Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems

被引：0
|
作者：
Doan, Thinh T. [1 ]
机构：
[1] Department of Electrical and Computer Engineering, Virginia Tech, United States
来源：
Proceedings of Machine Learning Research | 2022年 / 168卷
关键词：
Engineering Village;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Ascent algorithms - Condition - Convergence rates - Gradient descent-ascent method - Gradient-descent - Min-max optimization - Nonconvex - Singular perturbation theory - Two time scale - Two-time-scale dynamic
引用
收藏
页码：192 / 206
相关论文
共 17 条
  • [1] Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems
    Doan, Thinh T.
    LEARNING FOR DYNAMICS AND CONTROL CONFERENCE, VOL 168, 2022, 168
  • [2] Convergence Rates of Gradient Descent-Ascent Dynamics Under Delays in Solving Nonconvex Min-Max Optimization
    Do, Duy Anh
    Doan, Thinh T.
    2024 European Control Conference, ECC 2024, 2024, : 2748 - 2753
  • [3] Alternating Gradient Descent Ascent for Nonconvex Min-Max Problems in Robust Learning and GANs
    Lu, Songtao
    Singh, Rahul
    Chen, Xiangyi
    Chen, Yongxin
    Hong, Mingyi
    CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 680 - 684
  • [4] Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent
    Flokas, Lampros
    Vlatakis-Gkaragkounis, Emmanouil V.
    Piliouras, Georgios
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
  • [5] Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
    Yan, Yan
    Xu, Yi
    Lin, Qihang
    Liu, Wei
    Yang, Tianbao
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [6] Fixed-Time Convergence for a Class of Nonconvex-Nonconcave Min-Max Problems
    Garg, Kunal
    Baranwal, Mayank
    2022 EIGHTH INDIAN CONTROL CONFERENCE, ICC, 2022, : 19 - 24
  • [7] Last-Iterate Convergence Rates for Min-Max Optimization: Convergence of Hamiltonian Gradient Descent and Consensus Optimization
    Abernethy, Jacob
    Lai, Kevin A.
    Wibisono, Andre
    ALGORITHMIC LEARNING THEORY, VOL 132, 2021, 132
  • [8] Dissipative Gradient Descent Ascent Method: A Control Theory Inspired Algorithm for Min-Max Optimization
    Zheng, Tianqi
    Loizou, Nicolas
    You, Pengcheng
    Mallada, Enrique
    IEEE CONTROL SYSTEMS LETTERS, 2024, 8 : 2009 - 2014
  • [9] AN ACCELERATED INEXACT PROXIMAL POINT METHOD FOR SOLVING NONCONVEX-CONCAVE MIN-MAX PROBLEMS
    Kong, Weiwei
    Monteiro, Renato D. C.
    SIAM JOURNAL ON OPTIMIZATION, 2021, 31 (04) : 2558 - 2585
  • [10] Convergence rate analysis of the gradient descent-ascent method for convex-concave saddle-point problems
    Zamani, Moslem
    Abbaszadehpeivasti, Hadi
    de Klerk, Etienne
    OPTIMIZATION METHODS & SOFTWARE, 2024, 39 (05): : 967 - 989
12