A distributed Bregman forward-backward algorithm for a class of Nash equilibrium problems

Wicak Ananduta*, Sergio Grammatico

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Downloads (Pure)

Abstract

We present a distributed Nash equilibrium seeking method based on the Bregman forward-backward splitting, which allows us to have a mirror mapping instead of the standard projection as the backward operator. Our main technical contribution is to show convergence to a Nash equilibrium when the game has cocoercive pseudogradient mapping. Furthermore, when the feasible sets of the agents are simplices, a suitable choice of a Legendre function results in an exponentiated pseudogradient method, which, in our numerical experience, performs out the standard projected pseudogradient and dual averaging methods.

Original languageEnglish
Article number100686
Number of pages6
JournalEuropean Journal of Control
Volume68
DOIs
Publication statusPublished - 2022

Keywords

  • Distributed algorithms
  • Nash equilibrium seeking problems
  • Non-cooperative games

Fingerprint

Dive into the research topics of 'A distributed Bregman forward-backward algorithm for a class of Nash equilibrium problems'. Together they form a unique fingerprint.

Cite this