Convergence of the Iterates of the Stochastic Proximal Gradient Method

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Madariaga, Javier I.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914473886875648
author Madariaga, Javier I.
author_facet Madariaga, Javier I.
contents We propose a novel study of the stochastic proximal gradient method for minimizing the sum of two convex functions, one of which is smooth. Under suitable assumptions and without requiring any boundedness or control of the variance of the random variables, we derive the almost sure convergence and the convergence in the mean of the iterates to a solution of the minimization problem. The results are applied to classification and convex feasibility problems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13388
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Convergence of the Iterates of the Stochastic Proximal Gradient Method
Madariaga, Javier I.
Optimization and Control
We propose a novel study of the stochastic proximal gradient method for minimizing the sum of two convex functions, one of which is smooth. Under suitable assumptions and without requiring any boundedness or control of the variance of the random variables, we derive the almost sure convergence and the convergence in the mean of the iterates to a solution of the minimization problem. The results are applied to classification and convex feasibility problems.
title Convergence of the Iterates of the Stochastic Proximal Gradient Method
topic Optimization and Control
url https://arxiv.org/abs/2604.13388