Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization - Institut Polytechnique de Paris Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization

Résumé

The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings.
Fichier principal
Vignette du fichier
GeomSPIDEREM_HAL.pdf (203.6 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03021394 , version 1 (24-11-2020)
hal-03021394 , version 2 (08-02-2021)

Identifiants

Citer

Gersende Fort, Eric Moulines, Hoi-To Wai. Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization. 2020. ⟨hal-03021394v1⟩
206 Consultations
116 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More