🩵 123

Alex

snaykey

3 7

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

updated a Space about 3 hours ago

snaykey/repro-kmeans-hd-failure

published a Space about 3 hours ago

snaykey/repro-kmeans-hd-failure

updated a Space about 3 hours ago

snaykey/repro-variance-allocation

View all activity

Organizations

snaykey 's Spaces 195

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

Explore a research logbook and collaborate with your agent

Reproduction: Allocating Variance to Maximize Expectation

Explore and collaborate on a research logbook

Reproduction: Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation

Explore and share a research logbook with an AI agent

Repro: Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

Explore experiment logs and sync findings with an AI agent

Reproduction: Multi-task Linear Regression without Eigenvalue Lower Bounds (Adaptivity, Robustness, and Safety)

Explore and edit a research logbook with agent collaboration

Reproduction: Attention's forward pass and Frank-Wolfe

Explore and collaborate on a web‑based research logbook

Reproduction: On Structured State-Space Duality

Explore and collaborate on research logbooks with an AI agent

Reproduction: Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Lp Moments

Collaborate on research notes with an AI‑powered logbook

Reproduction: Sinkhorn Normalization of Diffusion Kernels

Explore experiment logbooks and sync with coding agents

Repro: Exactly Computing do-Shapley Values

Explore experiment logs and collaborate with an AI agent

Reproduction: The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

Explore and collaborate on research logbooks online

Reproduction: Online Conformal Prediction via Universal Portfolio Algorithms

Explore and collaborate on experiment logbooks online

Reproduction: Asymptotically Optimal Sequential Testing with Markovian Data

Explore a research logbook and sync with your coding agent

Reproduction: Exact Functional ANOVA Decomposition for Categorical Inputs Models

Explore experiment logs and collaborate with an AI agent

Reproduction: Innovation: An Almost Characterization of Hallucination

Explore and sync a research logbook with an AI coding agent

Reproduction: A Coin Flip for Safety - LLM Judges Fail to Reliably Measure Adversarial Robustness

Explore and edit project logbook with agent collaboration

Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo

Explore and collaborate on a research logbook online

Reproduction: A theory of learning data statistics in diffusion models, from easy to hard

Explore and edit a research logbook with AI assistance

Reproduction: Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis

Explore project logbooks and sync findings with an AI agent

Reproduction: Solving Imperfect-Recall Games via Sum-of-Squares Optimization

Explore and sync research logbook with an AI agent

Reproduction: Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming

Explore and manage project logs in an interactive web view

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

Explore do‑calculus derivation graphs and sync with an AI agent

Repro: Single-Head Attention in High Dimensions

Track experiments and sync notes with your coding agent

Repro: PINE — Pruning Boosted Tree Ensembles with Conformal Equivalence

Explore research logbook and sync with coding agents