Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Le, Tam, Malick, Jérôme
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2402.11981
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929687294377984
author Le, Tam
Malick, Jérôme
author_facet Le, Tam
Malick, Jérôme
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11981
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Universal generalization guarantees for Wasserstein distributionally robust models
Le, Tam
Malick, Jérôme
Optimization and Control
Machine Learning
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.
title Universal generalization guarantees for Wasserstein distributionally robust models
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2402.11981