🩵 123

Alex

snaykey

3 7

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

updated a Space about 2 hours ago

snaykey/repro-fair-ot

updated a Space about 2 hours ago

snaykey/repro-learn-to-parse

updated a bucket about 6 hours ago

snaykey/repro-list-decodable-mean-artifacts

View all activity

Organizations

updated 2 Spaces about 2 hours ago

Repro: Optimal Transport under Group Fairness Constraints

Explore and sync experiment logbooks with a coding agent

Repro: Deep Networks Learn to Parse Context-Free Languages from Local Statistics

Explore and collaborate on experiment logbooks online

updated a bucket about 6 hours ago

snaykey/repro-list-decodable-mean-artifacts

updated 3 Spaces about 6 hours ago

Token Sample Complexity of Attention

Explore and collaborate on your project logbook

Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions

Optimal structure learning and conditional independence testing

published 2 Spaces about 6 hours ago

Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions

Optimal structure learning and conditional independence testing

updated a Space about 6 hours ago

High-Probability Convergence Guarantees of Decentralized SGD

published a Space about 6 hours ago

High-Probability Convergence Guarantees of Decentralized SGD

updated a Space about 7 hours ago

Reproduction: Inference of Online Newton Methods with Nesterov's Accelerated Sketching

published a Space about 7 hours ago

Reproduction: Inference of Online Newton Methods with Nesterov's Accelerated Sketching

updated a Space about 7 hours ago

Reproduction: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

published a Space about 7 hours ago

Reproduction: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

updated a Space about 7 hours ago

Operator Splitting with Hamilton-Jacobi-based Proximals

published a Space about 7 hours ago

Operator Splitting with Hamilton-Jacobi-based Proximals

updated a Space about 7 hours ago

Covariance estimation using Markov chain Monte Carlo

published a Space about 7 hours ago

Covariance estimation using Markov chain Monte Carlo

updated 2 Spaces about 8 hours ago

Repro: Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem

Browse and collaborate on a research logbook

Reproduction: Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning

Explore research logbook and collaborate with a coding agent