collaborators

7 papers

cs.IT2026

Cofilling Shattering: A Syndrome-Support Hierarchy for Check Erasures

Joshua Steier

Let be a binary linear map with fixed coordinate bases, let , and let be the minimum Hamming weight of a preimage of the s…

cs.GT2026

Ergodic Deviation-Robust Equilibrium under Mirror Descent Learning in Finite Games

Joshua Steier

We introduce Ergodic Deviation-Robust Equilibrium (EDRE), a dynamics-relative equilibrium concept for repeated finite games in which agents learn via entropic mirror descent (EMD).…

math.CO2026

Adjacency Spectral Radius Under Laplacian Sparsification: Deterministic and Probabilistic Bounds

Joshua Steier

Spielman-Srivastava spectral sparsification preserves Laplacian quadratic forms to within (1 +/- epsilon), but does not directly control the adjacency spectral radius lambda_1, whi…

cs.LG2026

PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning

John Wu, Yongda Fan, Zhenbang Wu +14

Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research. To address these challenges, we introd…

cs.LG2026

Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear Disentanglement

Joshua Steier

What determines whether a molecular property prediction model organizes its representations so that geometric and compositional information can be cleanly separated? We introduce C…

cs.LG2026

PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure

Joshua Steier

When data is scarce or mistakes are costly, average-case metrics fall short. What a practitioner needs is a guarantee: with probability at least , the learned policy is $\var…