Kevin Arvai

arvkevi

3 14 13

AI & ML interests

Genomics, Healthcare, Sports

Recent Activity

updated a Space 20 days ago

arvkevi/repro-semi-knockoffs

updated a Space 20 days ago

arvkevi/snv-continual-learning-repro

updated a bucket 20 days ago

arvkevi/snv-continual-learning-repro-artifacts

View all activity

Organizations

arvkevi 's Spaces 72

Repro - Exact and Approximate Algorithms for Polytree Learning

🎯

Explore algorithm logs and collaborate with your coding agent

Repro - Mirror Descent Under Generalized Smoothness

🎯

Explore research logs and collaborate with an AI agent

Reproducing Stochastic Sparse Attention for Memory-Bound Inference

🎯

Browse and sync your project logbook with an AI agent

Repro - A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms

🎯

Explore and collaborate on a research logbook online

HypoSpace: Exact Certificates and Open-Model Coverage Audit

🎯

Explore audit logs and collaborate with your coding agent

Repro - Learning-Augmented Online Covering Problems

🎯

Collaborate with an AI agent to view and edit your project logbook

Repro - Learning to Execute Graph Algorithms Exactly with GNNs

🎯

Explore experiment logs and sync findings with an AI agent

Repro - Parsimonious Learning-Augmented Online Metric Matching

🎯

View and sync experiment logbook with a coding agent

Necessary Compositionality: ICML 2026 Reproduction

🎯

Explore experiment logs and sync findings with an AI agent

Repro - Provably Data-driven Lagrangian Relaxation

🎯

View and sync experiment logs with an AI coding agent

Repro - The Illusion of Generalization in TLMs

🎯

Collaborate on a shared logbook with your coding agent

Repro - Sharp Analysis of KL-UCB for KL-regularized Multi-armed Bandits

🎯

Explore research logbooks and sync findings with an AI agent

Repro - Multi-Distribution Robust Conformal Prediction

🎯

Browse and share experiment logs with your coding agent

Repro - Online Conformal Prediction via Universal Portfolio Algorithms

🎯

Generate conformal predictions using universal portfolio algorithms

Repro - On Densest k-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence

🎯

Explore research logbooks and sync findings with an AI agent

Repro - Revisiting ML Training under FHE: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

🎯

Explore research logbook and collaborate with an AI agent

Repro - Simple Algorithms for Bad Triangle Transversals

🎯

Explore algorithm notes and collaborate with an AI agent

Repro - A Rate-Distortion Theorem for Membership Testing

🎯

View and collaborate on a project logbook

Repro - Distribution-Shift Detection with Reference-Conditional Conformal Test Martingales

🎯

Detect distribution shifts and log findings interactively

Repro - Improved High-probability Convergence Guarantees of Decentralized SGD

🎯

Browse and collaborate on research logbooks in a web interface

Repro - Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety

🎯

Explore project logbook and collaborate with an AI agent

Repro - On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

🎯

Collaborate on research notes with an AI coding agent

Repro - To Grok Grokking: Provable Grokking in Ridge Regression

🎯

Explore and edit research logbook with AI collaboration

Repro - Explaining Concept Shift with Interpretable Feature Attribution

🎯

Explore and organize concept‑shift experiment logs