mlsanityData to 7 Oct 2026

An Asynchronous Decentralized Algorithm for Wasserstein Barycenter Problem

arXiv 2304.11653 ↗First posted 23 Apr 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 (A2DWB). A2DWB is induced by a novel stochastic block coordinate descent method to optimize the dual of entropy regularized WBP. To our knowledge, A2DWB 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

20 of 39 references.

References · 20

  1. 2018Computational Optimal Transportcited by 765
  2. 2015Optimal Transport for Domain Adaptationcited by 457
  3. 2013Fast Computation of Wasserstein Barycenterscited by 216
  4. 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
  5. 2015Scalable Bayes via Barycenter in Wasserstein Spacecited by 44
  6. 2015Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Supportcited by 30
  7. 2015Fast Convergence Rates for Distributed Non-Bayesian Learningcited by 26
  8. 2013Accelerated, Parallel and Proximal Coordinate Descentcited by 25
  9. 2018Stochastic Wasserstein Barycenterscited by 25
  10. 2018Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenterscited by 21
  11. 2017Parallel Streaming Wasserstein Barycenterscited by 14
  12. 2018Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectivescited by 11
8 more
  1. 2018A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenterscited by 8
  2. 2018AsySPA: An Exact Asynchronous Algorithm for Convex Optimization Over Digraphscited by 6
  3. 2017Distributed Learning for Cooperative Inferencecited by 3
  4. 2018Accelerating Asynchronous Algorithms for Convex Optimization by Momentum Compensationcited by 2
  5. 2018Improved Linear Programs for Discrete Barycenterscited by 2
  6. 2018Asynchronous decentralized accelerated stochastic gradient descentcited by 2
  7. 2018A2BCD: An Asynchronous Accelerated Block Coordinate Descent Algorithm With Optimal Complexitycited by 1
  8. 2019Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite Sumscited by 1

Built on by

Not cited yet.