An Asynchronous Decentralized Algorithm for Wasserstein Barycenter Problem

Chao Zhang, Hui Qian, Jiahao Xie
4/23/2023
cs.LG

No confident code implementation found for this paper.

Abstract

Wasserstein Barycenter Problem (WBP) has recently received much attention in the field of artificial intelligence. In this paper, we focus on the decentralized setting for WBP and propose an asynchronous decentralized algorithm (A$^2$DWB). A$^2$DWB is induced by a novel stochastic block coordinate descent method to optimize the dual of entropy regularized WBP. To our knowledge, A$^2$DWB is the first asynchronous decentralized algorithm for WBP. Unlike its synchronous counterpart, it updates local variables in a manner that only relies on the stale neighbor information, which effectively alleviate the waiting overhead, and thus substantially improve the time efficiency. Empirical results validate its superior performance compared to the latest synchronous algorithm.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations

81% match2023

A Particle-Flow Algorithm for Free-Support Wasserstein Barycenters

78% match2025

Asynchronous Decentralized SGD under Non-Convexity: A Block-Coordinate Descent Framework

77% match2025

Doubly Regularized Entropic Wasserstein Barycenters

76% match2023

On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization

76% match2024

Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization

75% match1 repo32025

Cite this paper

@article{zhang2023asynchronous,
  title  = {An Asynchronous Decentralized Algorithm for Wasserstein Barycenter Problem},
  author = {Chao Zhang and Hui Qian and Jiahao Xie},
  year   = {2023},
  eprint = {2304.11653},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.11653v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.11653.svg)](https://codeofpaper.com/paper/2304.11653)

Discussion