An Almost Sure Convergence Analysis of Zeroth-Order Mirror Descent Algorithm

被引：0
|
作者：
Paul, Anik Kumar [1 ]
Mahindrakar, Arun D. [1 ]
Kalaimani, Rachel K. [1 ]
机构：
[1] IIT Madras, Dept Elect Engn, Chennai 600036, India
来源：
2023 AMERICAN CONTROL CONFERENCE, ACC | 2023年
关键词：
derivative-free optimization; Distributed Optimization; almost sure convergence; OPTIMIZATION;
D O I：
10.23919/ACC55779.2023.10156450
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, we show almost sure convergence of zeroth-order mirror descent algorithm. The algorithm admits non-smooth convex functions and assumes only an estimate of the gradient is available, obtained using Nesterov's Gausssian Approximation technique (NGA). We establish that under suitable condition of step-size, the function value of the iterates of the algorithm converge to a neighborhood of the optimal function value almost surely. We extend the analysis to the distributed implementation of the zeroth-order mirror descent algorithm.
引用
收藏
页码：855 / 860
页数：6
相关论文
共 50 条
  • [1] Robust Analysis of Almost Sure Convergence of Zeroth-Order Mirror Descent Algorithm
    Paul, Anik Kumar
    Mahindrakar, Arun D.
    Kalaimani, Rachel K.
    [J]. IEEE CONTROL SYSTEMS LETTERS, 2023, 7 : 1933 - 1938
  • [2] Almost sure convergence rates of stochastic proximal gradient descent algorithm
    Liang, Yuqing
    Xu, Dongpo
    [J]. OPTIMIZATION, 2024, 73 (08) : 2413 - 2446
  • [3] Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method
    Zhang, Shengjun
    Dong, Yunlong
    Xie, Dong
    Yao, Lisha
    Bailey, Colleen P.
    Fu, Shengli
    [J]. 2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, : 1180 - 1185
  • [4] ZEROTH-ORDER STOCHASTIC PROJECTED GRADIENT DESCENT FOR NONCONVEX OPTIMIZATION
    Liu, Sijia
    Li, Xingguo
    Chen, Pin-Yu
    Haupt, Jarvis
    Amini, Lisa
    [J]. 2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2018), 2018, : 1179 - 1183
  • [5] Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications
    Liu, Sijia
    Chen, Jie
    Chen, Pin-Yu
    Hero, Alfred O.
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, 2018, 84
  • [6] Almost sure convergence of randomised-difference descent algorithm for stochastic convex optimisation
    Geng, Xiaoxue
    Huang, Gao
    Zhao, Wenxiao
    [J]. IET CONTROL THEORY AND APPLICATIONS, 2021, 15 (17): : 2183 - 2194
  • [7] LQR with Tracking: A Zeroth-order Approach and Its Global Convergence
    Ren, Zhaolin
    Zhong, Aoxiao
    Li, Na
    [J]. 2021 AMERICAN CONTROL CONFERENCE (ACC), 2021, : 2562 - 2568
  • [8] On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
    Cheng, Shuyu
    Wu, Guoqiang
    Zhu, Jun
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [9] A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization
    Cai, HanQin
    Lou, Yuchen
    Mckenzie, Daniel
    Yin, Wotao
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [10] A Proximal Zeroth-Order Algorithm for Nonconvex Nonsmooth Problems
    Kazemi, Ehsan
    Wang, Liqiang
    [J]. 2018 56TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2018, : 64 - 71
12345