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
  • [21] Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach.
    Greco, Giacomo
    Noble, Maxence
    Conforti, Giovanni
    Oliviero-Durmus, Alain
    THIRTY SIXTH ANNUAL CONFERENCE ON LEARNING THEORY, VOL 195, 2023, 195 : 716 - 746
  • [22] Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
    Zhang, Jianyi
    Zhang, Ruiyi
    Carin, Lawrence
    Chen, Changyou
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 1877 - 1886
  • [23] On almost sure convergence results in stochastic calculus
    Karandikar, Rajeeva L.
    IN MEMORIAM PAUL-ANDRE MEYER: SEMINAIRE DE PROBABILITIES XXXIX, 2006, 1874 : 137 - 147
  • [24] On almost sure convergence for sums of stochastic sequence
    Wang, Zhong-zhi
    Dong, Yun
    Ding, Fangqing
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2019, 48 (14) : 3609 - 3621
  • [25] ALMOST SURE CONVERGENCE OF A CLASS OF STOCHASTIC ALGORITHMS
    BISCARAT, JC
    STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 1994, 50 (01) : 83 - 99
  • [26] ON ALMOST-SURE BOUNDS FOR THE LMS ALGORITHM
    KOURITZIN, MA
    IEEE TRANSACTIONS ON INFORMATION THEORY, 1994, 40 (02) : 372 - 383
  • [27] General Tail Bounds for Non-Smooth Stochastic Mirror Descent
    Eldowa, Khaled
    Paudice, Andrea
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [28] Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT
    Anastasiou, Andreas
    Balasubramanian, Krishnakumar
    Erdogdu, Murat A.
    CONFERENCE ON LEARNING THEORY, VOL 99, 2019, 99
  • [29] The elitist non-homogeneous genetic algorithm: Almost sure convergence
    Rojas Cruz, J. A.
    Pereira, A. G. C.
    STATISTICS & PROBABILITY LETTERS, 2013, 83 (10) : 2179 - 2185
  • [30] CONVERGENCE OF THE EMPIRICAL MEASURE IN EXPECTED WASSERSTEIN DISTANCE: NON-ASYMPTOTIC EXPLICIT BOUNDS IN Rd
    Fournier, Nicolas
    ESAIM-PROBABILITY AND STATISTICS, 2023, 27 : 749 - 775
12345