A simulated annealing version of the EM algorithm for non-Gaussian deconvolution

Authors:
M. Lavielle;E. Moulines
Affiliations:
Universite´ Rene´ Descartes and Universite´ Paris-Sud, France lavielle@math-info.univ-paris5.fr;Te´le´com Paris/URA 820, 46, rue Barrault, 75634 Paris CEDEX 13, France
Venue:
Statistics and Computing
Year:
1997

Citing 3
Cited 4

Adaptive algorithms and stochastic approximations

Adaptive algorithms and stochastic approximations
Comparing sweep strategies for stochastic relaxation

Journal of Multivariate Analysis
Metropolis-type annealing algorithms for global optimization in Rd

SIAM Journal on Control and Optimization

Maximum likelihood estimation in nonlinear mixed effects models

Computational Statistics & Data Analysis
A SAEM algorithm for the estimation of template and deformation parameters in medical image sequences

Statistics and Computing
Bayesian learning of finite generalized Gaussian mixture models on images

Signal Processing
Simulated annealing algorithm with adaptive neighborhood

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Expectation–Maximization (EM) algorithm is a very popular technique for maximum likelihood estimation in incomplete data models. When the expectation step cannot be performed in closed form, a stochastic approximation of EM (SAEM) can be used. Under very general conditions, the authors have shown that the attractive stationary points of the SAEM algorithm correspond to the global and local maxima of the observed likelihood. In order to avoid convergence towards a local maxima, a simulated annealing version of SAEM is proposed. An illustrative application to the convolution model for estimating the coefficients of the filter is given.