一种面向去中心化非凸-强凹极小极大优化的高效随机算法
An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
浏览论文内容
中文总结 AI 辅助
针对多智能体网络下的随机非凸-强凹极小极大优化问题,提出DREAM算法,在寻找ε-平稳点上取得最优理论复杂度,且数值实验验证其优于现有方法。
中文摘要 AI 辅助
本文研究多智能体网络下的随机非凸-强凹极小极大优化问题。我们提出了一种名为Decentralized Recursive gradient descEnt Ascent Method(DREAM,去中心化递归梯度下降上升法)的高效算法,该算法在寻找ε-平稳点方面达到了目前已知的最优理论保证。具体而言,它需要O(min(κ³ε⁻³, κ²√N ε⁻²))次随机一阶预言机(SFO)调用以及Õ(κ²ε⁻²)轮通信,其中κ为条件数,N为个体函数的总数量。我们的数值实验也验证了DREAM相较于现有方法的优越性。
英文摘要
This paper studies the stochastic nonconvex-strongly-concave minimax optimization over a multi-agent network. We propose an efficient algorithm, called Decentralized Recursive gradient descEnt Ascent Method (DREAM), which achieves the best-known theoretical guarantee for finding the $ε$-stationary points. Concretely, it requires $\mathcal{O}(\min (κ^3ε^{-3},κ^2 \sqrt{N} ε^{-2} ))$ stochastic first-order oracle (SFO) calls and $\tilde{\mathcal{O}}(κ^2 ε^{-2})$ communication rounds, where $κ$ is the condition number and $N$ is the total number of individual functions. Our numerical experiments also validate the superiority of DREAM over previous methods.
发表机构
- SGIT AI Lab, State Grid Corporation of China(国网公司SGIT AI实验室)
- School of Data Science, Fudan University(复旦大学数据科学学院)
- Shanghai Key Laboratory for Contemporary Applied Mathematics(上海市现代应用数学重点实验室)
机构由 AI 辅助整理,请以论文原文为准。