probe vehicle data collected from GPS. We present a framework that works with large input of data, and scales linearly with the size of the network. Leveraging the planar topology of the graph, the method computes efficiently the time correlations between neighboring streets. First, raw probe vehicle traces are compressed into pairs of travel times and number of stops for each traversed road segment using a `stop-and-go' algorithm developed for this work. The compressed data is then used as input for training a path travel time model, which couples a Markov model along with a Gaussian Markov random field. Finally, scalable inference algorithms are developed for obtaining path travel time distributions from the composite MM-GMRF model. We illustrate the accuracy and scalability of our model on a 505,000 road link network spanning the San Francisco Bay Area.", "source": "arxiv/ml"}
{"id": "arxiv:2869", "title": "Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization", "text": "Integration is affected by the curse of dimensionality and quickly becomes intractable as the dimensionality of the problem grows. We propose a randomized algorithm that, with high probability, gives a constant-factor approximation of a general discrete integral defined over an exponentially large set. This algorithm relies on solving only a small number of instances of a discrete combinatorial optimization problem subject to randomly generated parity constraints used as a hash function. As an application, we demonstrate that with a small number of MAP queries we can efficiently approximate the partition function of discrete graphical models, which can in turn be used, for instance, for marginal computation or model selection.", "source": "arxiv/ml"}
{"id": "arxiv:2870", "title": "Categorizing Bugs with Social Networks: A Case Study on Four Open Source Software Communities", "text": "Efficient bug triaging procedures are an important precondition for successful collaborative software engineering projects. Triaging bugs can become a laborious task particularly in open source software (OSS) projects with a large base of comparably inexperienced part-time contributors. In this paper, we propose an efficient and practical method to identify valid bug reports which a) refer to an actual software bug, b) are not duplicates and c) contain enough information to be processed right away. Our classification is based on nine measures to quantify the social embeddedness of bug reporters in the collaboration network. We demonstrate its applicability in a case study, using a comprehensive data set of more than 700,000 bug reports obtained from the Bugzilla installation of four major OSS communities, for a period of more than ten years. For those projects that exhibit the lowest fraction of valid bug reports, we find that the bug reporters' position in the collaboration network is a strong indicator for the quality of bug reports. Based on this finding, we develop an automated classification scheme that can easily be integrated into bug tracking platforms and analyze its performance in the considered OSS communities. A support vector machine (SVM) to identify valid bug reports based on the nine measures yields a precision of up to 90.3% with an associated recall of 38.9%. With this, we significantly improve the results obtained in previous case studies for an automated early identification of bugs that are eventually fixed. Furthermore, our study highlights the potential of using quantitative measures of social organization in collaborative software engineering. It also opens a broad perspective for the integration of social awareness in the design of support infrastructures.", "source": "arxiv/ml"}
{"id": "arxiv:2871", "title": "Missing Entries Matrix Approximation and Completion", "text": "We describe several algorithms for matrix completion and matrix approximation when only some of its entries are known. The approximation constraint can be any whose approximated solution is known for the full matrix. For low rank approximations, similar algorithms appears recently in the literature under different names. In this work, we introduce new theorems for matrix approximation and show that these algorithms can be extended to handle different constraints such as nuclear norm, spectral norm, orthogonality constraints and more that are different than low rank approximations. As the algorithms can be viewed from an optimization point of view, we discuss their convergence to global solution for the convex case. We also discuss the optimal step size and show that it is fixed in each iteration. In addition, the derived matrix completion flow is robust and does not require any parameters. This matrix completion flow is applicable to different spectral minimizations and can be applied to physics, mathematics and electrical engineering problems such as data reconstruction of images and data coming from PDEs such as Helmholtz equation used for electromagnetic waves.", "source": "arxiv/ml"}
{"id": "arxiv:2872", "title": "Learning Gaussian Networks", "text": "We describe algorithms for learning Bayesian networks from a combination of user knowledge and statistical data. The algorithms have two components: a scoring metric and a search procedure. The scoring metric takes a network structure, statistical data, and a user's prior knowledge, and returns a score proportional to the posterior probability of the network structure given the data. The search procedure generates networks for evaluation by the scoring metric. Previous work has concentrated on metrics for domains containing only discrete variables, under the assumption that data represents a multinomial sample. In this paper, we extend this work, developing scoring metrics for domains containing all continuous variables or a mixture of discrete and continuous variables, under the assumption that continuous data is sampled from a multivariate normal distribution. Our work extends traditional statistical approaches for identifying vanishing regression coefficients in that we identify two important assumptions, called event equivalence and parameter modularity, that when combined allow the construction of prior distributions for multivariate normal parameters from a single prior Bayesian network specified by a user.", "source": "arxiv/ml"}
{"id": "arxiv:2873", "title": "Induction of Selective Bayesian Classifiers", "text": "In this paper, we examine previous work on the naive Bayesian classifier and review its limitations, which include a sensitivity to correlated features. We respond to this problem by embedding the naive Bayesian induction scheme within an algorithm that c arries out a greedy search through the space of features. We hypothesize that this approach will improve asymptotic accuracy in domains that involve correlated features without reducing the rate of learning in ones that do not. We report experimental results on six natural domains, including comparisons with decision-tree induction, that support these hypotheses. In closing, we discuss other approaches to extending naive Bayesian classifiers and outline some directions for future research.", "source": "arxiv/ml"}
{"id": "arxiv:2874", "title": "Online Learning for Time Series Prediction", "text": "In this paper we address the problem of predicting a time series using the ARMA (autoregressive moving average) model, under minimal assumptions on the noise terms. Using regret minimization techniques, we develop effective online learning algorithms for the prediction problem, without assuming that the noise terms are Gaussian, identically distributed or even independent. Furthermore, we show that our algorithm's performances asymptotically approaches the performance of the best ARMA model in hindsight.", "source": "arxiv/ml"}
{"id": "arxiv:2875", "title": "Online Convex Optimization Against Adversaries with Memory and Application to Statistical Arbitrage", "text": "The framework of online learning with memory naturally captures learning problems with temporal constraints, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obtaining optimal regret bounds for both convex and strongly convex losses. The second algorithm attains the optimal regret bounds and applies more broadly to convex losses without requiring Lipschitz continuity, yet is more complicated to implement. We complement our theoretic results with an application to statistical arbitrage in finance: we devise algorithms for constructing mean-reverting portfolios.", "source": "arxiv/ml"}
{"id": "arxiv:2876", "title": "Spectrum Bandit Optimization", "text": "We consider the problem of allocating radio channels to links in a wireless network. Links interact through interference, modelled as a conflict graph (i.e., two interfering links cannot be simultaneously active on the same channel). We aim at identifying the channel allocation maximizing the total network throughput over a finite time horizon. Should we know the average radio conditions on each channel and on each link, an optimal allocation would be obtained by solving an Integer Linear Program (ILP). When radio conditions are unknown a priori, we look for a sequential channel allocation policy that converges to the optimal allocation while minimizing on the way the throughput loss or {\\it regret} due to the need for exploring sub-optimal allocations. We formulate this problem as a generic linear bandit problem, and analyze it first in a stochastic setting where radio conditions are driven by a stationary stochastic process, and then in an adversarial setting where radio conditions can evolve arbitrarily. We provide new algorithms in both settings and derive upper bounds on their regrets.", "source": "arxiv/ml"}
{"id": "arxiv:2877", "title": "Scoup-SMT: Scalable Coupled Sparse Matrix-Tensor Factorization", "text": "How can we correlate neural activity in the human brain as it responds to words, with behavioral data expressed as answers to questions about these same words? In short, we want to find latent variables, that explain both the brain activity, as well as the behavioral responses. We show that this is an instance of the Coupled Matrix-Tensor Factorization (CMTF) problem. We propose Scoup-SMT, a novel, fast, and parallel algorithm that solves the CMTF problem and produces a sparse latent low-rank subspace of the data. In our experiments, we find that Scoup-SMT is 50-100 times faster than a state-of-the-art algorithm for CMTF, along with a 5 fold increase in sparsity. Moreover, we extend Scoup-SMT to handle missing data without degradation of performance. We apply Scoup-SMT to BrainQ, a dataset consisting of a (nouns, brain voxels, human subjects) tensor and a (nouns, properties) matrix, with coupling along the nouns dimension. Scoup-SMT is able to find meaningful latent variables, as well as to predict brain activity with competitive accuracy. Finally, we demonstrate the generality of Scoup-SMT, by applying it on a Facebook dataset (users, friends, wall-postings); there, Scoup-SMT spots spammer-like anomalies.", "source": "arxiv/ml"}
{"id": "arxiv:2878", "title": "Learning Theory in the Arithmetic Hierarchy", "text": "We consider the arithmetic complexity of index sets of uniformly computably enumerable families learnable under different learning criteria. We determine the exact complexity of these sets for the standard notions of finite learning, learning in the limit, behaviorally correct learning and anomalous learning in the limit. In proving the $\\Sigma_5^0$-completeness result for behaviorally correct learning we prove a result of independent interest; if a uniformly computably enumerable family is not learnable, then for any computable learner there is a $\\Delta_2^0$ enumeration witnessing failure.", "source": "arxiv/ml"}
{"id": "arxiv:2879", "title": "Estimating the Maximum Expected Value: An Analysis of (Nested) Cross Validation and the Maximum Sample Average", "text": "We investigate the accuracy of the two most common estimators for the maximum expected value of a general set of random variables: a generalization of the maximum sample average, and cross validation. No unbiased estimator exists and we show that it is non-trivial to select a good estimator without knowledge about the distributions of the random variables. We investigate and bound the bias and variance of the aforementioned estimators and prove consistency. The variance of cross validation can be significantly reduced, but not without risking a large bias. The bias and variance of different variants of cross validation are shown to be very problem-dependent, and a wrong choice can lead to very inaccurate estimates.", "source": "arxiv/ml"}
{"id": "arxiv:2880", "title": "Online Similarity Prediction of Networked Data from Known and Unknown Graphs", "text": "We consider online similarity prediction problems over networked data. We begin by relating this task to the more standard class prediction problem, showing that, given an arbitrary algorithm for class prediction, we can construct an algorithm for similarity prediction with \"nearly\" the same mistake bound, and vice versa. After noticing that this general construction is computationally infeasible, we target our study to {\\em feasible} similarity prediction algorithms on networked data. We initially assume that the network structure is {\\em known} to the learner. Here we observe that Matrix Winnow \\cite{w07} has a near-optimal mistake guarantee, at the price of cubic prediction time per round. This motivates our effort for an efficient implementation of a Perceptron algorithm with a weaker mistake guarantee but with only poly-logarithmic prediction time. Our focus then turns to the challenging case of networks whose structure is initially {\\em unknown} to the learner. In this novel setting, where the network structure is only incrementally revealed, we obtain a mistake-bounded algorithm with a quadratic prediction time per round.", "source": "arxiv/ml"}
{"id": "arxiv:2881", "title": "Bayesian Consensus Clustering", "text": "The task of clustering a set of objects based on multiple sources of data arises in several modern applications. We propose an integrative statistical model that permits a separate clustering of the objects for each data source. These separate clusterings adhere loosely to an overall consensus clustering, and hence they are not independent. We describe a computationally scalable Bayesian framework for simultaneous estimation of both the consensus clustering and the source-specific clusterings. We demonstrate that this flexible approach is more robust than joint clustering of all data sources, and is more powerful than clustering each data source separately. This work is motivated by the integrated analysis of heterogeneous biomedical data, and we present an application to subtype identification of breast cancer tumor samples using publicly available data from The Cancer Genome Atlas. Software is available at http://people.duke.edu/~el113/software.html.", "source": "arxiv/ml"}
{"id": "arxiv:2882", "title": "Source Separation using Regularized NMF with MMSE Estimates under GMM Priors with Online Learning for The Uncertainties", "text": "We propose a new method to enforce priors on the solution of the nonnegative matrix factorization (NMF). The proposed algorithm can be used for denoising or single-channel source separation (SCSS) applications. The NMF solution is guided to follow the Minimum Mean Square Error (MMSE) estimates under Gaussian mixture prior models (GMM) for the source signal. In SCSS applications, the spectra of the observed mixed signal are decomposed as a weighted linear combination of trained basis vectors for each source using NMF. In this work, the NMF decomposition weight matrices are treated as a distorted image by a distortion operator, which is learned directly from the observed signals. The MMSE estimate of the weights matrix under GMM prior and log-normal distribution for the distortion is then found to improve the NMF decomposition results. The MMSE estimate is embedded within the optimization objective to form a novel regularized NMF cost function. The corresponding update rules for the new objectives are derived in this paper. Experimental results show that, the proposed regularized NMF algorithm improves the source separation performance compared with using NMF without prior or with other prior models.", "source": "arxiv/ml"}
{"id": "arxiv:2883", "title": "A Method for Comparing Hedge Funds", "text": "The paper presents new machine learning methods: signal composition, which classifies time-series regardless of length, type, and quantity; and self-labeling, a supervised-learning enhancement. The paper describes further the implementation of the methods on a financial search engine system to identify behavioral similarities among time-series representing monthly returns of 11,312 hedge funds operated during approximately one decade (2000 - 2010). The presented approach of cross-category and cross-location classification assists the investor to identify alternative investments.", "source": "arxiv/ml"}
{"id": "arxiv:2884", "title": "Bio-Signals-based Situation Comparison Approach to Predict Pain", "text": "This paper describes a time-series-based classification approach to identify similarities between bio-medical-based situations. The proposed approach allows classifying collections of time-series representing bio-medical measurements, i.e., situations, regardless of the type, the length and the quantity of the time-series a situation comprised of.", "source": "arxiv/ml"}
{"id": "arxiv:2885", "title": "Label-dependent Feature Extraction in Social Networks for Node Classification", "text": "A new method of feature extraction in the social network for within-network classification is proposed in the paper. The method provides new features calculated by combination of both: network structure information and class labels assigned to nodes. The influence of various features on classification performance has also been studied. The experiments on real-world data have shown that features created owing to the proposed method can lead to significant improvement of classification accuracy.", "source": "arxiv/ml"}
{"id": "arxiv:2886", "title": "Second-Order Non-Stationary Online Learning for Regression", "text": "The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algorithms were shown to have this gap arbitrarily close to zero, compared with the best function that is chosen off-line. Nevertheless, many real-world applications, such as adaptive filtering, are non-stationary in nature, and the best prediction function may drift over time. We introduce two novel algorithms for online regression, designed to work well in non-stationary environment. Our first algorithm performs adaptive resets to forget the history, while the second is last-step min-max optimal in context of a drift. We analyze both algorithms in the worst-case regret framework and show that they maintain an average loss close to that of the best slowly changing sequence of linear functions, as long as the cumulative drift is sublinear. In addition, in the stationary case, when no drift occurs, our algorithms suffer logarithmic regret, as for previous algorithms. Our bounds improve over the existing ones, and simulations demonstrate the usefulness of these algorithms compared with other state-of-the-art approaches.", "source": "arxiv/ml"}
{"id": "arxiv:2887", "title": "Exploiting the Accumulated Evidence for Gene Selection in Microarray Gene Expression Data", "text": "Machine Learning methods have of late made significant efforts to solving multidisciplinary problems in the field of cancer classification using microarray gene expression data. Feature subset selection methods can play an important role in the modeling process, since these tasks are characterized by a large number of features and a few observations, making the modeling a non-trivial undertaking. In this particular scenario, it is extremely important to select genes by taking into account the possible interactions with other gene subsets. This paper shows that, by accumulating the evidence in favour (or against) each gene along the search process, the obtained gene subsets may constitute better solutions, either in terms of predictive accuracy or gene size, or in both. The proposed technique is extremely simple and applicable at a negligible overhead in cost.", "source": "arxiv/ml"}
{"id": "arxiv:2888", "title": "Inverse Signal Classification for Financial Instruments", "text": "The paper presents new machine learning methods: signal composition, which classifies time-series regardless of length, type, and quantity; and self-labeling, a supervised-learning enhancement. The paper describes further the implementation of the methods on a financial search engine system using a collection of 7,881 financial instruments traded during 2011 to identify inverse behavior among the time-series.", "source": "arxiv/ml"}
{"id": "arxiv:2889", "title": "One-Class Support Measure Machines for Group Anomaly Detection", "text": "We propose one-class support measure machines (OCSMMs) for group anomaly detection which aims at recognizing anomalous aggregate behaviors of data points. The OCSMMs generalize well-known one-class support vector machines (OCSVMs) to a space of probability measures. By formulating the problem as quantile estimation on distributions, we can establish an interesting connection to the OCSVMs and variable kernel density estimators (VKDEs) over the input space on which the distributions are defined, bridging the gap between large-margin methods and kernel density estimators. In particular, we show that various types of VKDEs can be considered as solutions to a class of regularization problems studied in this paper. Experiments on Sloan Digital Sky Survey dataset and High Energy Particle Physics dataset demonstrate the benefits of the proposed framework in real-world applications.", "source": "arxiv/ml"}
{"id": "arxiv:2890", "title": "Learning Hash Functions Using Column Generation", "text": "Fast nearest neighbor searching is becoming an increasingly important tool in solving many large-scale problems. Recently a number of approaches to learning data-dependent hash functions have been developed. In this work, we propose a column generation based method for learning data-dependent hash functions on the basis of proximity comparison information. Given a set of triplets that encode the pairwise proximity comparison information, our method learns hash functions that preserve the relative comparison relationships in the data as well as possible within the large-margin learning framework. The learning procedure is implemented using column generation and hence is named CGHash. At each iteration of the column generation procedure, the best hash function is selected. Unlike most other hashing methods, our method generalizes to new data points naturally; and has a training objective which is convex, thus ensuring that the global optimum can be identified. Experiments demonstrate that the proposed method learns compact binary codes and that its retrieval performance compares favorably with state-of-the-art methods when tested on a few benchmark datasets.", "source": "arxiv/ml"}
{"id": "arxiv:2891", "title": "Matrix Completion via Max-Norm Constrained Optimization", "text": "Matrix completion has been well studied under the uniform sampling model and the trace-norm regularized methods perform well both theoretically and numerically in such a setting. However, the uniform sampling model is unrealistic for a range of applications and the standard trace-norm relaxation can behave very poorly when the underlying sampling scheme is non-uniform. In this paper we propose and analyze a max-norm constrained empirical risk minimization method for noisy matrix completion under a general sampling model. The optimal rate of convergence is established under the Frobenius norm loss in the context of approximately low-rank matrix reconstruction. It is shown that the max-norm constrained method is minimax rate-optimal and yields a unified and robust approximate recovery guarantee, with respect to the sampling distributions. The computational effectiveness of this method is also discussed, based on first-order algorithms for solving convex optimizations involving max-norm regularization.", "source": "arxiv/ml"}
{"id": "arxiv:2892", "title": "Inductive Sparse Subspace Clustering", "text": "Sparse Subspace Clustering (SSC) has achieved state-of-the-art clustering quality by performing spectral clustering over a $\\ell^{1}$-norm based similarity graph. However, SSC is a transductive method which does not handle with the data not used to construct the graph (out-of-sample data). For each new datum, SSC requires solving $n$ optimization problems in O(n) variables for performing the algorithm over the whole data set, where $n$ is the number of data points. Therefore, it is inefficient to apply SSC in fast online clustering and scalable graphing. In this letter, we propose an inductive spectral clustering algorithm, called inductive Sparse Subspace Clustering (iSSC), which makes SSC feasible to cluster out-of-sample data. iSSC adopts the assumption that high-dimensional data actually lie on the low-dimensional manifold such that out-of-sample data could be grouped in the embedding space learned from in-sample data. Experimental results show that iSSC is promising in clustering out-of-sample data.", "source": "arxiv/ml"}
{"id": "arxiv:2893", "title": "Sparse PCA through Low-rank Approximations", "text": "We introduce a novel algorithm that computes the $k$-sparse principal component of a positive semidefinite matrix $A$. Our algorithm is combinatorial and operates by examining a discrete set of special vectors lying in a low-dimensional eigen-subspace of $A$. We obtain provable approximation guarantees that depend on the spectral decay profile of the matrix: the faster the eigenvalue decay, the better the quality of our approximation. For example, if the eigenvalues of $A$ follow a power-law decay, we obtain a polynomial-time approximation algorithm for any desired accuracy. A key algorithmic component of our scheme is a combinatorial feature elimination step that is provably safe and in practice significantly reduces the running complexity of our algorithm. We implement our algorithm and test it on multiple artificial and real data sets. Due to the feature elimination step, it is possible to perform sparse PCA on data sets consisting of millions of entries in a few minutes. Our experimental evaluation shows that our scheme is nearly optimal while finding very sparse vectors. We compare to the prior state of the art and show that our scheme matches or outperforms previous algorithms in all tested data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2894", "title": "Top-down particle filtering for Bayesian decision trees", "text": "Decision tree learning is a popular approach for classification and regression in machine learning and statistics, and Bayesian formulations---which introduce a prior distribution over decision trees, and formulate learning as posterior inference given data---have been shown to produce competitive performance. Unlike classic decision tree learning algorithms like ID3, C4.5 and CART, which work in a top-down manner, existing Bayesian algorithms produce an approximation to the posterior distribution by evolving a complete tree (or collection thereof) iteratively via local Monte Carlo modifications to the structure of the tree, e.g., using Markov chain Monte Carlo (MCMC). We present a sequential Monte Carlo (SMC) algorithm that instead works in a top-down manner, mimicking the behavior and speed of classic algorithms. We demonstrate empirically that our approach delivers accuracy comparable to the most popular MCMC method, but operates more than an order of magnitude faster, and thus represents a better computation-accuracy tradeoff.", "source": "arxiv/ml"}
{"id": "arxiv:2895", "title": "Bayesian Compressed Regression", "text": "As an alternative to variable selection or shrinkage in high dimensional regression, we propose to randomly compress the predictors prior to analysis. This dramatically reduces storage and computational bottlenecks, performing well when the predictors can be projected to a low dimensional linear subspace with minimal loss of information about the response. As opposed to existing Bayesian dimensionality reduction approaches, the exact posterior distribution conditional on the compressed data is available analytically, speeding up computation by many orders of magnitude while also bypassing robustness issues due to convergence and mixing problems with MCMC. Model averaging is used to reduce sensitivity to the random projection matrix, while accommodating uncertainty in the subspace dimension. Strong theoretical support is provided for the approach by showing near parametric convergence rates for the predictive density in the large p small n asymptotic paradigm. Practical performance relative to competitors is illustrated in simulations and real data applications.", "source": "arxiv/ml"}
{"id": "arxiv:2896", "title": "Denoising Deep Neural Networks Based Voice Activity Detection", "text": "Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this paper, we propose a denoising-deep-neural-network (DDNN) based VAD to address the aforementioned problem. Specifically, we pre-train a deep neural network in a special unsupervised denoising greedy layer-wise mode, and then fine-tune the whole network in a supervised way by the common back-propagation algorithm. In the pre-training phase, we take the noisy speech signals as the visible layer and try to extract a new feature that minimizes the reconstruction cross-entropy loss between the noisy speech signals and its corresponding clean speech signals. Experimental results show that the proposed DDNN-based VAD not only outperforms the DBN-based VAD but also shows an apparent performance improvement of the deep layers over shallower layers.", "source": "arxiv/ml"}
{"id": "arxiv:2897", "title": "Personalized News Recommendation with Context Trees", "text": "The profusion of online news articles makes it difficult to find interesting articles, a problem that can be assuaged by using a recommender system to bring the most relevant news stories to readers. However, news recommendation is challenging because the most relevant articles are often new content seen by few users. In addition, they are subject to trends and preference changes over time, and in many cases we do not have sufficient information to profile the reader. In this paper, we introduce a class of news recommendation systems based on context trees. They can provide high-quality news recommendation to anonymous visitors based on present browsing behaviour. We show that context-tree recommender systems provide good prediction accuracy and recommendation novelty, and they are sufficiently flexible to capture the unique properties of news articles.", "source": "arxiv/ml"}
{"id": "arxiv:2898", "title": "Learning AMP Chain Graphs and some Marginal Models Thereof under Faithfulness: Extended Version", "text": "This paper deals with chain graphs under the Andersson-Madigan-Perlman (AMP) interpretation. In particular, we present a constraint based algorithm for learning an AMP chain graph a given probability distribution is faithful to. Moreover, we show that the extension of Meek's conjecture to AMP chain graphs does not hold, which compromises the development of efficient and correct score+search learning algorithms under assumptions weaker than faithfulness. We also introduce a new family of graphical models that consists of undirected and bidirected edges. We name this new family maximal covariance-concentration graphs (MCCGs) because it includes both covariance and concentration graphs as subfamilies. However, every MCCG can be seen as the result of marginalizing out some nodes in an AMP CG. We describe global, local and pairwise Markov properties for MCCGs and prove their equivalence. We characterize when two MCCGs are Markov equivalent, and show that every Markov equivalence class of MCCGs has a distinguished member. We present a constraint based algorithm for learning a MCCG a given probability distribution is faithful to. Finally, we present a graphical criterion for reading dependencies from a MCCG of a probability distribution that satisfies the graphoid properties, weak transitivity and composition. We prove that the criterion is sound and complete in certain sense.", "source": "arxiv/ml"}
{"id": "arxiv:2899", "title": "Multivariate Temporal Dictionary Learning for EEG", "text": "This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a data-driven method to obtain an adapted dictionary. To reach an efficient dictionary learning, appropriate spatial and temporal modeling is required. Inter-channels links are taken into account in the spatial multivariate model, and shift-invariance is used for the temporal model. Multivariate learned kernels are informative (a few atoms code plentiful energy) and interpretable (the atoms can have a physiological meaning). Using real EEG data, the proposed method is shown to outperform the classical multichannel matching pursuit used with a Gabor dictionary, as measured by the representative power of the learned dictionary and its spatial flexibility. Moreover, dictionary learning can capture interpretable patterns: this ability is illustrated on real data, learning a P300 evoked potential.", "source": "arxiv/ml"}
{"id": "arxiv:2900", "title": "Riemannian metrics for neural networks I: feedforward networks", "text": "We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradient using the Fisher information matrix, or on Hessian methods, scaled down in a specific way to allow for scalability while keeping some of their key mathematical properties.", "source": "arxiv/ml"}
{"id": "arxiv:2901", "title": "GURLS: a Least Squares Library for Supervised Learning", "text": "We present GURLS, a least squares, modular, easy-to-extend software library for efficient supervised learning. GURLS is targeted to machine learning practitioners, as well as non-specialists. It offers a number state-of-the-art training strategies for medium and large-scale learning, and routines for efficient model selection. The library is particularly well suited for multi-output problems (multi-category/multi-label). GURLS is currently available in two independent implementations: Matlab and C++. It takes advantage of the favorable properties of regularized least squares algorithm to exploit advanced tools in linear algebra. Routines to handle computations with very large matrices by means of memory-mapped storage and distributed task execution are available. The package is distributed under the BSD licence and is available for download at https://github.com/CBCL/GURLS.", "source": "arxiv/ml"}
{"id": "arxiv:2902", "title": "An Equivalence between the Lasso and Support Vector Machines", "text": "We investigate the relation of two fundamental tools in machine learning and signal processing, that is the support vector machine (SVM) for classification, and the Lasso technique used in regression. We show that the resulting optimization problems are equivalent, in the following sense. Given any instance of an $\\ell_2$-loss soft-margin (or hard-margin) SVM, we construct a Lasso instance having the same optimal solutions, and vice versa. As a consequence, many existing optimization algorithms for both SVMs and Lasso can also be applied to the respective other problem instances. Also, the equivalence allows for many known theoretical insights for SVM and Lasso to be translated between the two settings. One such implication gives a simple kernelized version of the Lasso, analogous to the kernels used in the SVM setting. Another consequence is that the sparsity of a Lasso solution is equal to the number of support vectors for the corresponding SVM instance, and that one can use screening rules to prune the set of support vectors. Furthermore, we can relate sublinear time algorithms for the two problems, and give a new such algorithm variant for the Lasso. We also study the regularization paths for both methods.", "source": "arxiv/ml"}
{"id": "arxiv:2903", "title": "Classification with Asymmetric Label Noise: Consistency and Maximal Denoising", "text": "In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are known. In this work, we give conditions that are necessary and sufficient for the true class-conditional distributions to be identifiable. These conditions are weaker than those analyzed previously, and allow for the classes to be nonseparable and the noise levels to be asymmetric and unknown. The conditions essentially state that a majority of the observed labels are correct and that the true class-conditional distributions are \"mutually irreducible,\" a concept we introduce that limits the similarity of the two distributions. For any label noise problem, there is a unique pair of true class-conditional distributions satisfying the proposed conditions, and we argue that this pair corresponds in a certain sense to maximal denoising of the observed distributions. Our results are facilitated by a connection to \"mixture proportion estimation,\" which is the problem of estimating the maximal proportion of one distribution that is present in another. We establish a novel rate of convergence result for mixture proportion estimation, and apply this to obtain consistency of a discrimination rule based on surrogate loss minimization. Experimental results on benchmark data and a nuclear particle classification problem demonstrate the efficacy of our approach.", "source": "arxiv/ml"}
{"id": "arxiv:2904", "title": "Discovery of factors in matrices with grades", "text": "We present an approach to decomposition and factor analysis of matrices with ordinal data. The matrix entries are grades to which objects represented by rows satisfy attributes represented by columns, e.g. grades to which an image is red, a product has a given feature, or a person performs well in a test. We assume that the grades form a bounded scale equipped with certain aggregation operators and conforms to the structure of a complete residuated lattice. We present a greedy approximation algorithm for the problem of decomposition of such matrix in a product of two matrices with grades under the restriction that the number of factors be small. Our algorithm is based on a geometric insight provided by a theorem identifying particular rectangular-shaped submatrices as optimal factors for the decompositions. These factors correspond to formal concepts of the input data and allow an easy interpretation of the decomposition. We present illustrative examples and experimental evaluation.", "source": "arxiv/ml"}
{"id": "arxiv:2905", "title": "Convex and Scalable Weakly Labeled SVMs", "text": "In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete. This includes, for example, (i) semi-supervised learning where labels are partially known; (ii) multi-instance learning where labels are implicitly known; and (iii) clustering where labels are completely unknown. Unlike supervised learning, learning with weak labels involves a difficult Mixed-Integer Programming (MIP) problem. Therefore, it can suffer from poor scalability and may also get stuck in local minimum. In this paper, we focus on SVMs and propose the WellSVM via a novel label generation strategy. This leads to a convex relaxation of the original MIP, which is at least as tight as existing convex Semi-Definite Programming (SDP) relaxations. Moreover, the WellSVM can be solved via a sequence of SVM subproblems that are much more scalable than previous convex SDP relaxations. Experiments on three weakly labeled learning tasks, namely, (i) semi-supervised learning; (ii) multi-instance learning for locating regions of interest in content-based information retrieval; and (iii) clustering, clearly demonstrate improved performance, and WellSVM is also readily applicable on large data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2906", "title": "Large-Margin Metric Learning for Partitioning Problems", "text": "In this paper, we consider unsupervised partitioning problems, such as clustering, image segmentation, video segmentation and other change-point detection problems. We focus on partitioning problems based explicitly or implicitly on the minimization of Euclidean distortions, which include mean-based change-point detection, K-means, spectral clustering and normalized cuts. Our main goal is to learn a Mahalanobis metric for these unsupervised problems, leading to feature weighting and/or selection. This is done in a supervised way by assuming the availability of several potentially partially labelled datasets that share the same metric. We cast the metric learning problem as a large-margin structured prediction problem, with proper definition of regularizers and losses, leading to a convex optimization problem which can be solved efficiently with iterative techniques. We provide experiments where we show how learning the metric may significantly improve the partitioning performance in synthetic examples, bioinformatics, video segmentation and image segmentation problems.", "source": "arxiv/ml"}
{"id": "arxiv:2907", "title": "Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss", "text": "We propose a modular framework for multi-relational learning via tensor decomposition. In our learning setting, the training data contains multiple types of relationships among a set of objects, which we represent by a sparse three-mode tensor. The goal is to predict the values of the missing entries. To do so, we model each relationship as a function of a linear combination of latent factors. We learn this latent representation by computing a low-rank tensor decomposition, using quasi-Newton optimization of a weighted objective function. Sparsity in the observed data is captured by the weighted objective, leading to improved accuracy when training data is limited. Exploiting sparsity also improves efficiency, potentially up to an order of magnitude over unweighted approaches. In addition, our framework accommodates arbitrary combinations of smooth, task-specific loss functions, making it better suited for learning different types of relations. For the typical cases of real-valued functions and binary relations, we propose several loss functions and derive the associated parameter gradients. We evaluate our method on synthetic and real data, showing significant improvements in both accuracy and scalability over related factorization techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2908", "title": "Revisiting the Nystrom Method for Improved Large-Scale Machine Learning", "text": "We reconsider randomized algorithms for the low-rank approximation of symmetric positive semi-definite (SPSD) matrices such as Laplacian and kernel matrices that arise in data analysis and machine learning applications. Our main results consist of an empirical evaluation of the performance quality and running time of sampling and projection methods on a diverse suite of SPSD matrices. Our results highlight complementary aspects of sampling versus projection methods; they characterize the effects of common data preprocessing steps on the performance of these algorithms; and they point to important differences between uniform sampling and nonuniform sampling methods based on leverage scores. In addition, our empirical results illustrate that existing theory is so weak that it does not provide even a qualitative guide to practice. Thus, we complement our empirical results with a suite of worst-case theoretical bounds for both random sampling and random projection methods. These bounds are qualitatively superior to existing bounds---e.g. improved additive-error bounds for spectral and Frobenius norm error and relative-error bounds for trace norm error---and they point to future directions to make these algorithms useful in even larger-scale machine learning applications.", "source": "arxiv/ml"}
{"id": "arxiv:2909", "title": "Mining Representative Unsubstituted Graph Patterns Using Prior Similarity Matrix", "text": "One of the most powerful techniques to study protein structures is to look for recurrent fragments (also called substructures or spatial motifs), then use them as patterns to characterize the proteins under study. An emergent trend consists in parsing proteins three-dimensional (3D) structures into graphs of amino acids. Hence, the search of recurrent spatial motifs is formulated as a process of frequent subgraph discovery where each subgraph represents a spatial motif. In this scope, several efficient approaches for frequent subgraph discovery have been proposed in the literature. However, the set of discovered frequent subgraphs is too large to be efficiently analyzed and explored in any further process. In this paper, we propose a novel pattern selection approach that shrinks the large number of discovered frequent subgraphs by selecting the representative ones. Existing pattern selection approaches do not exploit the domain knowledge. Yet, in our approach we incorporate the evolutionary information of amino acids defined in the substitution matrices in order to select the representative subgraphs. We show the effectiveness of our approach on a number of real datasets. The results issued from our experiments show that our approach is able to considerably decrease the number of motifs while enhancing their interestingness.", "source": "arxiv/ml"}
{"id": "arxiv:2910", "title": "Transfer Learning for Voice Activity Detection: A Denoising Deep Neural Network Perspective", "text": "Mismatching problem between the source and target noisy corpora severely hinder the practical use of the machine-learning-based voice activity detection (VAD). In this paper, we try to address this problem in the transfer learning prospective. Transfer learning tries to find a common learning machine or a common feature subspace that is shared by both the source corpus and the target corpus. The denoising deep neural network is used as the learning machine. Three transfer techniques, which aim to learn common feature representations, are used for analysis. Experimental results demonstrate the effectiveness of the transfer learning schemes on the mismatch problem.", "source": "arxiv/ml"}
{"id": "arxiv:2911", "title": "Convex Discriminative Multitask Clustering", "text": "Multitask clustering tries to improve the clustering performance of multiple tasks simultaneously by taking their relationship into account. Most existing multitask clustering algorithms fall into the type of generative clustering, and none are formulated as convex optimization problems. In this paper, we propose two convex Discriminative Multitask Clustering (DMTC) algorithms to address the problems. Specifically, we first propose a Bayesian DMTC framework. Then, we propose two convex DMTC objectives within the framework. The first one, which can be seen as a technical combination of the convex multitask feature learning and the convex Multiclass Maximum Margin Clustering (M3C), aims to learn a shared feature representation. The second one, which can be seen as a combination of the convex multitask relationship learning and M3C, aims to learn the task relationship. The two objectives are solved in a uniform procedure by the efficient cutting-plane algorithm. Experimental results on a toy problem and two benchmark datasets demonstrate the effectiveness of the proposed algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2912", "title": "Heuristic Ternary Error-Correcting Output Codes Via Weight Optimization and Layered Clustering-Based Approach", "text": "One important classifier ensemble for multiclass classification problems is Error-Correcting Output Codes (ECOCs). It bridges multiclass problems and binary-class classifiers by decomposing multiclass problems to a serial binary-class problems. In this paper, we present a heuristic ternary code, named Weight Optimization and Layered Clustering-based ECOC (WOLC-ECOC). It starts with an arbitrary valid ECOC and iterates the following two steps until the training risk converges. The first step, named Layered Clustering based ECOC (LC-ECOC), constructs multiple strong classifiers on the most confusing binary-class problem. The second step adds the new classifiers to ECOC by a novel Optimized Weighted (OW) decoding algorithm, where the optimization problem of the decoding is solved by the cutting plane algorithm. Technically, LC-ECOC makes the heuristic training process not blocked by some difficult binary-class problem. OW decoding guarantees the non-increase of the training risk for ensuring a small code length. Results on 14 UCI datasets and a music genre classification problem demonstrate the effectiveness of WOLC-ECOC.", "source": "arxiv/ml"}
{"id": "arxiv:2913", "title": "Complex Support Vector Machines for Regression and Quaternary Classification", "text": "The paper presents a new framework for complex Support Vector Regression as well as Support Vector Machines for quaternary classification. The method exploits the notion of widely linear estimation to model the input-out relation for complex-valued data and considers two cases: a) the complex data are split into their real and imaginary parts and a typical real kernel is employed to map the complex data to a complexified feature space and b) a pure complex kernel is used to directly map the data to the induced complex feature space. The recently developed Wirtinger's calculus on complex reproducing kernel Hilbert spaces (RKHS) is employed in order to compute the Lagrangian and derive the dual optimization problem. As one of our major results, we prove that any complex SVM/SVR task is equivalent with solving two real SVM/SVR tasks exploiting a specific real kernel which is generated by the chosen complex kernel. In particular, the case of pure complex kernels leads to the generation of new kernels, which have not been considered before. In the classification case, the proposed framework inherently splits the complex space into four parts. This leads naturally in solving the four class-task (quaternary classification), instead of the typical two classes of the real SVM. In turn, this rationale can be used in a multiclass problem as a split-class scenario based on four classes, as opposed to the one-versus-all method; this can lead to significant computational savings. Experiments demonstrate the effectiveness of the proposed framework for regression and classification tasks that involve complex data.", "source": "arxiv/ml"}
{"id": "arxiv:2914", "title": "Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds", "text": "Relationships between entities in datasets are often of multiple nature, like geographical distance, social relationships, or common interests among people in a social network, for example. This information can naturally be modeled by a set of weighted and undirected graphs that form a global multilayer graph, where the common vertex set represents the entities and the edges on different layers capture the similarities of the entities in term of the different modalities. In this paper, we address the problem of analyzing multi-layer graphs and propose methods for clustering the vertices by efficiently merging the information provided by the multiple modalities. To this end, we propose to combine the characteristics of individual graph layers using tools from subspace analysis on a Grassmann manifold. The resulting combination can then be viewed as a low dimensional representation of the original data which preserves the most important information from diverse relationships between entities. We use this information in new clustering methods and test our algorithm on several synthetic and real world datasets where we demonstrate superior or competitive performances compared to baseline and state-of-the-art techniques. Our generic framework further extends to numerous analysis and learning problems that involve different types of information on graphs.", "source": "arxiv/ml"}
{"id": "arxiv:2915", "title": "Penalty-regulated dynamics and robust learning procedures in games", "text": "Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space repelling. These penalty-regulated dynamics are equivalent to players keeping an exponentially discounted aggregate of their on-going payoffs and then using a smooth best response to pick an action based on these performance scores. Owing to this inherent duality, the proposed dynamics satisfy a variant of the folk theorem of evolutionary game theory and they converge to (arbitrarily precise) approximations of Nash equilibria in potential games. Motivated by applications to traffic engineering, we exploit this duality further to design a discrete-time, payoff-based learning algorithm which retains these convergence properties and only requires players to observe their in-game payoffs: moreover, the algorithm remains robust in the presence of stochastic perturbations and observation errors, and it does not require any synchronization between players.", "source": "arxiv/ml"}
{"id": "arxiv:2916", "title": "Mini-Batch Primal and Dual Methods for SVMs", "text": "We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss.", "source": "arxiv/ml"}
{"id": "arxiv:2917", "title": "State estimation under non-Gaussian Levy noise: A modified Kalman filtering method", "text": "The Kalman filter is extensively used for state estimation for linear systems under Gaussian noise. When non-Gaussian L\\'evy noise is present, the conventional Kalman filter may fail to be effective due to the fact that the non-Gaussian L\\'evy noise may have infinite variance. A modified Kalman filter for linear systems with non-Gaussian L\\'evy noise is devised. It works effectively with reasonable computational cost. Simulation results are presented to illustrate this non-Gaussian filtering method.", "source": "arxiv/ml"}
{"id": "arxiv:2918", "title": "Linear NDCG and Pair-wise Loss", "text": "Linear NDCG is used for measuring the performance of the Web content quality assessment in ECML/PKDD Discovery Challenge 2010. In this paper, we will prove that the DCG error equals a new pair-wise loss.", "source": "arxiv/ml"}
{"id": "arxiv:2919", "title": "Monte-Carlo utility estimates for Bayesian reinforcement learning", "text": "This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly, gradient-based algorithms for approximate upper and lower bounds are introduced. Finally, we introduce a new class of gradient algorithms for Bayesian Bellman error minimisation. We theoretically show that the gradient methods are sound. Experimentally, we demonstrate the superiority of the upper bound method in terms of reward obtained. However, we also show that the Bayesian Bellman error method is a close second, despite its significant computational simplicity.", "source": "arxiv/ml"}
{"id": "arxiv:2920", "title": "Revealing Cluster Structure of Graph by Path Following Replicator Dynamic", "text": "In this paper, we propose a path following replicator dynamic, and investigate its potentials in uncovering the underlying cluster structure of a graph. The proposed dynamic is a generalization of the discrete replicator dynamic. The replicator dynamic has been successfully used to extract dense clusters of graphs; however, it is often sensitive to the degree distribution of a graph, and usually biased by vertices with large degrees, thus may fail to detect the densest cluster. To overcome this problem, we introduce a dynamic parameter, called path parameter, into the evolution process. The path parameter can be interpreted as the maximal possible probability of a current cluster containing a vertex, and it monotonically increases as evolution process proceeds. By limiting the maximal probability, the phenomenon of some vertices dominating the early stage of evolution process is suppressed, thus making evolution process more robust. To solve the optimization problem with a fixed path parameter, we propose an efficient fixed point algorithm. The time complexity of the path following replicator dynamic is only linear in the number of edges of a graph, thus it can analyze graphs with millions of vertices and tens of millions of edges on a common PC in a few minutes. Besides, it can be naturally generalized to hypergraph and graph with edges of different orders. We apply it to four important problems: maximum clique problem, densest k-subgraph problem, structure fitting, and discovery of high-density regions. The extensive experimental results clearly demonstrate its advantages, in terms of robustness, scalability and flexility.", "source": "arxiv/ml"}
{"id": "arxiv:2921", "title": "Hybrid Q-Learning Applied to Ubiquitous recommender system", "text": "Ubiquitous information access becomes more and more important nowadays and research is aimed at making it adapted to users. Our work consists in applying machine learning techniques in order to bring a solution to some of the problems concerning the acceptance of the system by users. To achieve this, we propose a fundamental shift in terms of how we model the learning of recommender system: inspired by models of human reasoning developed in robotic, we combine reinforcement learning and case-base reasoning to define a recommendation process that uses these two approaches for generating recommendations on different context dimensions (social, temporal, geographic). We describe an implementation of the recommender system based on this framework. We also present preliminary results from experiments with the system and show how our approach increases the recommendation quality.", "source": "arxiv/ml"}
{"id": "arxiv:2922", "title": "Spectral Clustering with Epidemic Diffusion", "text": "Spectral clustering is widely used to partition graphs into distinct modules or communities. Existing methods for spectral clustering use the eigenvalues and eigenvectors of the graph Laplacian, an operator that is closely associated with random walks on graphs. We propose a new spectral partitioning method that exploits the properties of epidemic diffusion. An epidemic is a dynamic process that, unlike the random walk, simultaneously transitions to all the neighbors of a given node. We show that the replicator, an operator describing epidemic diffusion, is equivalent to the symmetric normalized Laplacian of a reweighted graph with edges reweighted by the eigenvector centralities of their incident nodes. Thus, more weight is given to edges connecting more central nodes. We describe a method that partitions the nodes based on the componentwise ratio of the replicator's second eigenvector to the first, and compare its performance to traditional spectral clustering techniques on synthetic graphs with known community structure. We demonstrate that the replicator gives preference to dense, clique-like structures, enabling it to more effectively discover communities that may be obscured by dense intercommunity linking.", "source": "arxiv/ml"}
{"id": "arxiv:2923", "title": "Machine Learning for Bioclimatic Modelling", "text": "Many machine learning (ML) approaches are widely used to generate bioclimatic models for prediction of geographic range of organism as a function of climate. Applications such as prediction of range shift in organism, range of invasive species influenced by climate change are important parameters in understanding the impact of climate change. However, success of machine learning-based approaches depends on a number of factors. While it can be safely said that no particular ML technique can be effective in all applications and success of a technique is predominantly dependent on the application or the type of the problem, it is useful to understand their behavior to ensure informed choice of techniques. This paper presents a comprehensive review of machine learning-based bioclimatic model generation and analyses the factors influencing success of such models. Considering the wide use of statistical techniques, in our discussion we also include conventional statistical techniques used in bioclimatic modelling.", "source": "arxiv/ml"}
{"id": "arxiv:2924", "title": "A Cooperative Q-learning Approach for Real-time Power Allocation in Femtocell Networks", "text": "In this paper, we address the problem of distributed interference management of cognitive femtocells that share the same frequency range with macrocells (primary user) using distributed multi-agent Q-learning. We formulate and solve three problems representing three different Q-learning algorithms: namely, centralized, distributed and partially distributed power control using Q-learning (CPC-Q, DPC-Q and PDPC-Q). CPCQ, although not of practical interest, characterizes the global optimum. Each of DPC-Q and PDPC-Q works in two different learning paradigms: Independent (IL) and Cooperative (CL). The former is considered the simplest form for applying Qlearning in multi-agent scenarios, where all the femtocells learn independently. The latter is the proposed scheme in which femtocells share partial information during the learning process in order to strike a balance between practical relevance and performance. In terms of performance, the simulation results showed that the CL paradigm outperforms the IL paradigm and achieves an aggregate femtocells capacity that is very close to the optimal one. For the practical relevance issue, we evaluate the robustness and scalability of DPC-Q, in real time, by deploying new femtocells in the system during the learning process, where we showed that DPC-Q in the CL paradigm is scalable to large number of femtocells and more robust to the network dynamics compared to the IL paradigm", "source": "arxiv/ml"}
{"id": "arxiv:2925", "title": "Gaussian Processes for Nonlinear Signal Processing", "text": "Gaussian processes (GPs) are versatile tools that have been successfully employed to solve nonlinear estimation problems in machine learning, but that are rarely used in signal processing. In this tutorial, we present GPs for regression as a natural nonlinear extension to optimal Wiener filtering. After establishing their basic formulation, we discuss several important aspects and extensions, including recursive and adaptive algorithms for dealing with non-stationarity, low-complexity solutions, non-Gaussian noise models and classification scenarios. Furthermore, we provide a selection of relevant applications to wireless digital communications.", "source": "arxiv/ml"}
{"id": "arxiv:2926", "title": "Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions", "text": "We study the problem of learning Markov decision processes with finite state and action spaces when the transition probability distributions and loss functions are chosen adversarially and are allowed to change with time. We introduce an algorithm whose regret with respect to any policy in a comparison class grows as the square root of the number of rounds of the game, provided the transition probabilities satisfy a uniform mixing condition. Our approach is efficient as long as the comparison class is polynomial and we can compute expectations over sample paths for each policy. Designing an efficient algorithm with small regret for the general case remains an open problem.", "source": "arxiv/ml"}
{"id": "arxiv:2927", "title": "A Greedy Approximation of Bayesian Reinforcement Learning with Probably Optimistic Transition Model", "text": "Bayesian Reinforcement Learning (RL) is capable of not only incorporating domain knowledge, but also solving the exploration-exploitation dilemma in a natural way. As Bayesian RL is intractable except for special cases, previous work has proposed several approximation methods. However, these methods are usually too sensitive to parameter values, and finding an acceptable parameter setting is practically impossible in many applications. In this paper, we propose a new algorithm that greedily approximates Bayesian RL to achieve robustness in parameter space. We show that for a desired learning behavior, our proposed algorithm has a polynomial sample complexity that is lower than those of existing algorithms. We also demonstrate that the proposed algorithm naturally outperforms other existing algorithms when the prior distributions are not significantly misleading. On the other hand, the proposed algorithm cannot handle greatly misspecified priors as well as the other algorithms can. This is a natural consequence of the fact that the proposed algorithm is greedier than the other algorithms. Accordingly, we discuss a way to select an appropriate algorithm for different tasks based on the algorithms' greediness. We also introduce a new way of simplifying Bayesian planning, based on which future work would be able to derive new algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2928", "title": "Toggling a Genetic Switch Using Reinforcement Learning", "text": "In this paper, we consider the problem of optimal exogenous control of gene regulatory networks. Our approach consists in adapting an established reinforcement learning algorithm called the fitted Q iteration. This algorithm infers the control law directly from the measurements of the system's response to external control inputs without the use of a mathematical model of the system. The measurement data set can either be collected from wet-lab experiments or artificially created by computer simulations of dynamical models of the system. The algorithm is applicable to a wide range of biological systems due to its ability to deal with nonlinear and stochastic system dynamics. To illustrate the application of the algorithm to a gene regulatory network, the regulation of the toggle switch system is considered. The control objective of this problem is to drive the concentrations of two specific proteins to a target region in the state space.", "source": "arxiv/ml"}
{"id": "arxiv:2929", "title": "Group-Sparse Model Selection: Hardness and Relaxations", "text": "Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. The main promise of these models is the recovery of \"interpretable\" signals through the identification of their constituent groups. In this paper, we establish a combinatorial framework for group-model selection problems and highlight the underlying tractability issues. In particular, we show that the group-model selection problem is equivalent to the well-known NP-hard weighted maximum coverage problem (WMC). Leveraging a graph-based understanding of group models, we describe group structures which enable correct model selection in polynomial time via dynamic programming. Furthermore, group structures that lead to totally unimodular constraints have tractable discrete as well as convex relaxations. We also present a generalization of the group-model that allows for within group sparsity, which can be used to model hierarchical sparsity. Finally, we study the Pareto frontier of group-sparse approximations for two tractable models, among which the tree sparsity model, and illustrate selection and computation trade-offs between our framework and the existing convex relaxations.", "source": "arxiv/ml"}
{"id": "arxiv:2930", "title": "A Unified Framework for Probabilistic Component Analysis", "text": "We present a unifying framework which reduces the construction of probabilistic component analysis techniques to a mere selection of the latent neighbourhood, thus providing an elegant and principled framework for creating novel component analysis models as well as constructing probabilistic equivalents of deterministic component analysis methods. Under our framework, we unify many very popular and well-studied component analysis algorithms, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Locality Preserving Projections (LPP) and Slow Feature Analysis (SFA), some of which have no probabilistic equivalents in literature thus far. We firstly define the Markov Random Fields (MRFs) which encapsulate the latent connectivity of the aforementioned component analysis techniques; subsequently, we show that the projection directions produced by all PCA, LDA, LPP and SFA are also produced by the Maximum Likelihood (ML) solution of a single joint probability density function, composed by selecting one of the defined MRF priors while utilising a simple observation model. Furthermore, we propose novel Expectation Maximization (EM) algorithms, exploiting the proposed joint PDF, while we generalize the proposed methodologies to arbitrary connectivities via parameterizable MRF products. Theoretical analysis and experiments on both simulated and real world data show the usefulness of the proposed framework, by deriving methods which well outperform state-of-the-art equivalents.", "source": "arxiv/ml"}
{"id": "arxiv:2931", "title": "Ranking and combining multiple predictors without labeled data", "text": "In a broad range of classification and decision making problems, one is given the advice or predictions of several classifiers, of unknown reliability, over multiple questions or queries. This scenario is different from the standard supervised setting, where each classifier accuracy can be assessed using available labeled data, and raises two questions: given only the predictions of several classifiers over a large set of unlabeled test data, is it possible to a) reliably rank them; and b) construct a meta-classifier more accurate than most classifiers in the ensemble? Here we present a novel spectral approach to address these questions. First, assuming conditional independence between classifiers, we show that the off-diagonal entries of their covariance matrix correspond to a rank-one matrix. Moreover, the classifiers can be ranked using the leading eigenvector of this covariance matrix, as its entries are proportional to their balanced accuracies. Second, via a linear approximation to the maximum likelihood estimator, we derive the Spectral Meta-Learner (SML), a novel ensemble classifier whose weights are equal to this eigenvector entries. On both simulated and real data, SML typically achieves a higher accuracy than most classifiers in the ensemble and can provide a better starting point than majority voting, for estimating the maximum likelihood solution. Furthermore, SML is robust to the presence of small malicious groups of classifiers designed to veer the ensemble prediction away from the (unknown) ground truth.", "source": "arxiv/ml"}
{"id": "arxiv:2932", "title": "Iterative MapReduce for Large Scale Machine Learning", "text": "Large datasets (\"Big Data\") are becoming ubiquitous because the potential value in deriving insights from data, across a wide range of business and scientific applications, is increasingly recognized. In particular, machine learning - one of the foundational disciplines for data analysis, summarization and inference - on Big Data has become routine at most organizations that operate large clouds, usually based on systems such as Hadoop that support the MapReduce programming paradigm. It is now widely recognized that while MapReduce is highly scalable, it suffers from a critical weakness for machine learning: it does not support iteration. Consequently, one has to program around this limitation, leading to fragile, inefficient code. Further, reliance on the programmer is inherently flawed in a multi-tenanted cloud environment, since the programmer does not have visibility into the state of the system when his or her program executes. Prior work has sought to address this problem by either developing specialized systems aimed at stylized applications, or by augmenting MapReduce with ad hoc support for saving state across iterations (driven by an external loop). In this paper, we advocate support for looping as a first-class construct, and propose an extension of the MapReduce programming paradigm called {\\em Iterative MapReduce}. We then develop an optimizer for a class of Iterative MapReduce programs that cover most machine learning techniques, provide theoretical justifications for the key optimization steps, and empirically demonstrate that system-optimized programs for significant machine learning tasks are competitive with state-of-the-art specialized solutions.", "source": "arxiv/ml"}
{"id": "arxiv:2933", "title": "A survey on sensing methods and feature extraction algorithms for SLAM problem", "text": "This paper is a survey work for a bigger project for designing a Visual SLAM robot to generate 3D dense map of an unknown unstructured environment. A lot of factors have to be considered while designing a SLAM robot. Sensing method of the SLAM robot should be determined by considering the kind of environment to be modeled. Similarly the type of environment determines the suitable feature extraction method. This paper goes through the sensing methods used in some recently published papers. The main objective of this survey is to conduct a comparative study among the current sensing methods and feature extraction algorithms and to extract out the best for our work.", "source": "arxiv/ml"}
{"id": "arxiv:2934", "title": "Statistical Regression to Predict Total Cumulative CPU Usage of MapReduce Jobs", "text": "Recently, businesses have started using MapReduce as a popular computation framework for processing large amount of data, such as spam detection, and different data mining tasks, in both public and private clouds. Two of the challenging questions in such environments are (1) choosing suitable values for MapReduce configuration parameters e.g., number of mappers, number of reducers, and DFS block size, and (2) predicting the amount of resources that a user should lease from the service provider. Currently, the tasks of both choosing configuration parameters and estimating required resources are solely the users responsibilities. In this paper, we present an approach to provision the total CPU usage in clock cycles of jobs in MapReduce environment. For a MapReduce job, a profile of total CPU usage in clock cycles is built from the job past executions with different values of two configuration parameters e.g., number of mappers, and number of reducers. Then, a polynomial regression is used to model the relation between these configuration parameters and total CPU usage in clock cycles of the job. We also briefly study the influence of input data scaling on measured total CPU usage in clock cycles. This derived model along with the scaling result can then be used to provision the total CPU usage in clock cycles of the same jobs with different input data size. We validate the accuracy of our models using three realistic applications (WordCount, Exim MainLog parsing, and TeraSort). Results show that the predicted total CPU usage in clock cycles of generated resource provisioning options are less than 8% of the measured total CPU usage in clock cycles in our 20-node virtual Hadoop cluster.", "source": "arxiv/ml"}
{"id": "arxiv:2935", "title": "Topic Discovery through Data Dependent and Random Projections", "text": "We present algorithms for topic modeling based on the geometry of cross-document word-frequency patterns. This perspective gains significance under the so called separability condition. This is a condition on existence of novel-words that are unique to each topic. We present a suite of highly efficient algorithms based on data-dependent and random projections of word-frequency patterns to identify novel words and associated topics. We will also discuss the statistical guarantees of the data-dependent projections method based on two mild assumptions on the prior density of topic document matrix. Our key insight here is that the maximum and minimum values of cross-document frequency patterns projected along any direction are associated with novel words. While our sample complexity bounds for topic recovery are similar to the state-of-art, the computational complexity of our random projection scheme scales linearly with the number of documents and the number of words per document. We present several experiments on synthetic and real-world datasets to demonstrate qualitative and quantitative merits of our scheme.", "source": "arxiv/ml"}
{"id": "arxiv:2936", "title": "Subspace Clustering via Thresholding and Spectral Clustering", "text": "We consider the problem of clustering a set of high-dimensional data points into sets of low-dimensional linear subspaces. The number of subspaces, their dimensions, and their orientations are unknown. We propose a simple and low-complexity clustering algorithm based on thresholding the correlations between the data points followed by spectral clustering. A probabilistic performance analysis shows that this algorithm succeeds even when the subspaces intersect, and when the dimensions of the subspaces scale (up to a log-factor) linearly in the ambient dimension. Moreover, we prove that the algorithm also succeeds for data points that are subject to erasures with the number of erasures scaling (up to a log-factor) linearly in the ambient dimension. Finally, we propose a simple scheme that provably detects outliers.", "source": "arxiv/ml"}
{"id": "arxiv:2937", "title": "A Last-Step Regression Algorithm for Non-Stationary Online Learning", "text": "The goal of a learner in standard online learning is to maintain an average loss close to the loss of the best-performing single function in some class. In many real-world problems, such as rating or ranking items, there is no single best target function during the runtime of the algorithm, instead the best (local) target function is drifting over time. We develop a novel last-step minmax optimal algorithm in context of a drift. We analyze the algorithm in the worst-case regret framework and show that it maintains an average loss close to that of the best slowly changing sequence of linear functions, as long as the total of drift is sublinear. In some situations, our bound improves over existing bounds, and additionally the algorithm suffers logarithmic regret when there is no drift. We also build on the H_infinity filter and its bound, and develop and analyze a second algorithm for drifting setting. Synthetic simulations demonstrate the advantages of our algorithms in a worst-case constant drift setting.", "source": "arxiv/ml"}
{"id": "arxiv:2938", "title": "A Quorum Sensing Inspired Algorithm for Dynamic Clustering", "text": "Quorum sensing is a decentralized biological process, through which a community of cells with no global awareness coordinate their functional behaviors based solely on cell-medium interactions and local decisions. This paper draws inspirations from quorum sensing and colony competition to derive a new algorithm for data clustering. The algorithm treats each data as a single cell, and uses knowledge of local connectivity to cluster cells into multiple colonies simultaneously. It simulates auto-inducers secretion in quorum sensing to tune the influence radius for each cell. At the same time, sparsely distributed core cells spread their influences to form colonies, and interactions between colonies eventually determine each cell's identity. The algorithm has the flexibility to analyze not only static but also time-varying data, which surpasses the capacity of many existing algorithms. Its stability and convergence properties are established. The algorithm is tested on several applications, including both synthetic and real benchmarks data sets, alleles clustering, community detection, image segmentation. In particular, the algorithm's distinctive capability to deal with time-varying data allows us to experiment it on novel applications such as robotic swarms grouping and switching model identification. We believe that the algorithm's promising performance would stimulate many more exciting applications.", "source": "arxiv/ml"}
{"id": "arxiv:2939", "title": "$l_{2,p}$ Matrix Norm and Its Application in Feature Selection", "text": "Recently, $l_{2,1}$ matrix norm has been widely applied to many areas such as computer vision, pattern recognition, biological study and etc. As an extension of $l_1$ vector norm, the mixed $l_{2,1}$ matrix norm is often used to find jointly sparse solutions. Moreover, an efficient iterative algorithm has been designed to solve $l_{2,1}$-norm involved minimizations. Actually, computational studies have showed that $l_p$-regularization ($0<p<1$) is sparser than $l_1$-regularization, but the extension to matrix norm has been seldom considered. This paper presents a definition of mixed $l_{2,p}$ $(p\\in (0, 1])$ matrix pseudo norm which is thought as both generalizations of $l_p$ vector norm to matrix and $l_{2,1}$-norm to nonconvex cases $(0<p<1)$. Fortunately, an efficient unified algorithm is proposed to solve the induced $l_{2,p}$-norm $(p\\in (0, 1])$ optimization problems. The convergence can also be uniformly demonstrated for all $p\\in (0, 1]$. Typical $p\\in (0,1]$ are applied to select features in computational biology and the experimental results show that some choices of $0<p<1$ do improve the sparse pattern of using $p=1$.", "source": "arxiv/ml"}
{"id": "arxiv:2940", "title": "On multi-class learning through the minimization of the confusion matrix norm", "text": "In imbalanced multi-class classification problems, the misclassification rate as an error measure may not be a relevant choice. Several methods have been developed where the performance measure retained richer information than the mere misclassification rate: misclassification costs, ROC-based information, etc. Following this idea of dealing with alternate measures of performance, we propose to address imbalanced classification problems by using a new measure to be optimized: the norm of the confusion matrix. Indeed, recent results show that using the norm of the confusion matrix as an error measure can be quite interesting due to the fine-grain informations contained in the matrix, especially in the case of imbalanced classes. Our first contribution then consists in showing that optimizing criterion based on the confusion matrix gives rise to a common background for cost-sensitive methods aimed at dealing with imbalanced classes learning problems. As our second contribution, we propose an extension of a recent multi-class boosting method --- namely AdaBoost.MM --- to the imbalanced class problem, by greedily minimizing the empirical norm of the confusion matrix. A theoretical analysis of the properties of the proposed method is presented, while experimental results illustrate the behavior of the algorithm and show the relevancy of the approach compared to other methods.", "source": "arxiv/ml"}
{"id": "arxiv:2941", "title": "Markov Chain Monte Carlo for Arrangement of Hyperplanes in Locality-Sensitive Hashing", "text": "Since Hamming distances can be calculated by bitwise computations, they can be calculated with less computational load than L2 distances. Similarity searches can therefore be performed faster in Hamming distance space. The elements of Hamming distance space are bit strings. On the other hand, the arrangement of hyperplanes induce the transformation from the feature vectors into feature bit strings. This transformation method is a type of locality-sensitive hashing that has been attracting attention as a way of performing approximate similarity searches at high speed. Supervised learning of hyperplane arrangements allows us to obtain a method that transforms them into feature bit strings reflecting the information of labels applied to higher-dimensional feature vectors. In this p aper, we propose a supervised learning method for hyperplane arrangements in feature space that uses a Markov chain Monte Carlo (MCMC) method. We consider the probability density functions used during learning, and evaluate their performance. We also consider the sampling method for learning data pairs needed in learning, and we evaluate its performance. We confirm that the accuracy of this learning method when using a suitable probability density function and sampling method is greater than the accuracy of existing learning methods.", "source": "arxiv/ml"}
{"id": "arxiv:2942", "title": "Margins, Shrinkage, and Boosting", "text": "This manuscript shows that AdaBoost and its immediate variants can produce approximate maximum margin classifiers simply by scaling step size choices with a fixed small constant. In this way, when the unscaled step size is an optimal choice, these results provide guarantees for Friedman's empirically successful \"shrinkage\" procedure for gradient boosting (Friedman, 2000). Guarantees are also provided for a variety of other step sizes, affirming the intuition that increasingly regularized line searches provide improved margin guarantees. The results hold for the exponential loss and similar losses, most notably the logistic loss.", "source": "arxiv/ml"}
{"id": "arxiv:2943", "title": "Improving CUR Matrix Decomposition and the Nystr\\\"{o}m Approximation via Adaptive Sampling", "text": "The CUR matrix decomposition and the Nystr\\\"{o}m approximation are two important low-rank matrix approximation techniques. The Nystr\\\"{o}m method approximates a symmetric positive semidefinite matrix in terms of a small number of its columns, while CUR approximates an arbitrary data matrix by a small number of its columns and rows. Thus, CUR decomposition can be regarded as an extension of the Nystr\\\"{o}m approximation. In this paper we establish a more general error bound for the adaptive column/row sampling algorithm, based on which we propose more accurate CUR and Nystr\\\"{o}m algorithms with expected relative-error bounds. The proposed CUR and Nystr\\\"{o}m algorithms also have low time complexity and can avoid maintaining the whole data matrix in RAM. In addition, we give theoretical analysis for the lower error bounds of the standard Nystr\\\"{o}m method and the ensemble Nystr\\\"{o}m method. The main theoretical results established in this paper are novel, and our analysis makes no special assumption on the data matrices.", "source": "arxiv/ml"}
{"id": "arxiv:2944", "title": "A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems", "text": "Non-convex sparsity-inducing penalties have recently received considerable attentions in sparse learning. Recent theoretical investigations have demonstrated their superiority over the convex counterparts in several sparse learning settings. However, solving the non-convex optimization problems associated with non-convex penalties remains a big challenge. A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems. This approach is usually not very practical for large-scale problems because its computational cost is a multiple of solving a single convex problem. In this paper, we propose a General Iterative Shrinkage and Thresholding (GIST) algorithm to solve the nonconvex optimization problem for a large class of non-convex penalties. The GIST algorithm iteratively solves a proximal operator problem, which in turn has a closed-form solution for many commonly used penalties. At each outer iteration of the algorithm, we use a line search initialized by the Barzilai-Borwein (BB) rule that allows finding an appropriate step size quickly. The paper also presents a detailed convergence analysis of the GIST algorithm. The efficiency of the proposed algorithm is demonstrated by extensive experiments on large-scale data sets.", "source": "arxiv/ml"}
{"id": "arxiv:2945", "title": "On Improving Energy Efficiency within Green Femtocell Networks: A Hierarchical Reinforcement Learning Approach", "text": "One of the efficient solutions of improving coverage and increasing capacity in cellular networks is the deployment of femtocells. As the cellular networks are becoming more complex, energy consumption of whole network infrastructure is becoming important in terms of both operational costs and environmental impacts. This paper investigates energy efficiency of two-tier femtocell networks through combining game theory and stochastic learning. With the Stackelberg game formulation, a hierarchical reinforcement learning framework is applied for studying the joint expected utility maximization of macrocells and femtocells subject to the minimum signal-to-interference-plus-noise-ratio requirements. In the learning procedure, the macrocells act as leaders and the femtocells are followers. At each time step, the leaders commit to dynamic strategies based on the best responses of the followers, while the followers compete against each other with no further information but the leaders' transmission parameters. In this paper, we propose two reinforcement learning based intelligent algorithms to schedule each cell's stochastic power levels. Numerical experiments are presented to validate the investigations. The results show that the two learning algorithms substantially improve the energy efficiency of the femtocell networks.", "source": "arxiv/ml"}
{"id": "arxiv:2946", "title": "Large-Scale Learning with Less RAM via Randomization", "text": "We reduce the memory footprint of popular large-scale online learning methods by projecting our weight vector onto a coarse discrete set using randomized rounding. Compared to standard 32-bit float encodings, this reduces RAM usage by more than 50% during training and by up to 95% when making predictions from a fixed model, with almost no loss in accuracy. We also show that randomized counting can be used to implement per-coordinate learning rates, improving model quality with little additional RAM. We prove these memory-saving methods achieve regret guarantees similar to their exact variants. Empirical evaluation confirms excellent performance, dominating standard approaches across memory versus accuracy tradeoffs.", "source": "arxiv/ml"}
{"id": "arxiv:2947", "title": "Recovering Non-negative and Combined Sparse Representations", "text": "The non-negative solution to an underdetermined linear system can be uniquely recovered sometimes, even without imposing any additional sparsity constraints. In this paper, we derive conditions under which a unique non-negative solution for such a system can exist, based on the theory of polytopes. Furthermore, we develop the paradigm of combined sparse representations, where only a part of the coefficient vector is constrained to be non-negative, and the rest is unconstrained (general). We analyze the recovery of the unique, sparsest solution, for combined representations, under three different cases of coefficient support knowledge: (a) the non-zero supports of non-negative and general coefficients are known, (b) the non-zero support of general coefficients alone is known, and (c) both the non-zero supports are unknown. For case (c), we propose the combined orthogonal matching pursuit algorithm for coefficient recovery and derive the deterministic sparsity threshold under which recovery of the unique, sparsest coefficient vector is possible. We quantify the order complexity of the algorithms, and examine their performance in exact and approximate recovery of coefficients under various conditions of noise. Furthermore, we also obtain their empirical phase transition characteristics. We show that the basis pursuit algorithm, with partial non-negative constraints, and the proposed greedy algorithm perform better in recovering the unique sparse representation when compared to their unconstrained counterparts. Finally, we demonstrate the utility of the proposed methods in recovering images corrupted by saturation noise.", "source": "arxiv/ml"}
{"id": "arxiv:2948", "title": "Marginal Likelihoods for Distributed Parameter Estimation of Gaussian Graphical Models", "text": "We consider distributed estimation of the inverse covariance matrix, also called the concentration or precision matrix, in Gaussian graphical models. Traditional centralized estimation often requires global inference of the covariance matrix, which can be computationally intensive in large dimensions. Approximate inference based on message-passing algorithms, on the other hand, can lead to unstable and biased estimation in loopy graphical models. In this paper, we propose a general framework for distributed estimation based on a maximum marginal likelihood (MML) approach. This approach computes local parameter estimates by maximizing marginal likelihoods defined with respect to data collected from local neighborhoods. Due to the non-convexity of the MML problem, we introduce and solve a convex relaxation. The local estimates are then combined into a global estimate without the need for iterative message-passing between neighborhoods. The proposed algorithm is naturally parallelizable and computationally efficient, thereby making it suitable for high-dimensional problems. In the classical regime where the number of variables $p$ is fixed and the number of samples $T$ increases to infinity, the proposed estimator is shown to be asymptotically consistent and to improve monotonically as the local neighborhood size increases. In the high-dimensional scaling regime where both $p$ and $T$ increase to infinity, the convergence rate to the true parameters is derived and is seen to be comparable to centralized maximum likelihood estimation. Extensive numerical experiments demonstrate the improved performance of the two-hop version of the proposed estimator, which suffices to almost close the gap to the centralized maximum likelihood estimator at a reduced computational cost.", "source": "arxiv/ml"}
{"id": "arxiv:2949", "title": "Greedy Feature Selection for Subspace Clustering", "text": "Unions of subspaces provide a powerful generalization to linear subspace models for collections of high-dimensional data. To learn a union of subspaces from a collection of data, sets of signals in the collection that belong to the same subspace must be identified in order to obtain accurate estimates of the subspace structures present in the data. Recently, sparse recovery methods have been shown to provide a provable and robust strategy for exact feature selection (EFS)--recovering subsets of points from the ensemble that live in the same subspace. In parallel with recent studies of EFS with L1-minimization, in this paper, we develop sufficient conditions for EFS with a greedy method for sparse signal recovery known as orthogonal matching pursuit (OMP). Following our analysis, we provide an empirical study of feature selection strategies for signals living on unions of subspaces and characterize the gap between sparse recovery methods and nearest neighbor (NN)-based approaches. In particular, we demonstrate that sparse recovery methods provide significant advantages over NN methods and the gap between the two approaches is particularly pronounced when the sampling of subspaces in the dataset is sparse. Our results suggest that OMP may be employed to reliably recover exact feature sets in a number of regimes where NN approaches fail to reveal the subspace membership of points in the ensemble.", "source": "arxiv/ml"}
{"id": "arxiv:2950", "title": "Node-Based Learning of Multiple Gaussian Graphical Models", "text": "We consider the problem of estimating high-dimensional Gaussian graphical models corresponding to a single set of variables under several distinct conditions. This problem is motivated by the task of recovering transcriptional regulatory networks on the basis of gene expression data {containing heterogeneous samples, such as different disease states, multiple species, or different developmental stages}. We assume that most aspects of the conditional dependence networks are shared, but that there are some structured differences between them. Rather than assuming that similarities and differences between networks are driven by individual edges, we take a node-based approach, which in many cases provides a more intuitive interpretation of the network differences. We consider estimation under two distinct assumptions: (1) differences between the K networks are due to individual nodes that are perturbed across conditions, or (2) similarities among the K networks are due to the presence of common hub nodes that are shared across all K networks. Using a row-column overlap norm penalty function, we formulate two convex optimization problems that correspond to these two assumptions. We solve these problems using an alternating direction method of multipliers algorithm, and we derive a set of necessary and sufficient conditions that allows us to decompose the problem into independent subproblems so that our algorithm can be scaled to high-dimensional settings. Our proposal is illustrated on synthetic data, a webpage data set, and a brain cancer gene expression data set.", "source": "arxiv/ml"}
{"id": "arxiv:2951", "title": "Estimating Confusions in the ASR Channel for Improved Topic-based Language Model Adaptation", "text": "Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly sensitive to such changes, unless some form of adaptation takes place. One approach to speech language model adaptation is self-training, in which a language model's parameters are tuned based on automatically transcribed audio. However, transcription errors can misguide self-training, particularly in challenging settings such as conversational speech. In this work, we propose a model that considers the confusions (errors) of the ASR channel. By modeling the likely confusions in the ASR output instead of using just the 1-best, we improve self-training efficacy by obtaining a more reliable reference transcription estimate. We demonstrate improved topic-based language modeling adaptation results over both 1-best and lattice self-training using our ASR channel confusion estimates on telephone conversations.", "source": "arxiv/ml"}
{"id": "arxiv:2952", "title": "Separable Dictionary Learning", "text": "Many techniques in computer vision, machine learning, and statistics rely on the fact that a signal of interest admits a sparse representation over some dictionary. Dictionaries are either available analytically, or can be learned from a suitable training set. While analytic dictionaries permit to capture the global structure of a signal and allow a fast implementation, learned dictionaries often perform better in applications as they are more adapted to the considered class of signals. In imagery, unfortunately, the numerical burden for (i) learning a dictionary and for (ii) employing the dictionary for reconstruction tasks only allows to deal with relatively small image patches that only capture local image information. The approach presented in this paper aims at overcoming these drawbacks by allowing a separable structure on the dictionary throughout the learning process. On the one hand, this permits larger patch-sizes for the learning phase, on the other hand, the dictionary is applied efficiently in reconstruction tasks. The learning procedure is based on optimizing over a product of spheres which updates the dictionary as a whole, thus enforces basic dictionary properties such as mutual coherence explicitly during the learning procedure. In the special case where no separable structure is enforced, our method competes with state-of-the-art dictionary learning methods like K-SVD.", "source": "arxiv/ml"}
{"id": "arxiv:2953", "title": "An Entropy-based Learning Algorithm of Bayesian Conditional Trees", "text": "This article offers a modification of Chow and Liu's learning algorithm in the context of handwritten digit recognition. The modified algorithm directs the user to group digits into several classes consisting of digits that are hard to distinguish and then constructing an optimal conditional tree representation for each class of digits instead of for each single digit as done by Chow and Liu (1968). Advantages and extensions of the new method are discussed. Related works of Wong and Wang (1977) and Wong and Poon (1989) which offer a different entropy-based learning algorithm are shown to rest on inappropriate assumptions.", "source": "arxiv/ml"}
{"id": "arxiv:2954", "title": "Sparse Projections of Medical Images onto Manifolds", "text": "Manifold learning has been successfully applied to a variety of medical imaging problems. Its use in real-time applications requires fast projection onto the low-dimensional space. To this end, out-of-sample extensions are applied by constructing an interpolation function that maps from the input space to the low-dimensional manifold. Commonly used approaches such as the Nystr\\\"{o}m extension and kernel ridge regression require using all training points. We propose an interpolation function that only depends on a small subset of the input training data. Consequently, in the testing phase each new point only needs to be compared against a small number of input training data in order to project the point onto the low-dimensional space. We interpret our method as an out-of-sample extension that approximates kernel ridge regression. Our method involves solving a simple convex optimization problem and has the attractive property of guaranteeing an upper bound on the approximation error, which is crucial for medical applications. Tuning this error bound controls the sparsity of the resulting interpolation function. We illustrate our method in two clinical applications that require fast mapping of input images onto a low-dimensional space.", "source": "arxiv/ml"}
{"id": "arxiv:2955", "title": "Network Detection Theory and Performance", "text": "Network detection is an important capability in many areas of applied research in which data can be represented as a graph of entities and relationships. Oftentimes the object of interest is a relatively small subgraph in an enormous, potentially uninteresting background. This aspect characterizes network detection as a \"big data\" problem. Graph partitioning and network discovery have been major research areas over the last ten years, driven by interest in internet search, cyber security, social networks, and criminal or terrorist activities. The specific problem of network discovery is addressed as a special case of graph partitioning in which membership in a small subgraph of interest must be determined. Algebraic graph theory is used as the basis to analyze and compare different network detection methods. A new Bayesian network detection framework is introduced that partitions the graph based on prior information and direct observations. The new approach, called space-time threat propagation, is proved to maximize the probability of detection and is therefore optimum in the Neyman-Pearson sense. This optimality criterion is compared to spectral community detection approaches which divide the global graph into subsets or communities with optimal connectivity properties. We also explore a new generative stochastic model for covert networks and analyze using receiver operating characteristics the detection performance of both classes of optimal detection techniques.", "source": "arxiv/ml"}
{"id": "arxiv:2956", "title": "Sparse Factor Analysis for Learning and Content Analytics", "text": "We develop a new model and algorithms for machine learning-based learning analytics, which estimate a learner's knowledge of the concepts underlying a domain, and content analytics, which estimate the relationships among a collection of questions and those concepts. Our model represents the probability that a learner provides the correct response to a question in terms of three factors: their understanding of a set of underlying concepts, the concepts involved in each question, and each question's intrinsic difficulty. We estimate these factors given the graded responses to a collection of questions. The underlying estimation problem is ill-posed in general, especially when only a subset of the questions are answered. The key observation that enables a well-posed solution is the fact that typical educational domains of interest involve only a small number of key concepts. Leveraging this observation, we develop both a bi-convex maximum-likelihood and a Bayesian solution to the resulting SPARse Factor Analysis (SPARFA) problem. We also incorporate user-defined tags on questions to facilitate the interpretability of the estimated factors. Experiments with synthetic and real-world data demonstrate the efficacy of our approach. Finally, we make a connection between SPARFA and noisy, binary-valued (1-bit) dictionary learning that is of independent interest.", "source": "arxiv/ml"}
{"id": "arxiv:2957", "title": "A Diffusion Process on Riemannian Manifold for Visual Tracking", "text": "Robust visual tracking for long video sequences is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor, as this descriptor is robust to problems such as pixel-pixel misalignment, pose and illumination changes, that commonly occur in visual tracking. We model the changes in the template using a generative process. We introduce a new dynamical model for the template update using a random walk on the Riemannian manifold where the covariance descriptors lie in. This is done using log-transformed space of the manifold to free the constraints imposed inherently by positive semidefinite matrices. Modeling template variations and poses kinetics together in the state space enables us to jointly quantify the uncertainties relating to the kinematic states and the template in a principled way. Finally, the sequential inference of the posterior distribution of the kinematic states and the template is done using a particle filter. Our results shows that this principled approach can be robust to changes in illumination, poses and spatial affine transformation. In the experiments, our method outperformed the current state-of-the-art algorithm - the incremental Principal Component Analysis method, particularly when a target underwent fast poses changes and also maintained a comparable performance in stable target tracking cases.", "source": "arxiv/ml"}
{"id": "arxiv:2958", "title": "On Learnability, Complexity and Stability", "text": "We consider the fundamental question of learnability of a hypotheses class in the supervised learning setting and in the general learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in term of suitable notions of complexity, as well as more recent results that establish the connection between learnability and stability of a learning algorithm.", "source": "arxiv/ml"}
{"id": "arxiv:2959", "title": "Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems", "text": "We study the problem of adaptive control of a high dimensional linear quadratic (LQ) system. Previous work established the asymptotic convergence to an optimal controller for various adaptive control schemes. More recently, for the average cost LQ problem, a regret bound of ${O}(\\sqrt{T})$ was shown, apart form logarithmic factors. However, this bound scales exponentially with $p$, the dimension of the state space. In this work we consider the case where the matrices describing the dynamic of the LQ system are sparse and their dimensions are large. We present an adaptive control scheme that achieves a regret bound of ${O}(p \\sqrt{T})$, apart from logarithmic factors. In particular, our algorithm has an average cost of $(1+\\eps)$ times the optimum cost after $T = \\polylog(p) O(1/\\eps^2)$. This is in comparison to previous work on the dense dynamics where the algorithm requires time that scales exponentially with dimension in order to achieve regret of $\\eps$ times the optimal cost. We believe that our result has prominent applications in the emerging area of computational advertising, in particular targeted online advertising and advertising in social networks.", "source": "arxiv/ml"}
{"id": "arxiv:2960", "title": "Generalizing k-means for an arbitrary distance matrix", "text": "The original k-means clustering method works only if the exact vectors representing the data points are known. Therefore calculating the distances from the centroids needs vector operations, since the average of abstract data points is undefined. Existing algorithms can be extended for those cases when the sole input is the distance matrix, and the exact representing vectors are unknown. This extension may be named relational k-means after a notation for a similar algorithm invented for fuzzy clustering. A method is then proposed for generalizing k-means for scenarios when the data points have absolutely no connection with a Euclidean space.", "source": "arxiv/ml"}
{"id": "arxiv:2961", "title": "On Sparsity Inducing Regularization Methods for Machine Learning", "text": "During the past years there has been an explosion of interest in learning methods based on sparsity regularization. In this paper, we discuss a general class of such methods, in which the regularizer can be expressed as the composition of a convex function $\\omega$ with a linear function. This setting includes several methods such the group Lasso, the Fused Lasso, multi-task learning and many more. We present a general approach for solving regularization problems of this kind, under the assumption that the proximity operator of the function $\\omega$ is available. Furthermore, we comment on the application of this approach to support vector machines, a technique pioneered by the groundbreaking work of Vladimir Vapnik.", "source": "arxiv/ml"}
{"id": "arxiv:2962", "title": "Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression", "text": "In this paper, we consider supervised learning problems such as logistic regression and study the stochastic gradient method with averaging, in the usual stochastic approximation setting where observations are used only once. We show that after $N$ iterations, with a constant step-size proportional to $1/R^2 \\sqrt{N}$ where $N$ is the number of observations and $R$ is the maximum norm of the observations, the convergence rate is always of order $O(1/\\sqrt{N})$, and improves to $O(R^2 / \\mu N)$ where $\\mu$ is the lowest eigenvalue of the Hessian at the global optimum (when this eigenvalue is greater than $R^2/\\sqrt{N}$). Since $\\mu$ does not need to be known in advance, this shows that averaged stochastic gradient is adaptive to \\emph{unknown local} strong convexity of the objective function. Our proof relies on the generalized self-concordance properties of the logistic loss and thus extends to all generalized linear models with uniformly bounded features.", "source": "arxiv/ml"}
{"id": "arxiv:2963", "title": "Machine learning of hierarchical clustering to segment 2D and 3D images", "text": "We aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerative segmentation from superpixels. Our method combines multiple features at all scales of the agglomerative process, works for data with an arbitrary number of dimensions, and scales to very large datasets. We advocate the use of variation of information to measure segmentation accuracy, particularly in 3D electron microscopy (EM) images of neural tissue, and using this metric demonstrate an improvement over competing algorithms in EM and natural images.", "source": "arxiv/ml"}
{"id": "arxiv:2964", "title": "Convex Tensor Decomposition via Structured Schatten Norm Regularization", "text": "We discuss structured Schatten norms for tensor decomposition that includes two recently proposed norms (\"overlapped\" and \"latent\") for convex-optimization-based tensor decomposition, and connect tensor decomposition with wider literature on structured sparsity. Based on the properties of the structured Schatten norms, we mathematically analyze the performance of \"latent\" approach for tensor decomposition, which was empirically found to perform better than the \"overlapped\" approach in some settings. We show theoretically that this is indeed the case. In particular, when the unknown true tensor is low-rank in a specific mode, this approach performs as good as knowing the mode with the smallest rank. Along the way, we show a novel duality result for structures Schatten norms, establish the consistency, and discuss the identifiability of this approach. We confirm through numerical simulations that our theoretical prediction can precisely predict the scaling behavior of the mean squared error.", "source": "arxiv/ml"}
{"id": "arxiv:2965", "title": "A Note on k-support Norm Regularized Risk Minimization", "text": "The k-support norm has been recently introduced to perform correlated sparsity regularization. Although Argyriou et al. only reported experiments using squared loss, here we apply it to several other commonly used settings resulting in novel machine learning algorithms with interesting and familiar limit cases. Source code for the algorithms described here is available.", "source": "arxiv/ml"}
{"id": "arxiv:2966", "title": "Exploiting correlation and budget constraints in Bayesian multi-armed bandit optimization", "text": "We address the problem of finding the maximizer of a nonlinear smooth function, that can only be evaluated point-wise, subject to constraints on the number of permitted function evaluations. This problem is also known as fixed-budget best arm identification in the multi-armed bandit literature. We introduce a Bayesian approach for this problem and show that it empirically outperforms both the existing frequentist counterpart and other Bayesian optimization methods. The Bayesian approach places emphasis on detailed modelling, including the modelling of correlations among the arms. As a result, it can perform well in situations where the number of arms is much larger than the number of allowed function evaluation, whereas the frequentist counterpart is inapplicable. This feature enables us to develop and deploy practical applications, such as automatic machine learning toolboxes. The paper presents comprehensive comparisons of the proposed approach, Thompson sampling, classical Bayesian optimization techniques, more recent Bayesian bandit approaches, and state-of-the-art best arm identification methods. This is the first comparison of many of these methods in the literature and allows us to examine the relative merits of their different features.", "source": "arxiv/ml"}
{"id": "arxiv:2967", "title": "Sequential testing over multiple stages and performance analysis of data fusion", "text": "We describe a methodology for modeling the performance of decision-level data fusion between different sensor configurations, implemented as part of the JIEDDO Analytic Decision Engine (JADE). We first discuss a Bayesian network formulation of classical probabilistic data fusion, which allows elementary fusion structures to be stacked and analyzed efficiently. We then present an extension of the Wald sequential test for combining the outputs of the Bayesian network over time. We discuss an algorithm to compute its performance statistics and illustrate the approach on some examples. This variant of the sequential test involves multiple, distinct stages, where the evidence accumulated from each stage is carried over into the next one, and is motivated by a need to keep certain sensors in the network inactive unless triggered by other sensors.", "source": "arxiv/ml"}
{"id": "arxiv:2968", "title": "Efficiently Using Second Order Information in Large l1 Regularization Problems", "text": "We propose a novel general algorithm LHAC that efficiently uses second-order information to train a class of large-scale l1-regularized problems. Our method executes cheap iterations while achieving fast local convergence rate by exploiting the special structure of a low-rank matrix, constructed via quasi-Newton approximation of the Hessian of the smooth loss function. A greedy active-set strategy, based on the largest violations in the dual constraints, is employed to maintain a working set that iteratively estimates the complement of the optimal active set. This allows for smaller size of subproblems and eventually identifies the optimal active set. Empirical comparisons confirm that LHAC is highly competitive with several recently proposed state-of-the-art specialized solvers for sparse logistic regression and sparse inverse covariance matrix selection.", "source": "arxiv/ml"}
{"id": "arxiv:2969", "title": "ABC Reinforcement Learning", "text": "This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is that we only require a prior distribution on a class of simulators (generative models). This is useful in domains where an analytical probabilistic model of the underlying process is too complex to formulate, but where detailed simulation models are available. ABC-RL allows the use of any Bayesian reinforcement learning technique, even in this case. In addition, it can be seen as an extension of rollout algorithms to the case where we do not know what the correct model to draw rollouts from is. We experimentally demonstrate the potential of this approach in a comparison with LSPI. Finally, we introduce a theorem showing that ABC is a sound methodology in principle, even when non-sufficient statistics are used.", "source": "arxiv/ml"}
{"id": "arxiv:2970", "title": "Inductive Hashing on Manifolds", "text": "Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes that preserve the Euclidean distance in the original space. Manifold learning techniques, in contrast, are better able to model the intrinsic structure embedded in the original high-dimensional data. The complexity of these models, and the problems with out-of-sample data, have previously rendered them unsuitable for application to large-scale embedding, however. In this work, we consider how to learn compact binary embeddings on their intrinsic manifolds. In order to address the above-mentioned difficulties, we describe an efficient, inductive solution to the out-of-sample data problem, and a process by which non-parametric manifold learning may be used as the basis of a hashing method. Our proposed approach thus allows the development of a range of new hashing techniques exploiting the flexibility of the wide variety of manifold learning approaches available. We particularly show that hashing on the basis of t-SNE .", "source": "arxiv/ml"}
{"id": "arxiv:2971", "title": "Relevance As a Metric for Evaluating Machine Learning Algorithms", "text": "In machine learning, the choice of a learning algorithm that is suitable for the application domain is critical. The performance metric used to compare different algorithms must also reflect the concerns of users in the application domain under consideration. In this work, we propose a novel probability-based performance metric called Relevance Score for evaluating supervised learning algorithms. We evaluate the proposed metric through empirical analysis on a dataset gathered from an intelligent lighting pilot installation. In comparison to the commonly used Classification Accuracy metric, the Relevance Score proves to be more appropriate for a certain class of applications.", "source": "arxiv/ml"}
{"id": "arxiv:2972", "title": "Confidence sets for persistence diagrams", "text": "Persistent homology is a method for probing topological properties of point clouds and functions. The method involves tracking the birth and death of topological features (2000) as one varies a tuning parameter. Features with short lifetimes are informally considered to be \"topological noise,\" and those with a long lifetime are considered to be \"topological signal.\" In this paper, we bring some statistical ideas to persistent homology. In particular, we derive confidence sets that allow us to separate topological signal from topological noise.", "source": "arxiv/ml"}
{"id": "arxiv:2973", "title": "Detecting Overlapping Temporal Community Structure in Time-Evolving Networks", "text": "We present a principled approach for detecting overlapping temporal community structure in dynamic networks. Our method is based on the following framework: find the overlapping temporal community structure that maximizes a quality function associated with each snapshot of the network subject to a temporal smoothness constraint. A novel quality function and a smoothness constraint are proposed to handle overlaps, and a new convex relaxation is used to solve the resulting combinatorial optimization problem. We provide theoretical guarantees as well as experimental results that reveal community structure in real and synthetic networks. Our main insight is that certain structures can be identified only when temporal correlation is considered and when communities are allowed to overlap. In general, discovering such overlapping temporal community structure can enhance our understanding of real-world complex networks by revealing the underlying stability behind their seemingly chaotic evolution.", "source": "arxiv/ml"}
{"id": "arxiv:2974", "title": "Scalable Text and Link Analysis with Mixed-Topic Link Models", "text": "Many data sets contain rich information about objects, as well as pairwise relations between them. For instance, in networks of websites, scientific papers, and other documents, each node has content consisting of a collection of words, as well as hyperlinks or citations to other nodes. In order to perform inference on such data sets, and make predictions and recommendations, it is useful to have models that are able to capture the processes which generate the text at each node and the links between them. In this paper, we combine classic ideas in topic modeling with a variant of the mixed-membership block model recently developed in the statistical physics community. The resulting model has the advantage that its parameters, including the mixture of topics of each document and the resulting overlapping communities, can be inferred with a simple and scalable expectation-maximization algorithm. We test our model on three data sets, performing unsupervised topic classification and link prediction. For both tasks, our model outperforms several existing state-of-the-art methods, achieving higher accuracy with significantly less computation, analyzing a data set with 1.3 million words and 44 thousand links in a few minutes.", "source": "arxiv/ml"}
{"id": "arxiv:2975", "title": "On the symmetrical Kullback-Leibler Jeffreys centroids", "text": "Due to the success of the bag-of-word modeling paradigm, clustering histograms has become an important ingredient of modern information processing. Clustering histograms can be performed using the celebrated $k$-means centroid-based algorithm. From the viewpoint of applications, it is usually required to deal with symmetric distances. In this letter, we consider the Jeffreys divergence that symmetrizes the Kullback-Leibler divergence, and investigate the computation of Jeffreys centroids. We first prove that the Jeffreys centroid can be expressed analytically using the Lambert $W$ function for positive histograms. We then show how to obtain a fast guaranteed approximation when dealing with frequency histograms. Finally, we conclude with some remarks on the $k$-means histogram clustering.", "source": "arxiv/ml"}
{"id": "arxiv:2976", "title": "Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units", "text": "We generalize recent theoretical work on the minimal number of layers of narrow deep belief networks that can approximate any probability distribution on the states of their visible units arbitrarily well. We relax the setting of binary units (Sutskever and Hinton, 2008; Le Roux and Bengio, 2008, 2010; Mont\\'ufar and Ay, 2011) to units with arbitrary finite state spaces, and the vanishing approximation error to an arbitrary approximation error tolerance. For example, we show that a $q$-ary deep belief network with $L\\geq 2+\\frac{q^{\\lceil m-\\delta \\rceil}-1}{q-1}$ layers of width $n \\leq m + \\log_q(m) + 1$ for some $m\\in \\mathbb{N}$ can approximate any probability distribution on $\\{0,1,\\ldots,q-1\\}^n$ without exceeding a Kullback-Leibler divergence of $\\delta$. Our analysis covers discrete restricted Boltzmann machines and na\\\"ive Bayes models as special cases.", "source": "arxiv/ml"}
{"id": "arxiv:2977", "title": "Independent Vector Analysis: Identification Conditions and Performance Bounds", "text": "Recently, an extension of independent component analysis (ICA) from one to multiple datasets, termed independent vector analysis (IVA), has been the subject of significant research interest. IVA has also been shown to be a generalization of Hotelling's canonical correlation analysis. In this paper, we provide the identification conditions for a general IVA formulation, which accounts for linear, nonlinear, and sample-to-sample dependencies. The identification conditions are a generalization of previous results for ICA and for IVA when samples are independently and identically distributed. Furthermore, a principal aim of IVA is the identification of dependent sources between datasets. Thus, we provide the additional conditions for when the arbitrary ordering of the sources within each dataset is common. Performance bounds in terms of the Cramer-Rao lower bound are also provided for the demixing matrices and interference to source ratio. The performance of two IVA algorithms are compared to the theoretical bounds.", "source": "arxiv/ml"}
{"id": "arxiv:2978", "title": "Translation-Invariant Shrinkage/Thresholding of Group Sparse Signals", "text": "This paper addresses signal denoising when large-amplitude coefficients form clusters (groups). The L1-norm and other separable sparsity models do not capture the tendency of coefficients to cluster (group sparsity). This work develops an algorithm, called 'overlapping group shrinkage' (OGS), based on the minimization of a convex cost function involving a group-sparsity promoting penalty function. The groups are fully overlapping so the denoising method is translation-invariant and blocking artifacts are avoided. Based on the principle of majorization-minimization (MM), we derive a simple iterative minimization algorithm that reduces the cost function monotonically. A procedure for setting the regularization parameter, based on attenuating the noise to a specified level, is also described. The proposed approach is illustrated on speech enhancement, wherein the OGS approach is applied in the short-time Fourier transform (STFT) domain. The denoised speech produced by OGS does not suffer from musical noise.", "source": "arxiv/ml"}
{"id": "arxiv:2979", "title": "Parallel Computation Is ESS", "text": "There are enormous amount of examples of Computation in nature, exemplified across multiple species in biology. One crucial aim for these computations across all life forms their ability to learn and thereby increase the chance of their survival. In the current paper a formal definition of autonomous learning is proposed. From that definition we establish a Turing Machine model for learning, where rule tables can be added or deleted, but can not be modified. Sequential and parallel implementations of this model are discussed. It is found that for general purpose learning based on this model, the implementations capable of parallel execution would be evolutionarily stable. This is proposed to be of the reasons why in Nature parallelism in computation is found in abundance.", "source": "arxiv/ml"}
{"id": "arxiv:2980", "title": "Sparse Signal Processing with Linear and Nonlinear Observations: A Unified Shannon-Theoretic Approach", "text": "We derive fundamental sample complexity bounds for recovering sparse and structured signals for linear and nonlinear observation models including sparse regression, group testing, multivariate regression and problems with missing features. In general, sparse signal processing problems can be characterized in terms of the following Markovian property. We are given a set of $N$ variables $X_1,X_2,\\ldots,X_N$, and there is an unknown subset of variables $S \\subset \\{1,\\ldots,N\\}$ that are relevant for predicting outcomes $Y$. More specifically, when $Y$ is conditioned on $\\{X_n\\}_{n\\in S}$ it is conditionally independent of the other variables, $\\{X_n\\}_{n \\not \\in S}$. Our goal is to identify the set $S$ from samples of the variables $X$ and the associated outcomes $Y$. We characterize this problem as a version of the noisy channel coding problem. Using asymptotic information theoretic analyses, we establish mutual information formulas that provide sufficient and necessary conditions on the number of samples required to successfully recover the salient variables. These mutual information expressions unify conditions for both linear and nonlinear observations. We then compute sample complexity bounds for the aforementioned models, based on the mutual information expressions in order to demonstrate the applicability and flexibility of our results in general sparse signal processing models.", "source": "arxiv/ml"}
{"id": "arxiv:2981", "title": "Improved Performance of Unsupervised Method by Renovated K-Means", "text": "Clustering is a separation of data into groups of similar objects. Every group called cluster consists of objects that are similar to one another and dissimilar to objects of other groups. In this paper, the K-Means algorithm is implemented by three distance functions and to identify the optimal distance function for clustering methods. The proposed K-Means algorithm is compared with K-Means, Static Weighted K-Means (SWK-Means) and Dynamic Weighted K-Means (DWK-Means) algorithm by using Davis Bouldin index, Execution Time and Iteration count methods. Experimental results show that the proposed K-Means algorithm performed better on Iris and Wine dataset when compared with other three clustering methods.", "source": "arxiv/ml"}
{"id": "arxiv:2982", "title": "Representation, Approximation and Learning of Submodular Functions Using Low-rank Decision Trees", "text": "We study the complexity of approximate representation and learning of submodular functions over the uniform distribution on the Boolean hypercube $\\{0,1\\}^n$. Our main result is the following structural theorem: any submodular function is $\\epsilon$-close in $\\ell_2$ to a real-valued decision tree (DT) of depth $O(1/\\epsilon^2)$. This immediately implies that any submodular function is $\\epsilon$-close to a function of at most $2^{O(1/\\epsilon^2)}$ variables and has a spectral $\\ell_1$ norm of $2^{O(1/\\epsilon^2)}$. It also implies the closest previous result that states that submodular functions can be approximated by polynomials of degree $O(1/\\epsilon^2)$ (Cheraghchi et al., 2012). Our result is proved by constructing an approximation of a submodular function by a DT of rank $4/\\epsilon^2$ and a proof that any rank-$r$ DT can be $\\epsilon$-approximated by a DT of depth $\\frac{5}{2}(r+\\log(1/\\epsilon))$. We show that these structural results can be exploited to give an attribute-efficient PAC learning algorithm for submodular functions running in time $\\tilde{O}(n^2) \\cdot 2^{O(1/\\epsilon^{4})}$. The best previous algorithm for the problem requires $n^{O(1/\\epsilon^{2})}$ time and examples (Cheraghchi et al., 2012) but works also in the agnostic setting. In addition, we give improved learning algorithms for a number of related settings. We also prove that our PAC and agnostic learning algorithms are essentially optimal via two lower bounds: (1) an information-theoretic lower bound of $2^{\\Omega(1/\\epsilon^{2/3})}$ on the complexity of learning monotone submodular functions in any reasonable model; (2) computational lower bound of $n^{\\Omega(1/\\epsilon^{2/3})}$ based on a reduction to learning of sparse parities with noise, widely-believed to be intractable. These are the first lower bounds for learning of submodular functions over the uniform distribution.", "source": "arxiv/ml"}
{"id": "arxiv:2983", "title": "O(logT) Projections for Stochastic Optimization of Smooth and Strongly Convex Functions", "text": "Traditional algorithms for stochastic optimization require projecting the solution at each iteration into a given domain to ensure its feasibility. When facing complex domains, such as positive semi-definite cones, the projection operation can be expensive, leading to a high computational cost per iteration. In this paper, we present a novel algorithm that aims to reduce the number of projections for stochastic optimization. The proposed algorithm combines the strength of several recent developments in stochastic optimization, including mini-batch, extra-gradient, and epoch gradient descent, in order to effectively explore the smoothness and strong convexity. We show, both in expectation and with a high probability, that when the objective function is both smooth and strongly convex, the proposed algorithm achieves the optimal $O(1/T)$ rate of convergence with only $O(\\log T)$ projections. Our empirical study verifies the theoretical result.", "source": "arxiv/ml"}
{"id": "arxiv:2984", "title": "A Fast Semidefinite Approach to Solving Binary Quadratic Problems", "text": "Many computer vision problems can be formulated as binary quadratic programs (BQPs). Two classic relaxation methods are widely used for solving BQPs, namely, spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages. Spectral relaxation is simple and easy to implement, but its bound is loose. Semidefinite relaxation has a tighter bound, but its computational complexity is high for large scale problems. We present a new SDP formulation for BQPs, with two desirable properties. First, it has a similar relaxation bound to conventional SDP formulations. Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods. Extensive experiments on various applications including clustering, image segmentation, co-segmentation and registration demonstrate the usefulness of our SDP formulation for solving large-scale BQPs.", "source": "arxiv/ml"}
{"id": "arxiv:2985", "title": "A Novel Frank-Wolfe Algorithm. Analysis and Applications to Large-Scale SVM Training", "text": "Recently, there has been a renewed interest in the machine learning community for variants of a sparse greedy approximation procedure for concave optimization known as {the Frank-Wolfe (FW) method}. In particular, this procedure has been successfully applied to train large-scale instances of non-linear Support Vector Machines (SVMs). Specializing FW to SVM training has allowed to obtain efficient algorithms but also important theoretical results, including convergence analysis of training algorithms and new characterizations of model sparsity. In this paper, we present and analyze a novel variant of the FW method based on a new way to perform away steps, a classic strategy used to accelerate the convergence of the basic FW procedure. Our formulation and analysis is focused on a general concave maximization problem on the simplex. However, the specialization of our algorithm to quadratic forms is strongly related to some classic methods in computational geometry, namely the Gilbert and MDM algorithms. On the theoretical side, we demonstrate that the method matches the guarantees in terms of convergence rate and number of iterations obtained by using classic away steps. In particular, the method enjoys a linear rate of convergence, a result that has been recently proved for MDM on quadratic forms. On the practical side, we provide experiments on several classification datasets, and evaluate the results using statistical tests. Experiments show that our method is faster than the FW method with classic away steps, and works well even in the cases in which classic away steps slow down the algorithm. Furthermore, these improvements are obtained without sacrificing the predictive accuracy of the obtained SVM model.", "source": "arxiv/ml"}
{"id": "arxiv:2986", "title": "Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks", "text": "In hybrid hidden Markov model/artificial neural networks (HMM/ANN) automatic speech recognition (ASR) system, the phoneme class conditional probabilities are estimated by first extracting acoustic features from the speech signal based on prior knowledge such as, speech perception or/and speech production knowledge, and, then modeling the acoustic features with an ANN. Recent advances in machine learning techniques, more specifically in the field of image processing and text processing, have shown that such divide and conquer strategy (i.e., separating feature extraction and modeling steps) may not be necessary. Motivated from these studies, in the framework of convolutional neural networks (CNNs), this paper investigates a novel approach, where the input to the ANN is raw speech signal and the output is phoneme class conditional probability estimates. On TIMIT phoneme recognition task, we study different ANN architectures to show the benefit of CNNs and compare the proposed approach against conventional approach where, spectral-based feature MFCC is extracted and modeled by a multilayer perceptron. Our studies show that the proposed approach can yield comparable or better phoneme recognition performance when compared to the conventional approach. It indicates that CNNs can learn features relevant for phoneme classification automatically from the raw speech signal.", "source": "arxiv/ml"}
{"id": "arxiv:2987", "title": "Efficient Distance Metric Learning by Adaptive Sampling and Mini-Batch Stochastic Gradient Descent (SGD)", "text": "Distance metric learning (DML) is an important task that has found applications in many domains. The high computational cost of DML arises from the large number of variables to be determined and the constraint that a distance metric has to be a positive semi-definite (PSD) matrix. Although stochastic gradient descent (SGD) has been successfully applied to improve the efficiency of DML, it can still be computationally expensive because in order to ensure that the solution is a PSD matrix, it has to, at every iteration, project the updated distance metric onto the PSD cone, an expensive operation. We address this challenge by developing two strategies within SGD, i.e. mini-batch and adaptive sampling, to effectively reduce the number of updates (i.e., projections onto the PSD cone) in SGD. We also develop hybrid approaches that combine the strength of adaptive sampling with that of mini-batch online learning techniques to further improve the computational efficiency of SGD for DML. We prove the theoretical guarantees for both adaptive sampling and mini-batch based approaches for DML. We also conduct an extensive empirical study to verify the effectiveness of the proposed algorithms for DML.", "source": "arxiv/ml"}
{"id": "arxiv:2988", "title": "Fast SVM training using approximate extreme points", "text": "Applications of non-linear kernel Support Vector Machines (SVMs) to large datasets is seriously hampered by its excessive training time. We propose a modification, called the approximate extreme points support vector machine (AESVM), that is aimed at overcoming this burden. Our approach relies on conducting the SVM optimization over a carefully selected subset, called the representative set, of the training dataset. We present analytical results that indicate the similarity of AESVM and SVM solutions. A linear time algorithm based on convex hulls and extreme points is used to compute the representative set in kernel space. Extensive computational experiments on nine datasets compared AESVM to LIBSVM \\citep{LIBSVM}, CVM \\citep{Tsang05}, BVM \\citep{Tsang07}, LASVM \\citep{Bordes05}, $\\text{SVM}^{\\text{perf}}$ \\citep{Joachims09}, and the random features method \\citep{rahimi07}. Our AESVM implementation was found to train much faster than the other methods, while its classification accuracy was similar to that of LIBSVM in all cases. In particular, for a seizure detection dataset, AESVM training was almost $10^3$ times faster than LIBSVM and LASVM and more than forty times faster than CVM and BVM. Additionally, AESVM also gave competitively fast classification times.", "source": "arxiv/ml"}
{"id": "arxiv:2989", "title": "Generalization Bounds for Domain Adaptation", "text": "In this paper, we provide a new framework to obtain the generalization bounds of the learning process for domain adaptation, and then apply the derived bounds to analyze the asymptotical convergence of the learning process. Without loss of generality, we consider two kinds of representative domain adaptation: one is with multiple sources and the other is combining source and target data. In particular, we use the integral probability metric to measure the difference between two domains. For either kind of domain adaptation, we develop a related Hoeffding-type deviation inequality and a symmetrization inequality to achieve the corresponding generalization bound based on the uniform entropy number. We also generalized the classical McDiarmid's inequality to a more general setting where independent random variables can take values from different domains. By using this inequality, we then obtain generalization bounds based on the Rademacher complexity. Afterwards, we analyze the asymptotic convergence and the rate of convergence of the learning process for such kind of domain adaptation. Meanwhile, we discuss the factors that affect the asymptotic behavior of the learning process and the numerical experiments support our theoretical findings as well.", "source": "arxiv/ml"}
{"id": "arxiv:2990", "title": "Bug Classification: Feature Extraction and Comparison of Event Model using Na\\\"ive Bayes Approach", "text": "In software industries, individuals at different levels from customer to an engineer apply diverse mechanisms to detect to which class a particular bug should be allocated. Sometimes while a simple search in Internet might help, in many other cases a lot of effort is spent in analyzing the bug report to classify the bug. So there is a great need of a structured mining algorithm - where given a crash log, the existing bug database could be mined to find out the class to which the bug should be allocated. This would involve Mining patterns and applying different classification algorithms. This paper focuses on the feature extraction, noise reduction in data and classification of network bugs using probabilistic Na\\\"ive Bayes approach. Different event models like Bernoulli and Multinomial are applied on the extracted features. When new, unseen bugs are given as input to the algorithms, the performance comparison of different algorithms is done on the basis of accuracy and recall parameters.", "source": "arxiv/ml"}
{"id": "arxiv:2991", "title": "Image Retrieval using Histogram Factorization and Contextual Similarity Learning", "text": "Image retrieval has been a top topic in the field of both computer vision and machine learning for a long time. Content based image retrieval, which tries to retrieve images from a database visually similar to a query image, has attracted much attention. Two most important issues of image retrieval are the representation and ranking of the images. Recently, bag-of-words based method has shown its power as a representation method. Moreover, nonnegative matrix factorization is also a popular way to represent the data samples. In addition, contextual similarity learning has also been studied and proven to be an effective method for the ranking problem. However, these technologies have never been used together. In this paper, we developed an effective image retrieval system by representing each image using the bag-of-words method as histograms, and then apply the nonnegative matrix factorization to factorize the histograms, and finally learn the ranking score using the contextual similarity learning method. The proposed novel system is evaluated on a large scale image database and the effectiveness is shown.", "source": "arxiv/ml"}
{"id": "arxiv:2992", "title": "A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior", "text": "Recent advances in Bayesian reinforcement learning (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the environment's latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent environments, the transition dynamics are mainly controlled by the other agent's stochastic behavior for which FDM's independence and modeling assumptions do not hold. As a result, FDM does not allow the other agent's behavior to be generalized across different states nor specified using prior domain knowledge. To overcome these practical limitations of FDM, we propose a generalization of BRL to integrate the general class of parametric models and model priors, thus allowing practitioners' domain knowledge to be exploited to produce a fine-grained and compact representation of the other agent's behavior. Empirical evaluation shows that our approach outperforms existing multi-agent reinforcement learning algorithms.", "source": "arxiv/ml"}
{"id": "arxiv:2993", "title": "Learning Coverage Functions and Private Release of Marginals", "text": "We study the problem of approximating and learning coverage functions. A function $c: 2^{[n]} \\rightarrow \\mathbf{R}^{+}$ is a coverage function, if there exists a universe $U$ with non-negative weights $w(u)$ for each $u \\in U$ and subsets $A_1, A_2, \\ldots, A_n$ of $U$ such that $c(S) = \\sum_{u \\in \\cup_{i \\in S} A_i} w(u)$. Alternatively, coverage functions can be described as non-negative linear combinations of monotone disjunctions. They are a natural subclass of submodular functions and arise in a number of applications. We give an algorithm that for any $\\gamma,\\delta>0$, given random and uniform examples of an unknown coverage function $c$, finds a function $h$ that approximates $c$ within factor $1+\\gamma$ on all but $\\delta$-fraction of the points in time $poly(n,1/\\gamma,1/\\delta)$. This is the first fully-polynomial algorithm for learning an interesting class of functions in the demanding PMAC model of Balcan and Harvey (2011). Our algorithms are based on several new structural properties of coverage functions. Using the results in (Feldman and Kothari, 2014), we also show that coverage functions are learnable agnostically with excess $\\ell_1$-error $\\epsilon$ over all product and symmetric distributions in time $n^{\\log(1/\\epsilon)}$. In contrast, we show that, without assumptions on the distribution, learning coverage functions is at least as hard as learning polynomial-size disjoint DNF formulas, a class of functions for which the best known algorithm runs in time $2^{\\tilde{O}(n^{1/3})}$ (Klivans and Servedio, 2004). As an application of our learning results, we give simple differentially-private algorithms for releasing monotone conjunction counting queries with low average error. In particular, for any $k \\leq n$, we obtain private release of $k$-way marginals with average error $\\bar{\\alpha}$ in time $n^{O(\\log(1/\\bar{\\alpha}))}$.", "source": "arxiv/ml"}
{"id": "arxiv:2994", "title": "ClusterCluster: Parallel Markov Chain Monte Carlo for Dirichlet Process Mixtures", "text": "The Dirichlet process (DP) is a fundamental mathematical tool for Bayesian nonparametric modeling, and is widely used in tasks such as density estimation, natural language processing, and time series modeling. Although MCMC inference methods for the DP often provide a gold standard in terms asymptotic accuracy, they can be computationally expensive and are not obviously parallelizable. We propose a reparameterization of the Dirichlet process that induces conditional independencies between the atoms that form the random measure. This conditional independence enables many of the Markov chain transition operators for DP inference to be simulated in parallel across multiple cores. Applied to mixture modeling, our approach enables the Dirichlet process to simultaneously learn clusters that describe the data and superclusters that define the granularity of parallelization. Unlike previous approaches, our technique does not require alteration of the model and leaves the true posterior distribution invariant. It also naturally lends itself to a distributed software implementation in terms of Map-Reduce, which we test in cluster configurations of over 50 machines and 100 cores. We present experiments exploring the parallel efficiency and convergence properties of our approach on both synthetic and real-world data, including runs on 1MM data vectors in 256 dimensions.", "source": "arxiv/ml"}
{"id": "arxiv:2995", "title": "The PAV algorithm optimizes binary proper scoring rules", "text": "There has been much recent interest in application of the pool-adjacent-violators (PAV) algorithm for the purpose of calibrating the probabilistic outputs of automatic pattern recognition and machine learning algorithms. Special cost functions, known as proper scoring rules form natural objective functions to judge the goodness of such calibration. We show that for binary pattern classifiers, the non-parametric optimization of calibration, subject to a monotonicity constraint, can be solved by PAV and that this solution is optimal for all regular binary proper scoring rules. This extends previous results which were limited to convex binary proper scoring rules. We further show that this result holds not only for calibration of probabilities, but also for calibration of log-likelihood-ratios, in which case optimality holds independently of the prior probabilities of the pattern classes.", "source": "arxiv/ml"}
{"id": "arxiv:2996", "title": "Multiple decision trees", "text": "This paper describes experiments, on two domains, to investigate the effect of averaging over predictions of multiple decision trees, instead of using a single tree. Other authors have pointed out theoretical and commonsense reasons for preferring the multiple tree approach. Ideally, we would like to consider predictions from all trees, weighted by their probability. However, there is a vast number of different trees, and it is difficult to estimate the probability of each tree. We sidestep the estimation problem by using a modified version of the ID3 algorithm to build good trees, and average over only these trees. Our results are encouraging. For each domain, we managed to produce a small number of good trees. We find that it is best to average across sets of trees with different structure; this usually gives better performance than any of the constituent trees, including the ID3 tree.", "source": "arxiv/ml"}
{"id": "arxiv:2997", "title": "Kernel Reconstruction ICA for Sparse Representation", "text": "Independent Component Analysis (ICA) is an effective unsupervised tool to learn statistically independent representation. However, ICA is not only sensitive to whitening but also difficult to learn an over-complete basis. Consequently, ICA with soft Reconstruction cost(RICA) was presented to learn sparse representations with over-complete basis even on unwhitened data. Whereas RICA is infeasible to represent the data with nonlinear structure due to its intrinsic linearity. In addition, RICA is essentially an unsupervised method and can not utilize the class information. In this paper, we propose a kernel ICA model with reconstruction constraint (kRICA) to capture the nonlinear features. To bring in the class information, we further extend the unsupervised kRICA to a supervised one by introducing a discrimination constraint, namely d-kRICA. This constraint leads to learn a structured basis consisted of basis vectors from different basis subsets corresponding to different class labels. Then each subset will sparsely represent well for its own class but not for the others. Furthermore, data samples belonging to the same class will have similar representations, and thereby the learned sparse representations can take more discriminative power. Experimental results validate the effectiveness of kRICA and d-kRICA for image classification.", "source": "arxiv/ml"}
{"id": "arxiv:2998", "title": "Entropy landscape of solutions in the binary perceptron problem", "text": "The statistical picture of the solution space for a binary perceptron is studied. The binary perceptron learns a random classification of input random patterns by a set of binary synaptic weights. The learning of this network is difficult especially when the pattern (constraint) density is close to the capacity, which is supposed to be intimately related to the structure of the solution space. The geometrical organization is elucidated by the entropy landscape from a reference configuration and of solution-pairs separated by a given Hamming distance in the solution space. We evaluate the entropy at the annealed level as well as replica symmetric level and the mean field result is confirmed by the numerical simulations on single instances using the proposed message passing algorithms. From the first landscape (a random configuration as a reference), we see clearly how the solution space shrinks as more constraints are added. From the second landscape of solution-pairs, we deduce the coexistence of clustering and freezing in the solution space.", "source": "arxiv/ml"}
{"id": "arxiv:2999", "title": "The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF", "text": "The change of two orders of magnitude in the 'new DCF' of NIST's SRE'10, relative to the 'old DCF' evaluation criterion, posed a difficult challenge for participants and evaluator alike. Initially, participants were at a loss as to how to calibrate their systems, while the evaluator underestimated the required number of evaluation trials. After the fact, it is now obvious that both calibration and evaluation require very large sets of trials. This poses the challenges of (i) how to decide what number of trials is enough, and (ii) how to process such large data sets with reasonable memory and CPU requirements. After SRE'10, at the BOSARIS Workshop, we built solutions to these problems into the freely available BOSARIS Toolkit. This paper explains the principles and algorithms behind this toolkit. The main contributions of the toolkit are: 1. The Normalized Bayes Error-Rate Plot, which analyses likelihood- ratio calibration over a wide range of DCF operating points. These plots also help in judging the adequacy of the sizes of calibration and evaluation databases. 2. Efficient algorithms to compute DCF and minDCF for large score files, over the range of operating points required by these plots. 3. A new score file format, which facilitates working with very large trial lists. 4. A faster logistic regression optimizer for fusion and calibration. 5. A principled way to define EER (equal error rate), which is of practical interest when the absolute error count is small.", "source": "arxiv/ml"}
{"id": "arxiv:3000", "title": "A Generalized Online Mirror Descent with Applications to Classification and Regression", "text": "Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past few decades, some based on additive updates, like the Perceptron, and some on multiplicative updates, like Winnow. A unifying perspective on the design and the analysis of online algorithms is provided by online mirror descent, a general prediction strategy from which most first-order algorithms can be obtained as special cases. We generalize online mirror descent to time-varying regularizers with generic updates. Unlike standard mirror descent, our more general formulation also captures second order algorithms, algorithms for composite losses and algorithms for adaptive filtering. Moreover, we recover, and sometimes improve, known regret bounds as special cases of our analysis using specific regularizers. Finally, we show the power of our approach by deriving a new second order algorithm with a regret bound invariant with respect to arbitrary rescalings of individual features.", "source": "arxiv/ml"}
{"id": "arxiv:3001", "title": "Scaling the Indian Buffet Process via Submodular Maximization", "text": "Inference for latent feature models is inherently difficult as the inference space grows exponentially with the size of the input data and number of latent features. In this work, we use Kurihara & Welling (2008)'s maximization-expectation framework to perform approximate MAP inference for linear-Gaussian latent feature models with an Indian Buffet Process (IBP) prior. This formulation yields a submodular function of the features that corresponds to a lower bound on the model evidence. By adding a constant to this function, we obtain a nonnegative submodular function that can be maximized via a greedy algorithm that obtains at least a one-third approximation to the optimal solution. Our inference method scales linearly with the size of the input data, and we show the efficacy of our method on the largest datasets currently analyzed using an IBP model.", "source": "arxiv/ml"}
{"id": "arxiv:3002", "title": "Probabilistic Classification using Fuzzy Support Vector Machines", "text": "In medical applications such as recognizing the type of a tumor as Malignant or Benign, a wrong diagnosis can be devastating. Methods like Fuzzy Support Vector Machines (FSVM) try to reduce the effect of misplaced training points by assigning a lower weight to the outliers. However, there are still uncertain points which are similar to both classes and assigning a class by the given information will cause errors. In this paper, we propose a two-phase classification method which probabilistically assigns the uncertain points to each of the classes. The proposed method is applied to the Breast Cancer Wisconsin (Diagnostic) Dataset which consists of 569 instances in 2 classes of Malignant and Benign. This method assigns certain instances to their appropriate classes with probability of one, and the uncertain instances to each of the classes with associated probabilities. Therefore, based on the degree of uncertainty, doctors can suggest further examinations before making the final diagnosis.", "source": "arxiv/ml"}
{"id": "arxiv:3003", "title": "Machine Learning, Clustering, and Polymorphy", "text": "This paper describes a machine induction program (WITT) that attempts to model human categorization. Properties of categories to which human subjects are sensitive includes best or prototypical members, relative contrasts between putative categories, and polymorphy (neither necessary or sufficient features). This approach represents an alternative to usual Artificial Intelligence approaches to generalization and conceptual clustering which tend to focus on necessary and sufficient feature rules, equivalence classes, and simple search and match schemes. WITT is shown to be more consistent with human categorization while potentially including results produced by more traditional clustering schemes. Applications of this approach in the domains of expert systems and information retrieval are also discussed.", "source": "arxiv/ml"}
{"id": "arxiv:3004", "title": "Distributed dictionary learning over a sensor network", "text": "We consider the problem of distributed dictionary learning, where a set of nodes is required to collectively learn a common dictionary from noisy measurements. This approach may be useful in several contexts including sensor networks. Diffusion cooperation schemes have been proposed to solve the distributed linear regression problem. In this work we focus on a diffusion-based adaptive dictionary learning strategy: each node records observations and cooperates with its neighbors by sharing its local dictionary. The resulting algorithm corresponds to a distributed block coordinate descent (alternate optimization). Beyond dictionary learning, this strategy could be adapted to many matrix factorization problems and generalized to various settings. This article presents our approach and illustrates its efficiency on some numerical examples.", "source": "arxiv/ml"}