Penalized Barycenters in the Wasserstein Space

TL;DR

This paper introduces a regularization method for Wasserstein barycenters of random measures, providing theoretical guarantees for existence, uniqueness, stability, and convergence, applicable to both discrete and continuous measures.

Contribution

It develops a convex penalization framework for Wasserstein barycenters, proving existence, uniqueness, and stability, and analyzing convergence of empirical barycenters to population counterparts.

Findings

Existence and uniqueness of penalized Wasserstein barycenters established.

Stability results for penalized barycenters derived using Bregman divergence.

Convergence of empirical barycenters towards population barycenters demonstrated.

Abstract

In this paper, a regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^{d}$ is introduced via convex penalization. The existence and uniqueness of such barycenters is first proved for a large class of penalization functions. The Bregman divergence associated to the penalization term is then considered to obtain a stability result on penalized barycenters. This allows the comparison of data made of $n$ absolutely continuous probability measures, within the more realistic setting where one only has access to a dataset of random variables sampled from unknown distributions. The convergence of the penalized empirical barycenter of a set of $n$ iid random probability measures towards its population counterpart is finally analyzed. This approach is shown to be appropriate for the statistical analysis of either discrete or absolutely continuous random measures. It also allows to construct, from a set of discrete measures, consistent estimators of population Wasserstein barycenters that are absolutely continuous.