Preprints, Working Papers, ... Year : 2024

Universal generalization guarantees for Wasserstein distributionally robust models

Tam Le
Jérôme Malick

Abstract

Distributionally robust optimization has emerged as an attractive way to train robust machine learning models, capturing data uncertainty and distribution shifts. Recent statistical analyses have proved that generalization guarantees of robust models based on the Wasserstein distance have generalization guarantees that do not suffer from the curse of dimensionality. However, these results are either approximate, obtained in specific cases, or based on assumptions difficult to verify in practice. In contrast, we establish exact generalization guarantees that cover a wide range of cases, with arbitrary transport costs and parametric loss functions, including deep learning objectives with nonsmooth activations. We complete our analysis with an excess bound on the robust objective and an extension to Wasserstein robust models with entropic regularizations.
Fichier principal
Vignette du fichier
wdro_iclr2025.pdf (508.61 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04460543 , version 1 (15-02-2024)
hal-04460543 , version 2 (28-05-2024)
hal-04460543 , version 3 (11-10-2024)
hal-04460543 , version 4 (24-01-2025)

Licence

Identifiers

Cite

Tam Le, Jérôme Malick. Universal generalization guarantees for Wasserstein distributionally robust models. 2025. ⟨hal-04460543v4⟩
446 View
97 Download

Altmetric

Share

More