arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.13428math.OC
收藏

求解带有马尔可夫随机性的变分不等式的办法

Methods for Solving Variational Inequalities with Markovian Stochasticity

Basic Research of Artificial Intelligence Laboratory (BRAIn Lab)(人工智能基础研究实验室)

Vladimir Solodkin, Michael Ermoshin, Roman Gavrilenko, Aleksandr Beznosikov

AI总结:

本文提出一种新方法求解具有马尔可夫动态的变分不等式,通过extragradient技术证明在弱假设下算法收敛,并通过实验研究混合时间参数对收敛性的影响。

摘要:

在本文中,我们提出了一种新颖的随机方法来求解变分不等式(VI)问题,特别是在马尔可夫噪声背景下。通过利用Extragradient技术,我们可以有效地解决由马尔可夫动态特征的VI优化问题。我们通过严格的理论分析证明了算法在相当温和的假设下收敛,包括$ L $-Lipschitz性、算子的强单调性和噪声在最优时的有界性。为了进一步理解马尔可夫过程的本质,我们进行了实验,以研究混合时间参数对算法收敛性的影响。

英文摘要:

In this paper, we present a novel stochastic method for solving variational inequalities (VI) in the context of Markovian noise. By leveraging Extragradient technique, we can productively solve VI optimization problems characterized by Markovian dynamics. We demonstrate the efficacy of proposed method through rigorous theoretical analysis, proving convergence under quite mild assumptions of $L$-Lipschitzness, strong monotonicity of the operator and boundness of the noise only at the optimum. In order to gain further insight into the nature of Markov processes, we conduct the experiments to investigate the impact of the mixing time parameter on the convergence of the algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑