M Mesum Raza

algorise

·

AI & ML interests

None yet

Recent Activity

updated a Space 16 days ago

algorise/repro-sinkhorn-normalization-of-diffusion-kernels

published a Space 16 days ago

algorise/repro-sinkhorn-normalization-of-diffusion-kernels

updated a Space 16 days ago

algorise/repro-linear-regression-with-unknown-truncation-beyond-gaussian-features

View all activity

Organizations

algorise 's Spaces 204

Reproduction: Sinkhorn Normalization of Diffusion Kernels

Browse code, traces, and workspace in an interactive logbook

Reproduction: Linear Regression with Unknown Truncation Beyond Gaussian Features

Explore code, traces, and workspace with an interactive logbook

Reproduction: Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles

Explore project logs, code, and traces in a workspace

Reproduction: Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning

Explore code logs, traces, and workspace in an interactive UI

Reproduction: Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces

Explore research logbook with code, traces, and workspace

Reproduction: The Pareto-optimal Trade-off between Regret and Statistical Inference in Linear Stochastic Bandits under Safety Constraints

Explore research code, traces, and workspace in an interactive logbook

Reproduction: Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization

Browse and manage research logbooks with code, traces, and workspace

Reproduction: Chain-of-Thought Gradient Descent

View code logs, traces and workspace, then collaborate with AI

Reproduction: Second-Order Bilevel Optimization with Accelerated Convergence Rates

Explore project code, traces, and workspace in an interactive logbook

Reproduction: Improved Convergence Analysis of Topology Dependence in Decentralized SGD

Explore and manage experiment logs with interactive views

Reproduction: Constrained Adaptive Rejection Sampling

Explore code, traces, and workspace with an interactive logbook

Reproduction: Minimax-Optimal Policy Regret in Partially Observable Markov Games

Explore and document code, traces, and workspace in a research logbook

Reproduction: Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates

Explore code, traces, and workspace in a research logbook

Reproduction: Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions

Explore experiment logs, code, and traces in an interactive workspace

Reproduction: Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport

Explore project logs, traces, and workspace in an interactive UI

Reproduction: Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent

Explore and manage project logs and traces

Reproduction: Online Bayesian Experimental Design for Partially Observed Dynamical Systems

Explore experiment logs, traces, and workspace online

Reproduction: Latent Guided Sampling for Combinatorial Optimization

Explore and manage experiment logs with interactive views

Reproduction: FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model

Explore project logs, traces, and workspace

Reproduction: Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets

Explore experiment logs and collaborate with an AI agent

Reproduction: Bilevel Optimization over Saddle Points of Zero-Sum Markov Games

Explore and collaborate on experiment logbooks online

Reproduction: Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry

Browse and collaborate on project logbooks

Reproduction: HodgeFlow Policy Search by Topologically Dissecting Temporal-Difference Signals in Non-Markovian Environments

Explore research logbook with code, traces, and workspace

Reproduction: Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modeling and State Tracking

Explore experiment logs, traces, and workspace online