GAN Estimation of Lipschitz Optimal Transport Maps - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

GAN Estimation of Lipschitz Optimal Transport Maps

Résumé

This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks. Building on theoretical and practical advances in the field of Lipschitz neural networks, we define a Lipschitz-constrained generative adversarial network penalized by the quadratic transportation cost. Then, we demonstrate that, under regularity assumptions, the obtained generator converges uniformly to the optimal transport map as the sample size increases to infinity. Furthermore, we show through a number of numerical experiments that the learnt mapping has promising performances. In contrast to previous work tackling either statistical guarantees or practicality, we provide an expressive and feasible estimator which paves way for optimal transport applications where the asymptotic behaviour must be certified.
Fichier principal
Vignette du fichier
text.pdf (1001.05 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03575178 , version 1 (15-02-2022)

Identifiants

Citer

Alberto González-Sanz, Lucas de Lara, Louis Béthune, Jean-Michel Loubes. GAN Estimation of Lipschitz Optimal Transport Maps. 2022. ⟨hal-03575178⟩
83 Consultations
129 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More