arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.05913math.OCcs.LG
收藏

鞍点问题的无约束方法

Gradient-Free Methods for Saddle-Point Problem

Moscow Institute of Physics and Technology(莫斯科物理技术学院);Sirius University of Science and Technology(天狼星科技大学);Institute for Information Transmission Problems RAS(俄罗斯科学院信息传输问题研究所);Adyghe State University(阿迪格国立大学)

Aleksandr Beznosikov, Abdurakhmon Sadiev, Alexander Gasnikov

摘要:

在本文中,我们推广的方法Gasnikov等。al,2017年,它允许用不精确的无梯度预言来解决(随机)凸鞍点问题。所提出的方法至少像现有的最佳方法一样有效。但对于一个特殊的设置(单纯形类型的限制和接近Lipschitz常数在1和2的规范),我们的方法减少了$\frac{n}{\log n}$倍所需的Oracle调用(函数计算)。我们的方法通过有限差分使用梯度的随机逼近。在这种情况下,函数必须指定不仅在优化集本身,但在一定的邻域it.In第二部分的文件,我们分析的情况下,当这样的假设不能,我们提出了一个一般的方法,就如何现代化的方法来解决这个问题,我们也将这种方法应用到一些经典集的特殊情况。

英文摘要:

In the paper, we generalize the approach Gasnikov et. al, 2017, which allows to solve (stochastic) convex optimization problems with an inexact gradient-free oracle, to the convex-concave saddle-point problem. The proposed approach works, at least, like the best existing approaches. But for a special set-up (simplex type constraints and closeness of Lipschitz constants in 1 and 2 norms) our approach reduces $\frac{n}{\log n}$ times the required number of oracle calls (function calculations). Our method uses a stochastic approximation of the gradient via finite differences. In this case, the function must be specified not only on the optimization set itself, but in a certain neighbourhood of it. In the second part of the paper, we analyze the case when such an assumption cannot be made, we propose a general approach on how to modernize the method to solve this problem, and also we apply this approach to particular cases of some classical sets.

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。

↑