arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00321math.OC
收藏

光滑和非光滑鞍点问题的单点无约束方法

One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems

Aleksandr Beznosikov, Vasilii Novitskii, Alexander Gasnikov

摘要:

本文研究了随机鞍点问题$\min_{x}\max_{y} φ(x, y)$的单点反馈无梯度方法。对于非光滑和光滑的情况下,我们提出了分析在一个一般的几何设置与任意Bregman分歧。对于高阶光滑的问题,分析只在欧几里德的情况下进行。我们得到的估计重复目前已知的最好的无梯度方法的估计与一点反馈的问题,想象一个凸或强凸函数。本文使用三种主要方法通过有限差分来恢复梯度:随机方向的标准,以及其修改与内核和残差反馈。我们还提供了实验来比较这些方法的矩阵对策。

英文摘要:

In this paper, we analyze gradient-free methods with one-point feedback for stochastic saddle point problems $\min_{x}\max_{y} φ(x, y)$. For non-smooth and smooth cases, we present analysis in a general geometric setup with arbitrary Bregman divergence. For problems with higher-order smoothness, the analysis is carried out only in the Euclidean case. The estimates we have obtained repeat the best currently known estimates of gradient-free methods with one-point feedback for problems of imagining a convex or strongly convex function. The paper uses three main approaches to recovering the gradient through finite differences: standard with a random direction, as well as its modifications with kernels and residual feedback. We also provide experiments to compare these approaches for the matrix game.

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。

↑