Saved in:
Bibliographic Details
Main Authors: Chu, Hong T. M., Lin, Meixia, Toh, Kim-Chuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.03942
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910319677276160
author Chu, Hong T. M.
Lin, Meixia
Toh, Kim-Chuan
author_facet Chu, Hong T. M.
Lin, Meixia
Toh, Kim-Chuan
contents We study a variety of Wasserstein distributionally robust optimization (WDRO) problems where the distributions in the ambiguity set are chosen by constraining their Wasserstein discrepancies to the empirical distribution. Using the notion of weak Lipschitz property, we derive lower and upper bounds of the corresponding worst-case loss quantity and propose sufficient conditions under which this quantity coincides with its regularization scheme counterpart. Our constructive methodology and elementary analysis also directly characterize the closed-form of the approximate worst-case distribution. Extensive applications show that our theoretical results are applicable to various problems, including regression, classification and risk measure problems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Wasserstein distributionally robust optimization and its tractable regularization formulations
Chu, Hong T. M.
Lin, Meixia
Toh, Kim-Chuan
Optimization and Control
We study a variety of Wasserstein distributionally robust optimization (WDRO) problems where the distributions in the ambiguity set are chosen by constraining their Wasserstein discrepancies to the empirical distribution. Using the notion of weak Lipschitz property, we derive lower and upper bounds of the corresponding worst-case loss quantity and propose sufficient conditions under which this quantity coincides with its regularization scheme counterpart. Our constructive methodology and elementary analysis also directly characterize the closed-form of the approximate worst-case distribution. Extensive applications show that our theoretical results are applicable to various problems, including regression, classification and risk measure problems.
title Wasserstein distributionally robust optimization and its tractable regularization formulations
topic Optimization and Control
url https://arxiv.org/abs/2402.03942