arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08708math.OCcs.LGstat.ML
收藏

非凸-强-凹Min-Max Optimization的复杂性下界

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization

Massachusetts Institute of Technology(麻省理工学院)

Haochuan Li, Yi Tian, Jingzhao Zhang, Ali Jadbabaie

摘要:

我们提供了一个一阶的甲骨文复杂性下界寻找最小最大最优化问题的平稳点,其中的目标函数是光滑的,非凸的最小化变量,和强凹的最大化变量。我们建立了确定性预言机的$Ω\left(\sqrtκε^{-2}\right)$的一个下界,其中$ε$定义了近似平稳的水平,$κ$是条件数.我们的分析表明,(Lin et al.,2020 b)在高达对数因子的$ε$和$κ$依赖性中是最佳的。对于随机预言机,我们给出了$Ω\left(\sqrtκε^{-2} + κ^{1/3}ε^{-4}\right)$的一个下界.这表明在(Lin等人,2020 a)和我们的下限在条件数依赖。

英文摘要:

We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minimization variable, and strongly concave in the maximization variable. We establish a lower bound of $Ω\left(\sqrtκε^{-2}\right)$ for deterministic oracles, where $ε$ defines the level of approximate stationarity and $κ$ is the condition number. Our analysis shows that the upper bound achieved in (Lin et al., 2020b) is optimal in the $ε$ and $κ$ dependence up to logarithmic factors. For stochastic oracles, we provide a lower bound of $Ω\left(\sqrtκε^{-2} + κ^{1/3}ε^{-4}\right)$. It suggests that there is a significant gap between the upper bound $\mathcal{O}(κ^3 ε^{-4})$ in (Lin et al., 2020a) and our lower bound in the condition number dependence.

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。

↑