On Convergence Properties of the Monte Carlo EM Algorithm

TL;DR

This paper reviews the convergence properties of the EM and Monte Carlo EM algorithms, demonstrating their theoretical behavior, practical implementation, and implications for high-dimensional data analysis.

Contribution

It provides an accessible, rigorous introduction to EM and Monte Carlo EM convergence, including proofs, examples, and practical insights for determining sample sizes.

Findings

EM converges to a stationary point of the likelihood.

Convergence rate of EM is at best linear.

Monte Carlo EM's convergence depends on sample size and approximation accuracy.

Abstract

The Expectation-Maximization (EM) algorithm (Dempster, Laird and Rubin, 1977) is a popular method for computing maximum likelihood estimates (MLEs) in problems with missing data. Each iteration of the al- gorithm formally consists of an E-step: evaluate the expected complete-data log-likelihood given the observed data, with expectation taken at current pa- rameter estimate; and an M-step: maximize the resulting expression to find the updated estimate. Conditions that guarantee convergence of the EM se- quence to a unique MLE were found by Boyles (1983) and Wu (1983). In complicated models for high-dimensional data, it is common to encounter an intractable integral in the E-step. The Monte Carlo EM algorithm of Wei and Tanner (1990) works around this difficulty by maximizing instead a Monte Carlo approximation to the appropriate conditional expectation. Convergence properties of Monte Carlo EM have been studied, most notably, by Chan and Ledolter (1995) and Fort and Moulines (2003). The goal of this review paper is to provide an accessible but rigorous in- troduction to the convergence properties of EM and Monte Carlo EM. No previous knowledge of the EM algorithm is assumed. We demonstrate the im- plementation of EM and Monte Carlo EM in two simple but realistic examples. We show that if the EM algorithm converges it converges to a stationary point of the likelihood, and that the rate of convergence is linear at best. For Monte Carlo EM we present a readable proof of the main result of Chan and Ledolter (1995), and state without proof the conclusions of Fort and Moulines (2003). An important practical implication of Fort and Moulines's (2003) result relates to the determination of Monte Carlo sample sizes in MCEM; we provide a brief review of the literature (Booth and Hobert, 1999; Caffo, Jank and Jones, 2005) on that problem.