🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

·

https://navigatingnoise.substack.com/

AI & ML interests

None yet

Recent Activity

liked a model about 13 hours ago

0xSero/Gemma-4-21B

liked a model about 21 hours ago

0xSero/Gemma-4-19B

updated a Space 2 days ago

amkkk/repro-a-fine-grained-understanding-of-uniform-convergence-for-halfspaces

View all activity

Organizations

amkkk 's Spaces 283

Reproduction: A Stronger Benchmark for Online Bilateral Trade

Explore code logs and traces in an interactive workspace

Reproduction: Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions

Explore code, execution traces, and workspace in a unified logbook

Reproduction: On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models

Reproduction: Universal Representation of Generalized Convex Functions and their Gradients

Reproduction: Stable Deep Reinforcement Learning via Isotropic Gaussian Representations

Browse project logs, traces, and workspace with AI help

Reproduction: Differentiable Conformal Training for LLM Reasoning Factuality

Explore project logs, code, and traces with AI collaboration

Reproduction: Approximation Theory for Lipschitz Continuous Transformers

Explore and navigate experiment logs, code, and traces

Reproduction: Conservation Laws for Modern Neural Architectures

Explore code, traces, and workspace in a collaborative logbook

Reproduction: Quantifying the noise sensitivity of the Wasserstein metric for images

Explore experiment logs and collaborate with an AI agent

Reproduction: Near-Optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation

Explore experiment logs, code, and traces in an interactive web UI

Reproduction: Performative Learning Theory

Explore and manage experiment logbooks with AI collaboration

Reproduction: Provable Bounds for the Learnability of Sample-Compressible Families from Noisy Samples

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

Reproduction: A Direct Second-Order Method for Solving Two-Player Zero-Sum Games

Explore and manage experiment logs, code, and traces

Reproduction: Accelerating Langevin Monte Carlo via Efficient Stochastic Runge-Kutta Methods beyond Log-Concavity

Explore code, traces, and workspace with an interactive logbook

Reproduction: Networked Information Aggregation for Binary Classification

Explore project logs, traces, and workspace in a web logbook

Reproduction: Operator Splitting with Hamilton-Jacobi-based Proximals

Explore and manage experiment logs, traces, and workspace

Reproduction: Equivalence of Context and Parameter Updates in Modern Transformer Blocks

Explore and share a research logbook with code, traces, and workspace

Reproduction: Enhancing Affine Maximizer Auctions with Correlation-Aware Payment

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

Reproduction: Step-Size Stability in Stochastic Optimization: A Theoretical Perspective

Explore experiment logs, traces, and workspace online

Reproduction: Learning-Augmented Online Covering Problems

Explore code, traces, and workspace in an interactive logbook

Reproduction: Optimal Transport under Group Fairness Constraints

Explore project code, traces, and workspace with a logbook

Reproduction: Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Explore research logs and collaborate with an AI agent

Reproduction: Black-Box Assisted Regression — Phase Transitions and Minimax Optimality

Explore experiment logs and code in an interactive web logbook

Reproduction: Computationally-efficient Graph Modeling with Refined Graph Random Features

Explore project logbook and collaborate with AI agent