Online estimation of the asymptotic variance for averaged stochastic gradient algorithms - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Statistical Planning and Inference Année : 2019

Online estimation of the asymptotic variance for averaged stochastic gradient algorithms

Résumé

Stochastic gradient algorithms are more and more studied since they can deal efficiently and online with large samples in high dimensional spaces. In this paper, we first establish a Central Limit Theorem for these estimates as well as for their averaged version in general Hilbert spaces. Moreover, since having the asymptotic normality of estimates is often unusable without an estimation of the asymptotic variance, we introduce a new recursive algorithm for estimating this last one, and we establish its almost sure rate of convergence as well as its rate of convergence in quadratic mean. Finally, two examples consisting in estimating the parameters of the logistic regression and estimating geometric quantiles are given.
Fichier principal
Vignette du fichier
S0378375819300011.pdf (334.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01678855 , version 1 (22-10-2021)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Antoine Godichon. Online estimation of the asymptotic variance for averaged stochastic gradient algorithms. Journal of Statistical Planning and Inference, 2019, 203, pp.Pages 1-19. ⟨10.1016/j.jspi.2019.01.001⟩. ⟨hal-01678855⟩
64 Consultations
37 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More