Martin Zubeldia

Assistant Professor, University of Minnesota - Twin Cities

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging

#3206 · Sajad Khodadadian, Martin Zubeldia

This paper introduces a unified method that converts high-probability bounds for individual Stochastic Approximation iterates into tight concentration bounds for their Polyak–Ruppert averages.