WIAS Preprint No. 2782, (2020)

Distributed optimization with quantization for computing Wasserstein barycenters



Authors

  • Krawchenko, Roman
  • Uribe, César A.
  • Gasnikov, Alexander
  • Dvurechensky, Pavel
    ORCID: 0000-0003-1201-2343

2010 Mathematics Subject Classification

  • 90C25 90C30 90C06

Keywords

  • Distributed convex optimization, quantization, optimal transport, Wasserstein distance

DOI

10.20347/WIAS.PREPRINT.2782

Abstract

We study the problem of the decentralized computation of entropy-regularized semi-discrete Wasserstein barycenters over a network. Building upon recent primal-dual approaches, we propose a sampling gradient quantization scheme that allows efficient communication and computation of approximate barycenters where the factor distributions are stored distributedly on arbitrary networks. The communication and algorithmic complexity of the proposed algorithm are shown, with explicit dependency on the size of the support, the number of distributions, and the desired accuracy. Numerical results validate our algorithmic analysis.

Download Documents