Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue ESAIM: Probability and Statistics Année : 2019

Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective

Résumé

An usual problem in statistics consists in estimating the minimizer of a convex function. When we have to deal with large samples taking values in high dimensional spaces, stochastic gradient algorithms and their averaged versions are efficient candidates. Indeed, (1) they do not need too much computational efforts, (2) they do not need to store all the data, which is crucial when we deal with big data, (3) they allow to simply update the estimates, which is important when data arrive sequentially. The aim of this work is to give asymptotic and non asymptotic rates of convergence of stochastic gradient estimates as well as of their averaged versions when the function we would like to minimize is only locally strongly convex.
Fichier principal
Vignette du fichier
ps180092.pdf (602.39 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-01678852 , version 1 (30-01-2024)

Identifiants

Citer

Antoine Godichon-Baggioni. Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective. ESAIM: Probability and Statistics, 2019, 23, pp.841-873. ⟨10.1051/ps/2019011⟩. ⟨hal-01678852⟩
82 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More