One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems
Abstract
In this paper, we analyze gradient-free methods with one-point feedback for stochastic saddle point problems . 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.
Cite
@article{arxiv.2103.00321,
title = {One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems},
author = {Aleksandr Beznosikov and Vasilii Novitskii and Alexander Gasnikov},
journal= {arXiv preprint arXiv:2103.00321},
year = {2022}
}
Comments
arXiv admin note: text overlap with arXiv:2005.05913