Mirror Descent-Ascent for mean-field min-max problems
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要