Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

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

Abstract

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 (677.59 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

Gersende Fort, Eric Moulines, Hoi-To Wai. Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, Canada. ⟨hal-03021394v2⟩
212 View
117 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More