Deprecated: $wgMWOAuthSharedUserIDs=false is deprecated, set $wgMWOAuthSharedUserIDs=true, $wgMWOAuthSharedUserSource='local' instead [Called from MediaWiki\HookContainer\HookContainer::run in /var/www/html/w/includes/HookContainer/HookContainer.php at line 135] in /var/www/html/w/includes/Debug/MWDebug.php on line 372
Doubly Regularized Entropic Wasserstein Barycenters - MaRDI portal

Doubly Regularized Entropic Wasserstein Barycenters

From MaRDI portal
Publication:6430335

arXiv2303.11844MaRDI QIDQ6430335

Lénaïc Chizat

Publication date: 21 March 2023

Abstract: We study a general formulation of regularized Wasserstein barycenters that enjoys favorable regularity, approximation, stability and (grid-free) optimization properties. This barycenter is defined as the unique probability measure that minimizes the sum of entropic optimal transport (EOT) costs with respect to a family of given probability measures, plus an entropy term. We denote it (lambda,au)-barycenter, where lambda is the inner regularization strength and au the outer one. This formulation recovers several previously proposed EOT barycenters for various choices of lambda,augeq0 and generalizes them. First, in spite of -- and in fact owing to -- being emph{doubly} regularized, we show that our formulation is debiased for au=lambda/2: the suboptimality in the (unregularized) Wasserstein barycenter objective is, for smooth densities, of the order of the strength lambda2 of entropic regularization, instead of maxlambda,au in general. We discuss this phenomenon for isotropic Gaussians where all (lambda,au)-barycenters have closed form. Second, we show that for lambda,au>0, this barycenter has a smooth density and is strongly stable under perturbation of the marginals. In particular, it can be estimated efficiently: given n samples from each of the probability measures, it converges in relative entropy to the population barycenter at a rate n1/2. And finally, this formulation lends itself naturally to a grid-free optimization algorithm: we propose a simple emph{noisy particle gradient descent} which, in the mean-field limit, converges globally at an exponential rate to the barycenter.




Has companion code repository: https://github.com/lchizat/2023-doubly-entropic-barycenter








This page was built for publication: Doubly Regularized Entropic Wasserstein Barycenters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6430335)