ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2106.03579
33
6

Forward Looking Best-Response Multiplicative Weights Update Methods for Bilinear Zero-sum Games

7 June 2021
M. Fasoulakis
E. Markakis
Yannis Pantazis
Constantinos Varsos
ArXivPDFHTML
Abstract

Our work focuses on extra gradient learning algorithms for finding Nash equilibria in bilinear zero-sum games. The proposed method, which can be formally considered as a variant of Optimistic Mirror Descent \cite{DBLP:conf/iclr/MertikopoulosLZ19}, uses a large learning rate for the intermediate gradient step which essentially leads to computing (approximate) best response strategies against the profile of the previous iteration. Although counter-intuitive at first sight due to the irrationally large, for an iterative algorithm, intermediate learning step, we prove that the method guarantees last-iterate convergence to an equilibrium. Particularly, we show that the algorithm reaches first an η1/ρ\eta^{1/\rho}η1/ρ-approximate Nash equilibrium, with ρ>1\rho > 1ρ>1, by decreasing the Kullback-Leibler divergence of each iterate by at least Ω(η1+1ρ)\Omega(\eta^{1+\frac{1}{\rho}})Ω(η1+ρ1​), for sufficiently small learning rate, η\etaη, until the method becomes a contracting map, and converges to the exact equilibrium. Furthermore, we perform experimental comparisons with the optimistic variant of the multiplicative weights update method, by \cite{Daskalakis2019LastIterateCZ} and show that our algorithm has significant practical potential since it offers substantial gains in terms of accelerated convergence.

View on arXiv
Comments on this paper