Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications

Abstract : The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data analysis. The Sinkhorn divergence allows the fast computation of an entropically regularized Wasserstein distance between two probability distributions supported on a finite metric space of (possibly) high-dimension. For data sampled from one or two unknown probability distributions, we derive the distributional limits of the empirical Sinkhorn divergence and its centered version (Sinkhorn loss). We also propose a bootstrap procedure which allows to obtain new test statistics for measuring the discrepancies between multivariate probability distributions. Our work is inspired by the results of Sommerfeld and Munk (2016) on the asymptotic distribution of empirical Wasserstein distance on finite space using unregularized transportation costs. Incidentally we also analyze the asymptotic distribution of entropy-regularized Wasserstein distances when the regularization parameter tends to zero. Simulated and real datasets are used to illustrate our approach.
Type de document :
Pré-publication, Document de travail
2019
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01647869
Contributeur : Elsa Cazelles <>
Soumis le : jeudi 7 février 2019 - 19:32:22
Dernière modification le : samedi 9 février 2019 - 01:27:40

Fichier

tcl_sinkhorn_revisited.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01647869, version 2

Collections

Citation

Jérémie Bigot, Elsa Cazelles, Nicolas Papadakis. Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications. 2019. 〈hal-01647869v2〉

Partager

Métriques

Consultations de la notice

7

Téléchargements de fichiers

34