Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex

被引：14
|
作者：
Gasnikov, A. V. [1 ,2 ]
Lagunovskaya, A. A. [1 ,3 ]
Usmanova, I. N. [1 ,2 ]
Fedorenko, F. A. [1 ]
机构：
[1] State Univ, Moscow Inst Phys & Technol, Moscow, Russia
[2] Russian Acad Sci, Inst Informat Transmiss Problems, Kharkevich Inst, Moscow, Russia
[3] Russian Acad Sci, Keldysh Inst Appl Math, Moscow, Russia
来源：
AUTOMATION AND REMOTE CONTROL | 2016年 / 77卷 / 11期
基金：
俄罗斯科学基金会; 俄罗斯基础研究基金会;
关键词：
Stochastic systems;
D O I：
10.1134/S0005117916110114
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 propose a modification of the mirror descent method for non-smooth stochastic convex optimization problems on the unit simplex. The optimization problems considered differ from the classical ones by availability of function values realizations. Our purpose is to derive the convergence rate of the method proposed and to determine the level of noise that does not significantly affect the convergence rate.
引用
收藏
页码：2018 / 2034
页数：17
相关论文
共 50 条
  • [31] Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold
    Wang, Bokun
    Ma, Shiqian
    Xue, Lingzhou
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
  • [32] Inexact Proximal Gradient Methods for Non-Convex and Non-Smooth Optimization
    Gu, Bin
    Wang, De
    Huo, Zhouyuan
    Huang, Heng
    [J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3093 - 3100
  • [33] Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold
    Wang, Bokun
    Ma, Shiqian
    Xue, Lingzhou
    [J]. Journal of Machine Learning Research, 2022, 23
  • [34] Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
    E. A. Vorontsova
    A. V. Gasnikov
    E. A. Gorbunov
    P. E. Dvurechenskii
    [J]. Automation and Remote Control, 2019, 80 : 1487 - 1501
  • [35] Gradient-free algorithms for distributed online convex optimization
    Liu, Yuhang
    Zhao, Wenxiao
    Dong, Daoyi
    [J]. ASIAN JOURNAL OF CONTROL, 2023, 25 (04) : 2451 - 2468
  • [36] Distributed and Inexact Proximal Gradient Method for Online Convex Optimization
    Bastianello, Nicola
    Dall'Anese, Emiliano
    [J]. 2021 EUROPEAN CONTROL CONFERENCE (ECC), 2021, : 2432 - 2437
  • [37] Accelerated Stochastic Gradient-free and Projection-free Methods
    Huang, Feihu
    Tao, Lue
    Chen, Songcan
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [38] Inexact tensor methods and their application to stochastic convex optimization
    Agafonov, Artem
    Kamzolov, Dmitry
    Dvurechensky, Pavel
    Gasnikov, Alexander
    Takac, Martin
    [J]. OPTIMIZATION METHODS & SOFTWARE, 2023, 39 (01): : 42 - 83
  • [39] New inertial proximal gradient methods for unconstrained convex optimization problems
    Peichao Duan
    Yiqun Zhang
    Qinxiong Bu
    [J]. Journal of Inequalities and Applications, 2020
  • [40] New inertial proximal gradient methods for unconstrained convex optimization problems
    Duan, Peichao
    Zhang, Yiqun
    Bu, Qinxiong
    [J]. JOURNAL OF INEQUALITIES AND APPLICATIONS, 2020, 2020 (01)
12345