Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization

Published: 22 Jan 2025, Last Modified: 06 Mar 2025AISTATS 2025 PosterEveryoneRevisionsBibTeXCC BY 4.0
TL;DR: We provide a black-box reduction from an optimization algorithm to a nearly-optimal uniformly stable algorithm with the same convergence rate.
Abstract: We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p \geq 1$. We propose a black-box reduction method that, by employing properties of uniformly convex regularizers, turns an optimization algorithm for Hölder smooth convex losses into a uniformly stable learning algorithm with optimal statistical risk bounds on the excess risk, up to a constant factor depending on $p$. Achieving a black-box reduction for uniform stability was posed as an open question by Attia and Koren (2022), which had solved the Euclidean case $p=2$. We explore applications that leverage non-Euclidean geometry in addressing binary classification problems.
Submission Number: 1945
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview