Almost Sure Convergence and Non-Asymptotic Concentration Bounds for Stochastic Mirror Descent Algorithm

被引：0
|
作者：
Paul, Anik Kumar [1 ]
Mahindrakar, Arun D. [1 ]
Kalaimani, Rachel K. [1 ]
机构：
[1] Indian Inst Technol Madras, Dept Elect Engn, Chennai 600036, India
来源：
IEEE CONTROL SYSTEMS LETTERS | 2024年 / 8卷
关键词：
Mirror descent algorithm; almost sure convergence; concentration inequality; sub-gaussian random vectors; OPTIMIZATION;
D O I：
10.1109/LCSYS.2024.3482148
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This letter investigates the convergence and concentration properties of the Stochastic Mirror Descent (SMD) algorithm utilizing biased stochastic subgradients. We establish the almost sure convergence of the algorithm's iterates under the assumption of diminishing bias. Furthermore, we derive concentration bounds for the discrepancy between the iterates' function values and the optimal value, based on standard assumptions. Subsequently, leveraging the assumption of Sub-Gaussian noise in stochastic subgradients, we present refined concentration bounds for this discrepancy.
引用
收藏
页码：2397 / 2402
页数：6
相关论文
共 50 条
  • [31] Non-Asymptotic Error Bounds for Bidirectional GANs
    Liu, Shiao
    Yang, Yunfei
    Huang, Jian
    Jiao, Yuling
    Wang, Yang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [32] Almost sure convergence of solutions to non-homogeneous stochastic difference equation
    Berkolaiko, G
    Rodkina, A
    JOURNAL OF DIFFERENCE EQUATIONS AND APPLICATIONS, 2006, 12 (06) : 535 - 553
  • [33] Asymptotic almost sure efficiency of averaged stochastic algorithms
    Pelletier, M
    COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE I-MATHEMATIQUE, 1996, 323 (07): : 813 - 816
  • [34] Asymptotic almost sure efficiency of averaged stochastic algorithms
    Pelletier, M
    SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2000, 39 (01) : 49 - 72
  • [35] Optimal Non-Asymptotic Bounds for the Sparse β Model
    Yang, Xiaowei
    Pan, Lu
    Cheng, Kun
    Liu, Chao
    MATHEMATICS, 2023, 11 (22)
  • [36] Non-asymptotic distributional bounds for the Dickman approximation of the running time of the Quickselect algorithm
    Goldstein, Larry
    ELECTRONIC JOURNAL OF PROBABILITY, 2018, 23
  • [37] Almost sure and mean convergence of extended stochastic complexity
    Gotoh, M
    Matsushima, T
    Hirasawa, S
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1999, E82A (10) : 2129 - 2137
  • [38] Almost sure convergence to zero in stochastic growth models
    Kamihigashi, Takashi
    ECONOMIC THEORY, 2006, 29 (01) : 231 - 237
  • [39] Almost sure convergence to zero in stochastic growth models
    Takashi Kamihigashi
    Economic Theory, 2006, 29 : 231 - 237
  • [40] On Almost Sure Convergence Rates of Stochastic Gradient Methods
    Liu, Jun
    Yuan, Ye
    CONFERENCE ON LEARNING THEORY, VOL 178, 2022, 178
12345