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

On the Convergence Properties of the Mini-Batch EM and MCEM Algorithms

Belhal Karimi 1, 2 Marc Lavielle 1, 2 Éric Moulines 2, 1 
1 XPOP - Modélisation en pharmacologie de population
CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique, Inria Saclay - Ile de France
Abstract : The EM algorithm is one of the most popular algorithm for inference in latent data models. For large datasets, each iteration of the algorithm can be numerically involved. To alleviate this problem, (Neal and Hinton, 1998) has proposed an incremental version in which the conditional expectation of the latent data (E-step) is computed on a mini-batch of observations. In this paper, we analyse this variant and propose and analyse the Monte Carlo version of the incremental EM in which the conditional expectation is evaluated by a Markov Chain Monte Carlo (MCMC). We establish the almost-sure convergence of these algorithms, covering both the mini-batch EM and its stochastic version. Various numerical applications are introduced in this article to illustrate our findings.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [41 references]  Display  Hide  Download
Contributor : Belhal Karimi Connect in order to contact the contributor
Submitted on : Saturday, October 26, 2019 - 5:09:04 PM
Last modification on : Friday, February 4, 2022 - 3:09:54 AM
Long-term archiving on: : Monday, January 27, 2020 - 2:12:51 PM


Files produced by the author(s)


  • HAL Id : hal-02334485, version 1


Belhal Karimi, Marc Lavielle, Éric Moulines. On the Convergence Properties of the Mini-Batch EM and MCEM Algorithms. 2019. ⟨hal-02334485⟩



Record views


Files downloads