🩵 123

Alex

snaykey

3 7

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

updated a Space 1 day ago

snaykey/repro-twostage-kernel-cate

published a Space 1 day ago

snaykey/repro-twostage-kernel-cate

updated a Space 1 day ago

snaykey/repro-linear-markov-games-mail

View all activity

Organizations

updated a Space 1 day ago

Reproduction: Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression

Explore and collaborate on research logbooks with AI assistance

published a Space 1 day ago

Reproduction: Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression

Explore and collaborate on research logbooks with AI assistance

updated a Space 1 day ago

Reproduction: Multi-Agent Imitation Learning in Linear Markov Games

Explore experiment logs and sync findings with an AI agent

published a Space 1 day ago

Reproduction: Multi-Agent Imitation Learning in Linear Markov Games

Explore experiment logs and sync findings with an AI agent

updated a Space 1 day ago

Reproduction: Robust Linear Dueling Bandits (RCDP-UCB)

Explore experiment logs and collaborate with an AI agent

published a Space 1 day ago

Reproduction: Robust Linear Dueling Bandits (RCDP-UCB)

Explore experiment logs and collaborate with an AI agent

updated a Space 1 day ago

Reproduction: Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation

Collaborate on research logbooks with your AI agent

published a Space 1 day ago

Reproduction: Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation

Collaborate on research logbooks with your AI agent

updated a Space 2 days ago

Reproduction: Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

Explore research logbooks and sync findings with an AI agent

published a Space 2 days ago

Reproduction: Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

Explore research logbooks and sync findings with an AI agent

updated a Space 2 days ago

Reproduction: Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Collaborate on a research logbook with your coding agent

published a Space 2 days ago

Reproduction: Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Collaborate on a research logbook with your coding agent

updated a Space 2 days ago

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

Explore and collaborate on research logbooks with an AI agent

published a Space 2 days ago

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

Explore and collaborate on research logbooks with an AI agent

updated a Space 2 days ago

Reproduction: Best-of-Both-Worlds for Heavy-Tailed MDPs

Explore experiment logs and sync findings with an AI agent

published a Space 2 days ago

Reproduction: Best-of-Both-Worlds for Heavy-Tailed MDPs

Explore experiment logs and sync findings with an AI agent

updated a Space 2 days ago

Reproduction: Projection-Free Algorithms for Minimax Problems

Explore and collaborate on a structured research logbook

published a Space 2 days ago

Reproduction: Projection-Free Algorithms for Minimax Problems

Explore and collaborate on a structured research logbook

updated a Space 2 days ago

Reproduction: Towards a Holistic Understanding of Selection Bias for Causal Effect Identification

Explore research logbook and sync findings with an AI agent

published a Space 2 days ago

Reproduction: Towards a Holistic Understanding of Selection Bias for Causal Effect Identification

Explore research logbook and sync findings with an AI agent