BIGOT, Jeremie; FREULON, Paul; HEJBLUM, Boris; LECLAIRE, Arthur

Institut de Mathématiques de Bordeaux [IMB]

FREULON, Paul

Institut de Mathématiques de Bordeaux [IMB]

HEJBLUM, Boris

Statistics In System biology and Translational Medicine [SISTM]
Bordeaux population health [BPH]

Langue

Document de travail - Pré-publication

Résumé en anglais

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.< Réduire

URI

https://oskar-bordeaux.fr/handle/20.500.12278/172214

Voir/Ouvrir

Métadonnées

Licence d’utilisation du document

On the potential benefits of entropic regularization for smoothing Wasserstein estimators

Langue

Résumé en anglais

URI

Unités de recherche

Voir/Ouvrir

Métadonnées

Partager cette publication !

Licence d’utilisation du document

On the potential benefits of entropic regularization for smoothing Wasserstein estimators

Langue

Résumé en anglais

URI

Unités de recherche