Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models

Résumé

Wasserstein distributionally robust estimators have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive generalization guarantees: the robust objective obtained from the training distribution is an exact upper bound on the true risk with high probability. However, existing guarantees either suffer from the curse of dimensionality, are restricted to specific settings, or lead to spurious error terms. In this paper, we show that these generalization guarantees actually hold on general classes of models, do not suffer from the curse of dimensionality, and can even cover distribution shifts at testing. We also prove that these results carry over to the newly-introduced regularized versions of Wasserstein distributionally robust problems.
Fichier principal
Vignette du fichier
main.pdf (1.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04106850 , version 1 (25-05-2023)
hal-04106850 , version 2 (26-10-2023)
hal-04106850 , version 3 (02-11-2023)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Waïss Azizian, Franck Iutzeler, Jérôme Malick. Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models. 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023), Dec 2023, New Orleans, United States. ⟨hal-04106850v3⟩
127 Consultations
49 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More