Loss-aware distributionally robust optimization via trainable optimal transport ambiguity sets

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ohnemus, Jonas, Fochesato, Marta, Zuliani, Riccardo, 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_ 1866908541139288064
author Ohnemus, Jonas
Fochesato, Marta
Zuliani, Riccardo
Lygeros, John
author_facet Ohnemus, Jonas
Fochesato, Marta
Zuliani, Riccardo
Lygeros, John
contents Optimal-Transport Distributionally Robust Optimization (OT-DRO) robustifies data-driven decision-making under uncertainty by capturing the sampling-induced statistical error via optimal transport ambiguity sets. The standard OT-DRO pipeline consists of a two-step procedure, where the ambiguity set is first designed and subsequently embedded into the downstream OT-DRO problem. However, this separation between uncertainty quantification and optimization might result in excessive conservatism. We introduce an end-to-end pipeline to automatically learn decision-focused ambiguity sets for OT-DRO problems, where the loss function informs the shape of the optimal transport ambiguity set, leading to less conservative yet distributionally robust decisions. We formulate the learning problem as a bilevel optimization program and solve it via a hypergradient-based method. By leveraging the recently introduced nonsmooth conservative implicit function theorem, we establish convergence to a critical point of the bilevel problem. We present experiments validating our method on standard portfolio optimization and linear regression tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12689
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Loss-aware distributionally robust optimization via trainable optimal transport ambiguity sets
Ohnemus, Jonas
Fochesato, Marta
Zuliani, Riccardo
Lygeros, John
Optimization and Control
Systems and Control
Optimal-Transport Distributionally Robust Optimization (OT-DRO) robustifies data-driven decision-making under uncertainty by capturing the sampling-induced statistical error via optimal transport ambiguity sets. The standard OT-DRO pipeline consists of a two-step procedure, where the ambiguity set is first designed and subsequently embedded into the downstream OT-DRO problem. However, this separation between uncertainty quantification and optimization might result in excessive conservatism. We introduce an end-to-end pipeline to automatically learn decision-focused ambiguity sets for OT-DRO problems, where the loss function informs the shape of the optimal transport ambiguity set, leading to less conservative yet distributionally robust decisions. We formulate the learning problem as a bilevel optimization program and solve it via a hypergradient-based method. By leveraging the recently introduced nonsmooth conservative implicit function theorem, we establish convergence to a critical point of the bilevel problem. We present experiments validating our method on standard portfolio optimization and linear regression tasks.
title Loss-aware distributionally robust optimization via trainable optimal transport ambiguity sets
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2509.12689