Mirror Descent-Ascent for mean-field min-max problems

Razvan-Andrei Lascu, Mateusz Majka, Łukasz Szpruch

Research output: Working paperPreprint

Abstract

We study two variants of the mirror descent-ascent algorithm for solving min-max problems on the space of measures: simultaneous and sequential. We work under assumptions of convexity-concavity and relative smoothness of the payoff function with respect to a suitable Bregman divergence, defined on the space of measures via flat derivatives. We show that the convergence rates to mixed Nash equilibria, measured in the Nikaidò-Isoda error, are of order O(N−1/2) and O(N−2/3) for the simultaneous and sequential schemes, respectively, which is in line with the state-of-the-art results for related finite-dimensional algorithms.
Original languageEnglish
PublisherarXiv
DOIs
Publication statusPublished - 28 May 2024

Publication series

NamearXiv

Fingerprint

Dive into the research topics of 'Mirror Descent-Ascent for mean-field min-max problems'. Together they form a unique fingerprint.

Cite this