arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.09421math.OC
收藏

联合改进去中心化随机Minimax优化中的样本与通信复杂度

Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization

Xuan Zhang, Gabriel Mancino-Ball, Necdet Serhat Aybat, Yangyang Xu

AI总结:

提出单环去中心化算法DGDA-VR,在连通网络上求解随机非凸强凹minimax问题,首次联合优化并达到了与下界匹配的最优样本与通信复杂度。

摘要:

我们提出了一种名为DGDA-VR的新型单环去中心化算法,用于在由$M$个智能体组成的连通网络上求解随机非凸强凹minimax问题。通过使用随机一阶预言机来估计局部梯度,我们证明该算法能以$\mathcal{O}(ε^{-3})$的样本复杂度和$\mathcal{O}(ε^{-2})$的通信复杂度找到$ε$精确解,两者均达到最优并与该类问题的下界相匹配。与竞争方法不同,该算法不需要多次通信即可保证收敛结果成立,使其适用于更广泛的计算环境。据我们所知,这是首个针对此处所考虑问题联合优化样本与通信复杂度的此类算法。

英文摘要:

We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of $M$ agents. By using stochastic first-order oracles to estimate the local gradients, we prove that our algorithm finds an $ε$-accurate solution with $\mathcal{O}(ε^{-3})$ sample complexity and $\mathcal{O}(ε^{-2})$ communication complexity, both of which are optimal and match the lower bounds for this class of problems. Unlike competitors, our algorithm does not require multiple communications for the convergence results to hold, making it applicable to a broader computational environment setting. To the best of our knowledge, this is the first such algorithm to jointly optimize the sample and communication complexities for the problem considered here.

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。

↑