Laboratoire IMATH

Institut de Mathématiques de Toulon (EA 2134)

logoUTLN

Séminaire de Thibaut Le Gouic (Univ. Marseille)

Séminaire MN-AA
Jeudi 27/10/22, 14h30, Salle M210

Sampler for the Wasserstein barycenter

Résumé : Wasserstein barycenters have become a central object in applied optimal transport as a tool to summarize complex objects that can be represented as distributions. Such objects include posterior distributions in Bayesian statistics, functions in functional data analysis and images in graphics. In a nutshell a Wasserstein barycenter is a probability distribution that provides a compelling summary of a finite set of input distributions. While the question of computing Wasserstein barycenters has received significant attention, this talk focuses on a new and important question : sampling from a barycenter given a natural query access to the input distribution. We describe a new methodology built on the theory of Gradient flows over Wasserstein space.
This is joint work with Chiheb Daaloul, Magali Tournus and Jacques Liandrat.

Séminaire de Thibaut Le Gouic (Univ. Marseille)