Regularization for Wasserstein Distributionally Robust Optimization - Laboratoire Jean Kuntzmann Accéder directement au contenu
Article Dans Une Revue ESAIM: Control, Optimisation and Calculus of Variations Année : 2023

Regularization for Wasserstein Distributionally Robust Optimization

Résumé

Optimal transport has recently proved to be a useful tool in various machine learning applications needing comparisons of probability measures. Among these, applications of distributionally robust optimization naturally involve Wasserstein distances in their models of uncertainty, capturing data shifts or worst-case scenarios. Inspired by the success of the regularization of Wasserstein distances in optimal transport, we study in this paper the regularization of Wasserstein distributionally robust optimization. First, we derive a general strong duality result of regularized Wasserstein distributionally robust problems. Second, we refine this duality result in the case of entropic regularization and provide an approximation result when the regularization parameters vanish.
Fichier principal
Vignette du fichier
regularization_WDRO.pdf (477.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03837681 , version 1 (03-11-2022)
hal-03837681 , version 2 (23-03-2023)

Identifiants

Citer

Waïss Azizian, Franck Iutzeler, Jérôme Malick. Regularization for Wasserstein Distributionally Robust Optimization. ESAIM: Control, Optimisation and Calculus of Variations, 2023, 33, pp.31. ⟨10.1051/cocv/2023019⟩. ⟨hal-03837681v2⟩
67 Consultations
99 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More