Sinkhorn Divergences for Unbalanced Optimal Transport - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Sinkhorn Divergences for Unbalanced Optimal Transport

Thibault Séjourné
  • Fonction : Auteur
Jean Feydy
  • Fonction : Auteur
Alain Trouvé
  • Fonction : Auteur
Gabriel Peyré
  • Fonction : Auteur

Résumé

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been studied in depth: unbalanced transport, which is robust to the presence of outliers and can be used when distributions don't have the same total mass; entropy-regularized transport, which is robust to sampling noise and lends itself to fast computations using the Sinkhorn algorithm. This paper combines both lines of work to put robust optimal transport on solid ground. Our main contribution is a generalization of the Sinkhorn algorithm to unbalanced transport: our method alternates between the standard Sinkhorn updates and the pointwise application of a contractive function. This implies that entropic transport solvers on grid images, point clouds and sampled distributions can all be modified easily to support unbalanced transport, with a proof of linear convergence that holds in all settings. We then show how to use this method to define pseudo-distances on the full space of positive measures that satisfy key geometric axioms: (unbalanced) Sinkhorn divergences are differentiable, positive, definite, convex, statistically robust and avoid any "entropic bias" towards a shrinkage of the measures' supports.
Fichier non déposé

Dates et versions

hal-04435912 , version 1 (02-02-2024)

Identifiants

Citer

Thibault Séjourné, Jean Feydy, François-Xavier Vialard, Alain Trouvé, Gabriel Peyré. Sinkhorn Divergences for Unbalanced Optimal Transport. 2024. ⟨hal-04435912⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More