A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Changjie, Yang, Hao, Chen, Shenglan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908933988286464
author Fang, Changjie
Yang, Hao
Chen, Shenglan
author_facet Fang, Changjie
Yang, Hao
Chen, Shenglan
contents In this paper, we propose a proximal stochasitc gradient algorithm (PSGA) for solving composite optimization problems by incorporating variance reduction techniques and an adaptive step-size strategy. In the PSGA method, the objective function consists of two components: one is a smooth convex function, and the other is a non-smooth convex function. We establish the strong convergence of the proposed method, provided that the smooth convex function is Lipschitz continuous. We also prove that the expected value of the error between the estimated gradient and the actual gradient converges to zero. Furthermore, we get an \( O(\sqrt{1/k}) \) convergence rate for our method. Finally, the effectiveness of the proposed method is validated through numerical experiments on Logistic regression and Lasso regression.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization
Fang, Changjie
Yang, Hao
Chen, Shenglan
Optimization and Control
90C15 90C25 90C30 49M37 65K05
In this paper, we propose a proximal stochasitc gradient algorithm (PSGA) for solving composite optimization problems by incorporating variance reduction techniques and an adaptive step-size strategy. In the PSGA method, the objective function consists of two components: one is a smooth convex function, and the other is a non-smooth convex function. We establish the strong convergence of the proposed method, provided that the smooth convex function is Lipschitz continuous. We also prove that the expected value of the error between the estimated gradient and the actual gradient converges to zero. Furthermore, we get an \( O(\sqrt{1/k}) \) convergence rate for our method. Finally, the effectiveness of the proposed method is validated through numerical experiments on Logistic regression and Lasso regression.
title A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization
topic Optimization and Control
90C15 90C25 90C30 49M37 65K05
url https://arxiv.org/abs/2509.11043