Saved in:
Bibliographic Details
Main Authors: Bao, Chenglong, Yuan, Yancheng, Zhu, Shulan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10826
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908705823391744
author Bao, Chenglong
Yuan, Yancheng
Zhu, Shulan
author_facet Bao, Chenglong
Yuan, Yancheng
Zhu, Shulan
contents This paper focuses on investigating an inexact stochastic model-based optimization algorithm that integrates preconditioning techniques for solving stochastic composite optimization problems. The proposed framework unifies and extends the fixed-metric stochastic model-based algorithm to its preconditioned and inexact variants. Convergence guarantees are established under mild assumptions for both weakly convex and convex settings, without requiring smoothness or global Lipschitz continuity of the objective function. By assuming a local Lipschitz condition, we derive nonasymptotic and asymptotic convergence rates measured by the gradient of the Moreau envelope. Furthermore, convergence rates in terms of the distance to the optimal solution set are obtained under an additional quadratic growth condition on the objective function. Numerical experiment results demonstrate the theoretical findings for the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Convergence Analysis of an Inexact Preconditioned Stochastic Model-Based Algorithm
Bao, Chenglong
Yuan, Yancheng
Zhu, Shulan
Optimization and Control
This paper focuses on investigating an inexact stochastic model-based optimization algorithm that integrates preconditioning techniques for solving stochastic composite optimization problems. The proposed framework unifies and extends the fixed-metric stochastic model-based algorithm to its preconditioned and inexact variants. Convergence guarantees are established under mild assumptions for both weakly convex and convex settings, without requiring smoothness or global Lipschitz continuity of the objective function. By assuming a local Lipschitz condition, we derive nonasymptotic and asymptotic convergence rates measured by the gradient of the Moreau envelope. Furthermore, convergence rates in terms of the distance to the optimal solution set are obtained under an additional quadratic growth condition on the objective function. Numerical experiment results demonstrate the theoretical findings for the proposed algorithm.
title On the Convergence Analysis of an Inexact Preconditioned Stochastic Model-Based Algorithm
topic Optimization and Control
url https://arxiv.org/abs/2512.10826