Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03021394
Contributor : Gersende Fort Connect in order to contact the contributor
Submitted on : Tuesday, November 24, 2020 - 12:09:55 PM
Last modification on : Monday, April 4, 2022 - 3:24:14 PM
Long-term archiving on: : Thursday, February 25, 2021 - 7:39:30 PM

Files

GeomSPIDEREM_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03021394, version 1
  • ARXIV : 2011.12392

Citation

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

Share

Metrics

Record views

150

Files downloads

99