Stochastic gradient with least-squares control variates

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nobile, Fabio, Raviola, Matteo, Schaeffer, Nathan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908665767788544
author Nobile, Fabio
Raviola, Matteo
Schaeffer, Nathan
author_facet Nobile, Fabio
Raviola, Matteo
Schaeffer, Nathan
contents The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by leveraging stored gradient information; however, they are restricted to settings where the objective functional is a finite sum, and their performance degrades when the number of terms in the sum is large. In this work, we propose a novel approach which is well suited when the objective is given by an expectation over random variables with a continuous probability distribution. Our method constructs a control variate by fitting a linear model to past gradient evaluations using weighted discrete least-squares, effectively reducing variance while preserving computational efficiency. We establish theoretical sublinear convergence guarantees for strongly convex objectives and demonstrate the method's effectiveness through numerical experiments on random PDE-constrained optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic gradient with least-squares control variates
Nobile, Fabio
Raviola, Matteo
Schaeffer, Nathan
Optimization and Control
Numerical Analysis
The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by leveraging stored gradient information; however, they are restricted to settings where the objective functional is a finite sum, and their performance degrades when the number of terms in the sum is large. In this work, we propose a novel approach which is well suited when the objective is given by an expectation over random variables with a continuous probability distribution. Our method constructs a control variate by fitting a linear model to past gradient evaluations using weighted discrete least-squares, effectively reducing variance while preserving computational efficiency. We establish theoretical sublinear convergence guarantees for strongly convex objectives and demonstrate the method's effectiveness through numerical experiments on random PDE-constrained optimization problems.
title Stochastic gradient with least-squares control variates
topic Optimization and Control
Numerical Analysis
url https://arxiv.org/abs/2507.20981