🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

·

https://navigatingnoise.substack.com/

AI & ML interests

None yet

Recent Activity

updated a Space about 20 hours ago

amkkk/repro-orthogonal-clustered-multitask-learning

published a Space about 20 hours ago

amkkk/repro-orthogonal-clustered-multitask-learning

updated a Space about 20 hours ago

amkkk/repro-tight-margin-voting-bounds

View all activity

Organizations

amkkk 's Spaces 263

Reproduction: Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality

Explore code, traces, and workspace in an interactive logbook

Reproduction: Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets

Explore and manage code logs, traces, and workspace

Reproduction: Language Generation with Replay: A Learning-Theoretic View of Model Collapse

Explore experiment logs and collaborate with an AI agent

Reproduction: FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction

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

Reproduction: nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

Explore code logs, traces, and workspace in a collaborative UI

Reproduction: SENDAI (YblLI3n0dn)

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

Reproduction: HaloProbe — Bayesian Detection and Mitigation of Object Hallucinations in VLMs

Explore experiment logs and collaborate with an AI agent

Reproduction: Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories

Explore code, traces and workspace in an interactive logbook

Reproduction: Causal Matrix Completion under Multiple Treatments via Mixed Synthetic Nearest Neighbors

Explore and manage experiment logs with an interactive web logbook

Reproduction: Learning to Approximate Uniform Facility Location via Graph Neural Networks

Explore experiment logs and code in an interactive workspace

Reproduction: Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees

Explore experiment logs, traces, and workspace in a web UI

Reproduction: A Theoretical Framework for Modular Learning of Robust Generative Models

Explore experiment logs, code, and traces in a web workspace

Reproduction: Coverage Improvement and Fast Convergence of On-policy Preference Learning

Explore experiment logs and traces in an interactive web UI

Reproduction: On the Expressive Power of Permutation-Equivariant Weight-Space Networks

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

Reproduction: Single-Head Attention in High Dimensions

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

Reproduction: FormulaCode: Evaluating Agentic Optimization on Large Codebases

Explore code logs, traces, and workspace in a collaborative UI

Reproduction: When Do Graph Foundation Models Transfer? A Data-Centric Theory

Explore project logs, code, and execution traces in one view

Reproduction: Conditional Equivalence of DPO and RLHF

Explore code, traces, and workspace in an interactive logbook

Reproduction: Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification

Explore experiment logs, traces, and workspace in a web UI

Reproduction: Improved Bounds for Reward-Agnostic and Reward-Free Exploration

Explore experiment logs and traces in an interactive workspace

Reproduction: Infinite Mask Diffusion for Few-Step Distillation

Explore experiment logs and code traces in an interactive UI

Reproduction: On the Anisotropy of Score-Based Generative Models

Explore research reproducibility logs and traces

Reproduction: Nonparametric Distribution Regression Re-calibration

Explore experiment logs and collaborate with an AI agent

Reproduction: High-accuracy and dimension-free sampling with diffusions

Explore research logs, traces, and workspace online