Properties of the stochastic approximation EM algorithm with mini-batch sampling

To deal with very large datasets a mini-batch version of the Monte Carlo Markov Chain Stochastic Approximation Expectation–Maximization algorithm for general latent variable models is proposed. For exponential models the algorithm is shown to be convergent under classical conditions as the number of...

Full description

Saved in:
Bibliographic Details
Published in:Statistics and computing 2020-11, Vol.30 (6), p.1725-1739
Main Authors: Kuhn, Estelle, Matias, Catherine, Rebafka, Tabea
Format: Article
Language:English
Subjects:
Algorithms
Approximation
Artificial Intelligence
Computing time
Convergence
Markov chains
Mathematical analysis
Mathematics and Statistics
Methodology
Probability and Statistics in Computer Science
Sampling
Statistical Theory and Methods
Statistics
Statistics and Computing/Statistics Programs
Statistics Theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To deal with very large datasets a mini-batch version of the Monte Carlo Markov Chain Stochastic Approximation Expectation–Maximization algorithm for general latent variable models is proposed. For exponential models the algorithm is shown to be convergent under classical conditions as the number of iterations increases. Numerical experiments illustrate the performance of the mini-batch algorithm in various models. In particular, we highlight that mini-batch sampling results in an important speed-up of the convergence of the sequence of estimators generated by the algorithm. Moreover, insights on the effect of the mini-batch size on the limit distribution are presented. Finally, we illustrate how to use mini-batch sampling in practice to improve results when a constraint on the computing time is given.
ISSN:0960-3174
1573-1375
DOI:10.1007/s11222-020-09968-0