English

A GPM-based algorithm for solving regularized Wasserstein barycenter problems in some spaces of probability measures

Optimization and Control 2022-08-09 v4 Numerical Analysis Numerical Analysis

Abstract

In this paper, we focus on the analysis of the regularized Wasserstein barycenter problem. We provide uniqueness and a characterization of the barycenter for two important classes of probability measures: (i) Gaussian distributions and (ii) qq-Gaussian distributions; each regularized by a particular entropy functional. We propose an algorithm based on gradient projection method in the space of matrices in order to compute these regularized barycenters. We also consider a general class of φ\varphi-exponential measures, for which only the non-regularized barycenter is studied. Finally, we numerically show the influence of parameters and stability of the algorithm under small perturbation of data.

Keywords

Cite

@article{arxiv.2006.08743,
  title  = {A GPM-based algorithm for solving regularized Wasserstein barycenter problems in some spaces of probability measures},
  author = {S. Kum and M. H. Duong and Y. Lim and S. Yun},
  journal= {arXiv preprint arXiv:2006.08743},
  year   = {2022}
}

Comments

39 pages, significant revised from the previous version, results were strengthened, title changed

R2 v1 2026-06-23T16:21:08.768Z