🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

·

https://navigatingnoise.substack.com/

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

0xSero/Gemma-4-21B

liked a model about 18 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: Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes

Repro - Learning to Rank by Directly Optimizing Full-Order Probabilities

Explore dataset similarity with an interactive logbook

Repro - Generalized Linear Bandits with Memory

Explore experiment logs and sync findings with your coding agent

Reproduction: Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

Explore research logbooks and sync notes with an AI agent

Reproduction: Set-Preserving Calibration from Conformal P-Values to E-Values

Reproduction: Online Conformal Prediction via Universal Portfolio Algorithms

Explore code, traces, and workspace in an interactive logbook

Repro - Geometric Coherence Learning for Structuring Value Functions in Plain MDPs

Explore and collaborate on a research logbook

Repro - Multi-Agent Imitation Learning in Linear Markov Games

Browse and collaborate on research logbooks online

Repro - Non-Uniform Noise-to-Signal Ratio in REINFORCE

Explore and share experiment logbook with coding agents

Repro - Softmax as Linear Attention in the Large-Prompt Regime

Collaborate on research logbooks with your AI coding agent

Repro - Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs

Explore derivation graphs of do‑calculus reasoning

Repro - To Grok Grokking: Provable Grokking in Ridge Regression

Explore research logbook and sync with an AI coding agent

Reproduction: A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms

Reproduction: Anytime Detection of Strategic Deviations in Multi-Agent Systems

Reproduction: The Catastrophic Failure of the k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It

Reproduction: Mirror Descent Under Generalized Smoothness

Explore code, traces, and workspace in an interactive logbook

Reproduction: Towards Understanding Adam Convergence on Highly Degenerate Polynomials

Collaborate on experiment logbooks with an AI coding agent

Reproduction: Instance-Specific Approximation Ratios for Correlation Clustering and Max-Cut

Explore research logbooks and collaborate with an AI agent

Reproduction: Logarithmic Switching Regret for Online Convex Optimization

View and sync research logbook with your coding agent

Reproduction: Improved Convergence Analysis of Topology Dependence in Decentralized SGD

Explore research logbooks and sync with AI agents

Reproduction: Desirable Effort Fairness and Optimality Trade-offs in Strategic Learning

Explore and collaborate on a structured logbook

Reproduction: Asymmetric conformal prediction with penalized kernel sum-of-squares

Explore research logbooks and collaborate with an AI agent

Reproduction: Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings

Explore research logbook and collaborate with an AI agent

Reproduction: Box Thirding: Anytime Best Arm Identification under Insufficient Sampling

Explore research logbook and collaborate with an AI agent