Article Dans Une Revue Electronic Journal of Statistics Année : 2025

On the potential benefits of entropic regularization for smoothing Wasserstein estimators

Résumé

This paper is focused on the study of entropic regularization in optimal transport as a smoothing method for Wasserstein estimators, through the prism of the classical tradeoff between approximation and estimation errors in statistics. Wasserstein estimators are defined as solutions of variational problems whose objective function involves the use of an optimal transport cost between probability measures. Such estimators can be regularized by replacing the optimal transport cost by its regularized version using an entropy penalty on the transport plan. The use of such a regularization has a potentially significant smoothing effect on the resulting estimators. In this work, we investigate its potential benefits on the approximation and estimation properties of regularized Wasserstein estimators. Our main contribution is to discuss how entropic regularization may reach, at a lowest computational cost, statistical performances that are comparable to those of un-regularized Wasserstein estimators in statistical learning problems involving distributional data analysis. To this end, we present new theoretical results on the convergence of regularized Wasserstein estimators. We also study their numerical performances using simulated and real data in the supervised learning problem of proportions estimation in mixture models using optimal transport.

Fichier principal
Vignette du fichier
2210.06934v3.pdf (2.43 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03908229 , version 1 (25-08-2025)

Licence

Identifiants

Citer

Jérémie Bigot, Paul Freulon, Boris P. Hejblum, Arthur Leclaire. On the potential benefits of entropic regularization for smoothing Wasserstein estimators. Electronic Journal of Statistics , 2025, 19 (2), pp.3867-3894. ⟨10.1214/25-EJS2430⟩. ⟨hal-03908229⟩
854 Consultations
140 Téléchargements

Altmetric

Partager

  • More