Distributionally Robust Optimization over Wasserstein Balls with i.i.d. Structure

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kharitenko, Andrey, Fochesato, Marta, Tsiamis, Anastasios, Schmid, Niklas, Lygeros, John
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908955634040832
author Kharitenko, Andrey
Fochesato, Marta
Tsiamis, Anastasios
Schmid, Niklas
Lygeros, John
author_facet Kharitenko, Andrey
Fochesato, Marta
Tsiamis, Anastasios
Schmid, Niklas
Lygeros, John
contents We consider distributionally robust optimization problems where the uncertainty is modeled via a structured Wasserstein ambiguity set. Specifically, the ambiguity is restricted to product measures $P^{\otimes N}$, where $P$ lies within a Wasserstein ball centered at an empirical distribution $\widehat{P}$. This structure reflects the assumption of independent and identically distributed (i.i.d.) uncertainty components and yields a non-convex ambiguity set that is strictly contained in its unstructured counterpart, thereby reducing conservatism. The resulting optimization problem is generally intractable due to the loss of convexity. We address this by introducing a sequence of tractable convex relaxations, each admitting strong duality, and prove that this sequence converges to the original problem value under suitable conditions. Numerical examples are provided to illustrate the effectiveness of the proposed approach. As a byproduct of our proofs, we establish a novel formula, of independent interest, relating the Wasserstein distance of a mixture of product distributions to the Wasserstein distance between its constituent measures.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributionally Robust Optimization over Wasserstein Balls with i.i.d. Structure
Kharitenko, Andrey
Fochesato, Marta
Tsiamis, Anastasios
Schmid, Niklas
Lygeros, John
Optimization and Control
90C15, 90C25
We consider distributionally robust optimization problems where the uncertainty is modeled via a structured Wasserstein ambiguity set. Specifically, the ambiguity is restricted to product measures $P^{\otimes N}$, where $P$ lies within a Wasserstein ball centered at an empirical distribution $\widehat{P}$. This structure reflects the assumption of independent and identically distributed (i.i.d.) uncertainty components and yields a non-convex ambiguity set that is strictly contained in its unstructured counterpart, thereby reducing conservatism. The resulting optimization problem is generally intractable due to the loss of convexity. We address this by introducing a sequence of tractable convex relaxations, each admitting strong duality, and prove that this sequence converges to the original problem value under suitable conditions. Numerical examples are provided to illustrate the effectiveness of the proposed approach. As a byproduct of our proofs, we establish a novel formula, of independent interest, relating the Wasserstein distance of a mixture of product distributions to the Wasserstein distance between its constituent measures.
title Distributionally Robust Optimization over Wasserstein Balls with i.i.d. Structure
topic Optimization and Control
90C15, 90C25
url https://arxiv.org/abs/2503.23543