鞍点
算法
马鞍
点(几何)
梯度法
计算机科学
数学
应用数学
数学优化
几何学
作者
Ekaterina Statkevich,Sofiya Bondar,Darina Dvinskikh,Alexander Gasnikov,A. V. Lobanov
标识
DOI:10.1016/j.chaos.2024.115048
摘要
This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermediate step, we generalize Same-sample Stochastic Extra-gradient algorithm (Gorbunov et al., 2022) to a biased oracle and estimate novel convergence rates. As the result of the paper we introduce an algorithm, which uses gradient approximation instead of a gradient oracle. We also conduct an analysis to find the maximum admissible level of adversarial noise and the optimal number of iterations at which our algorithm can guarantee achieving the desired accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI