Close Search Advanced
Journals
Resources
About Us
Open Access

Stochastic Trust-Region Methods with Trust-Region Radius Depending on Probabilistic Models

Stochastic Trust-Region Methods with Trust-Region Radius Depending on Probabilistic Models
Preview
Add to basket

Year:    2022

Author:    Xiaoyu Wang, Yaxiang Yuan

Journal of Computational Mathematics, Vol. 40 (2022), Iss. 2 : pp. 294–334

Abstract

We present a stochastic trust-region model-based framework in which its radius is related to the probabilistic models. Especially, we propose a specific algorithm termed STRME, in which the trust-region radius depends linearly on the gradient used to define the latest model. The complexity results of the STRME method in nonconvex, convex and strongly convex settings are presented, which match those of the existing algorithms based on probabilistic properties. In addition, several numerical experiments are carried out to reveal the benefits of the proposed methods compared to the existing stochastic trust-region methods and other relevant stochastic gradient methods.

Submit Article

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/jcm.2012-m2020-0144

Journal of Computational Mathematics, Vol. 40 (2022), Iss. 2 : pp. 294–334

Published online:    2022-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    41

Keywords:    Trust-region methods Stochastic optimization Probabilistic models Trust-region radius Global convergence.

Author Details

Xiaoyu Wang

Yaxiang Yuan

  1. A stochastic first-order trust-region method with inexact restoration for finite-sum minimization

    Bellavia, Stefania | Krejić, Nataša | Morini, Benedetta | Rebegoldi, Simone

    Computational Optimization and Applications, Vol. 84 (2023), Iss. 1 P.53

    https://doi.org/10.1007/s10589-022-00430-7 [Citations: 6]

  2. Riemannian Natural Gradient Methods

    Hu, Jiang | Ao, Ruicheng | So, Anthony Man-Cho | Yang, Minghan | Wen, Zaiwen

    SIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 1 P.A204

    https://doi.org/10.1137/22M1509643 [Citations: 1]

  3. A stochastic nonmonotone trust-region training algorithm for image classification

    Yousefi, Mahsa | Calomardo, Ángeles Martínez

    2022 16th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), (2022), P.522

    https://doi.org/10.1109/SITIS57111.2022.00084 [Citations: 2]

  4. Stochastic Trust-Region Algorithm in Random Subspaces with Convergence and Expected Complexity Analyses

    Dzahini, K. J. | Wild, S. M.

    SIAM Journal on Optimization, Vol. 34 (2024), Iss. 3 P.2671

    https://doi.org/10.1137/22M1524072 [Citations: 1]

  5. Convergence and worst-case complexity of adaptive Riemannian trust-region methods for optimization on manifolds

    Sheng, Zhou | Yuan, Gonglin

    Journal of Global Optimization, Vol. 89 (2024), Iss. 4 P.949

    https://doi.org/10.1007/s10898-024-01378-0 [Citations: 0]