Justin Johnson

RyeCatcher

·

https://www.jandsgroupllc.com

AI & ML interests

Im a builder

Recent Activity

updated a Space about 20 hours ago

RyeCatcher/repro-robust-linear-dueling-bandits-with-post-serving-context-under-unknown-delays-and-adversari

published a Space about 20 hours ago

RyeCatcher/repro-robust-linear-dueling-bandits-with-post-serving-context-under-unknown-delays-and-adversari

updated a Space about 21 hours ago

RyeCatcher/repro-why-are-linear-rnns-more-parallelizable

View all activity

Organizations

RyeCatcher 's Spaces 46

Reproduction: Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions

Explore project logs, traces, and workspace

Reproduction: Why Are Linear RNNs More Parallelizable?

Explore project logs, traces and workspace in a web UI

Reproduction: Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms

Browse experiment logs and collaborate with an AI agent

Reproduction: Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Explore project logs, traces, and workspace online

Reproduction: Gaussian Mean Field Variational Inference can Overestimate Predictive Variance

Explore code, traces, and workspace in an interactive logbook

Reproduction: Stochastic Gradient Methods under Heavy-Tailed Noises in Weakly Convex Optimization

Explore code logs, traces, and workspace collaboratively

Reproduction: A Fine-Grained Understanding of Uniform Convergence for Halfspaces

Explore code logs, traces, and workspace in one view

Reproduction: Exact and Approximate Algorithms for Polytree Learning

Explore code logs, execution traces, and workspace online

Reproduction: The Optimal Sample Complexity of Linear Contracts

Explore code, traces, and workspace in an interactive logbook

Reproduction: Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

Explore experiment logs with an interactive web viewer

Reproduction: Theoretical Challenges in Learning for Branch-and-Cut

Explore and manage research logs, traces, and workspace online

Reproduction: Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation

Explore research logbooks with code, traces, and workspace

Reproduction: Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets

Explore code, traces, and workspace in an interactive logbook

Reproduction: Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

Browse research code, traces, and workspace in an interactive logbook

Reproduction: Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States

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

Reproduction: Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective

Explore and manage experiment logs in a web workspace

Reproduction: Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

Explore experiment logs and traces in an interactive view

Reproduction: The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradients

Explore code, traces, and workspace in an interactive logbook

Reproduction: On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks

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

Reproduction: Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

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

Reproduction: Attention's forward pass and Frank-Wolfe

Explore code logs, traces, and workspace

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

Explore code, traces and workspace in an interactive logbook

Reproduction: The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity

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

Reproduction: Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions

Explore code logs, execution traces, and workspaces