Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Le, Tam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911722146627584
author Le, Tam
author_facet Le, Tam
contents Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a sampled approximation of the original objective. We establish convergence of the approximate gradients to subgradients of the unregularized objective as the regularization parameter vanishes, enabling convergence guarantees for stochastic gradient methods. We obtain qualitative convergence results under general assumptions, then we provide convergence rates under additional regularity. In particular, we prove rates for the convergence of the unregularized objective values, up to sampling errors, when the regularization level is decreased across iterations. Our analysis yields byproducts of independent interest, including approximation results for smoothing of maximum functions subdifferentials and empirical lower bounds for dual solutions of Wasserstein distributionally robust optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
Le, Tam
Optimization and Control
Machine Learning
Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a sampled approximation of the original objective. We establish convergence of the approximate gradients to subgradients of the unregularized objective as the regularization parameter vanishes, enabling convergence guarantees for stochastic gradient methods. We obtain qualitative convergence results under general assumptions, then we provide convergence rates under additional regularity. In particular, we prove rates for the convergence of the unregularized objective values, up to sampling errors, when the regularization level is decreased across iterations. Our analysis yields byproducts of independent interest, including approximation results for smoothing of maximum functions subdifferentials and empirical lower bounds for dual solutions of Wasserstein distributionally robust optimization.
title Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2506.04948