user

Adaptive Stochastic Mirror Descent for Constrained Optimization

被引：0
|
作者：
Bayandina, Anastasia [1 ]
机构：
[1] Moscow Inst Phys & Technol, Moscow, Russia
来源：
2017 CONSTRUCTIVE NONSMOOTH ANALYSIS AND RELATED TOPICS (DEDICATED TO THE MEMORY OF V.F. DEMYANOV) (CNSA) | 2017年
基金：
俄罗斯科学基金会;
关键词：
D O I：
暂无
中图分类号：
O1 [数学];
学科分类号：
0701 ; 070101 ;
摘要：
Mirror Descent (MD) is a well-known method of solving non-smooth convex optimization problems. This paper analyzes the stochastic variant of MD with adaptive stepsizes. Its convergence on average is shown to be faster than with the fixed stepsizes and optimal in terms of lower bounds.
引用
收藏
页码：40 / 43
页数：4
相关论文
共 50 条
  • [41] Adaptive Stochastic Gradient Descent Method for Convex and Non-Convex Optimization
    Chen, Ruijuan
    Tang, Xiaoquan
    Li, Xiuting
    [J]. FRACTAL AND FRACTIONAL, 2022, 6 (12)
  • [42] A Stochastic Interpretation of Stochastic Mirror Descent: Risk-Sensitive Optimality
    Azizan, Navid
    Hassibi, Babak
    [J]. 2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 3960 - 3965
  • [43] Stochastic incremental mirror descent algorithms with Nesterov smoothing
    Bitterlich, Sandy
    Grad, Sorin-Mihai
    [J]. NUMERICAL ALGORITHMS, 2024, 95 (01) : 351 - 382
  • [44] ON THE CONVERGENCE OF MIRROR DESCENT BEYOND STOCHASTIC CONVEX PROGRAMMING
    Zhou, Zhengyuan
    Mertikopoulos, Panayotis
    Bambos, Nicholas
    Boyd, Stephen P.
    Glynn, Peter W.
    [J]. SIAM JOURNAL ON OPTIMIZATION, 2020, 30 (01) : 687 - 716
  • [45] A CHARACTERIZATION OF STOCHASTIC MIRROR DESCENT ALGORITHMS AND THEIR CONVERGENCE PROPERTIES
    Azizan, Navid
    Hassibi, Babak
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 5167 - 5171
  • [46] Primal-Dual Stochastic Mirror Descent for MDPs
    Tiapkin, Daniil
    Gasnikov, Alexander
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [47] Validation analysis of mirror descent stochastic approximation method
    Guanghui Lan
    Arkadi Nemirovski
    Alexander Shapiro
    [J]. Mathematical Programming, 2012, 134 : 425 - 458
  • [48] Stochastic incremental mirror descent algorithms with Nesterov smoothing
    Sandy Bitterlich
    Sorin-Mihai Grad
    [J]. Numerical Algorithms, 2024, 95 : 351 - 382
  • [49] Validation analysis of mirror descent stochastic approximation method
    Lan, Guanghui
    Nemirovski, Arkadi
    Shapiro, Alexander
    [J]. MATHEMATICAL PROGRAMMING, 2012, 134 (02) : 425 - 458
  • [50] Distributed Mirror Descent for Online Composite Optimization
    Yuan, Deming
    Hong, Yiguang
    Ho, Daniel W. C.
    Xu, Shengyuan
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2021, 66 (02) : 714 - 729
12345