Saved in:
Bibliographic Details
Main Authors: Jerinkic, Natasa Krklec, Morini, Benedetta, Yousefi, Mahsa
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16263
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914571040587776
author Jerinkic, Natasa Krklec
Morini, Benedetta
Yousefi, Mahsa
author_facet Jerinkic, Natasa Krklec
Morini, Benedetta
Yousefi, Mahsa
contents A stochastic gradient method for finite-sum minimization subject to deterministic linear constraints is proposed and analyzed. The procedure presented adapts the projected gradient method on convex set to the use of both a stochastic gradient and a possibly inexact projection map. Under standard assumptions in the field of stochastic gradient methods, we provide theoretical results in agreement with the theory for unconstrained problems. Numerical results are presented to show the practical behavior of the procedure.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16263
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Projected Stochastic Gradient Method for Finite-Sum Problems with Linear Equality Constraints
Jerinkic, Natasa Krklec
Morini, Benedetta
Yousefi, Mahsa
Optimization and Control
A stochastic gradient method for finite-sum minimization subject to deterministic linear constraints is proposed and analyzed. The procedure presented adapts the projected gradient method on convex set to the use of both a stochastic gradient and a possibly inexact projection map. Under standard assumptions in the field of stochastic gradient methods, we provide theoretical results in agreement with the theory for unconstrained problems. Numerical results are presented to show the practical behavior of the procedure.
title A Projected Stochastic Gradient Method for Finite-Sum Problems with Linear Equality Constraints
topic Optimization and Control
url https://arxiv.org/abs/2605.16263