🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

11 2 36

https://navigatingnoise.substack.com/

AI & ML interests

Tough question as I love all areas of DL, but from all of it, embeddings are my favourite topic. Currently obsessed with what can we do around LLMs. MLE @ DPD, prev DS in Recs Systems @ Alibaba Group

Recent Activity

updated a model 1 day ago

amkkk/Trace-Inverter-4B-NoBubble-GGUF

published a model 1 day ago

amkkk/Trace-Inverter-4B-NoBubble-GGUF

updated a model 6 days ago

amkkk/Trace-Inverter-4B-NoBubble

View all activity

Organizations

amkkk 's Spaces 283

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

🎯

Browse and collaborate on a research logbook with an AI agent

Reproduction: Cost-aware Stopping for Bayesian Optimization

🎯

Explore experiment logs and sync with an AI agent

Reproduction: To Grok Grokking: Provable Grokking in Ridge Regression

🎯

Explore research logbooks and collaborate with an agent

Reproduction: Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs

🎯

Explore a research logbook and collaborate with an AI agent

Reproduction: CAffNet: Hard Constraint-Affine Neural Networks

🎯

Explore and collaborate on a research logbook online

Reproduction audit: Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

🎯

Explore a logbook and collaborate with an AI agent

Reproduction: Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency

🎯

Explore research logbooks and collaborate with an AI agent

Reproduction: Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success

🎯

View and sync a research logbook with an AI agent

Reproduction: Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad

🎯

Collaborate on a coding logbook with your AI agent

Reproduction: Gaussian Mean Field Variational Inference can Overestimate Predictive Variance

🎯

Explore and collaborate on research logbooks

Reproduction: Ski Rental with Distributional Predictions of Unknown Quality

🎯

Explore research logbooks and sync findings with an AI agent

Reproduction: Learning in Structured Stackelberg Games

🎯

Explore and sync experiment logbooks with your coding agent

Repro - Sharp Inequalities between TV and Hellinger for Gaussian Mixtures

🎯

Browse and collaborate on research logbooks online

Repro - High-Dimensional Learning Dynamics of Quantized Models with STE

🎯

Explore and share experiment logs with an AI coding agent

Repro - On the Coordination of Value-Maximizing Bidders

🎯

View and sync research logbook with your coding agent

Repro - On the Accuracy of Newton Step and Influence Function Data Attributions

🎯

Browse and collaborate on a project logbook online

Repro - Theoretical Challenges in Learning for Branch-and-Cut

🎯

Explore and manage research logbook for branch‑and‑cut challenges

Repro - Chebyshev Policies and the Mountain Car Problem

🎯

View and manage a collaborative logbook with AI agent

Repro - Tighter Regret Lower Bound for GP Bandits with SE Kernel

🎯

View and collaborate on research logbooks online

Repro - Improved Analysis of the Accelerated Noisy Power Method

🎯

Explore and share project logbooks with a coding agent

Repro - Welfare-Optimal Classification with Accuracy Auctions

🎯

Collaborate with an AI agent to update your project logbook

Repro - A General Framework for Fair and Robust Regression

🎯

Explore and manage regression experiment logs

Repro - On Structured State-Space Duality

🎯

Collaborate on a coding logbook with an AI agent

Repro - Asymptotically Optimal Sequential Testing with Markovian Data

🎯

Explore and share experiment logbooks online