vix.ing · top · new · best · stats

On the Convergence Properties of the EM Algorithm

1983/03/01 by C. F. Jeff Wu, Changbao Wu · 3,298 citations
Engineering · Mathematics · Physics and Astronomy · #Algorithm #Applied mathematics #Computer science #Control Systems and Identification #Convergence (economics) #Differentiable function #Estimation theory #Expectation–maximization algorithm #Exponential family #Exponential function #Function (biology) #Likelihood function #Limit (mathematics) #Limit of a function #Mathematical analysis #Mathematics #Maximum likelihood #Scientific Research and Discoveries #Sequence (biology) #Statistical and numerical algorithms #Statistics #Weak convergence

paper · pdf · doi:10.1214/aos/1176346060

published in The Annals of Statistics 11(1) (Institute of Mathematical Statistics)

openalex publication_date 1983/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

Two convergence aspects of the EM algorithm are studied: (i) does the EM algorithm find a local maximum or a stationary value of the (incomplete-data) likelihood function? (ii) does the sequence of parameter estimates generated by EM converge? Several convergence results are obtained under conditions that are applicable to many practical situations. Two useful special cases are: (a) if the unobserved complete-data specification can be described by a curved exponential family with compact parameter space, all the limit points of any EM sequence are stationary points of the likelihood function; (b) if the likelihood function is unimodal and a certain differentiability condition is satisfied, then any EM sequence converges to the unique maximum likelihood estimate. A list of key properties of the algorithm is included.

Citations

Cited by

Related