Gradient Flow Sampler-based Distributionally Robust Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Zusen, Zhu, Jia-Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910255936438272
author Xu, Zusen
Zhu, Jia-Jie
author_facet Xu, Zusen
Zhu, Jia-Jie
contents We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Markov Chain Monte Carlo sampling and gradient flow theory, we show that our theoretical framework can be implemented as practical algorithms for sampling from worst-case distributions and, consequently, DRO. While numerous previous works have proposed various reformulation techniques and iterative algorithms, we contribute a sound gradient flow view of the distributional optimization that can be used to construct new algorithms. As an example of applications, we solve a class of Wasserstein and Sinkhorn DRO problems using the recently-discovered Wasserstein Fisher-Rao and Stein variational gradient flows. Notably, we also show some simple reductions of our framework recover exactly previously proposed popular DRO methods, and provide new insights into their theoretical limit and optimization dynamics. Numerical studies based on stochastic gradient descent provide empirical backing for our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gradient Flow Sampler-based Distributionally Robust Optimization
Xu, Zusen
Zhu, Jia-Jie
Optimization and Control
Analysis of PDEs
Machine Learning
We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Markov Chain Monte Carlo sampling and gradient flow theory, we show that our theoretical framework can be implemented as practical algorithms for sampling from worst-case distributions and, consequently, DRO. While numerous previous works have proposed various reformulation techniques and iterative algorithms, we contribute a sound gradient flow view of the distributional optimization that can be used to construct new algorithms. As an example of applications, we solve a class of Wasserstein and Sinkhorn DRO problems using the recently-discovered Wasserstein Fisher-Rao and Stein variational gradient flows. Notably, we also show some simple reductions of our framework recover exactly previously proposed popular DRO methods, and provide new insights into their theoretical limit and optimization dynamics. Numerical studies based on stochastic gradient descent provide empirical backing for our theoretical findings.
title Gradient Flow Sampler-based Distributionally Robust Optimization
topic Optimization and Control
Analysis of PDEs
Machine Learning
url https://arxiv.org/abs/2510.25956