Adaptive control mechanisms in gradient descent algorithms

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Iannelli, Andrea
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911122981912576
author Iannelli, Andrea
author_facet Iannelli, Andrea
contents The problem of designing adaptive stepsize sequences for the gradient descent method applied to convex and locally smooth functions is studied. We take an adaptive control perspective and design update rules for the stepsize that make use of both past (measured) and future (predicted) information. We show that Lyapunov analysis can guide in the systematic design of adaptive parameters striking a balance between convergence rates and robustness to computational errors or inexact gradient information. Theoretical and numerical results indicate that closed-loop adaptation guided by system theory is a promising approach for designing new classes of adaptive optimization algorithms with improved convergence properties.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19100
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive control mechanisms in gradient descent algorithms
Iannelli, Andrea
Optimization and Control
Systems and Control
The problem of designing adaptive stepsize sequences for the gradient descent method applied to convex and locally smooth functions is studied. We take an adaptive control perspective and design update rules for the stepsize that make use of both past (measured) and future (predicted) information. We show that Lyapunov analysis can guide in the systematic design of adaptive parameters striking a balance between convergence rates and robustness to computational errors or inexact gradient information. Theoretical and numerical results indicate that closed-loop adaptation guided by system theory is a promising approach for designing new classes of adaptive optimization algorithms with improved convergence properties.
title Adaptive control mechanisms in gradient descent algorithms
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2508.19100