Acceleration of the EM algorithm: P-EM versus epsilon algorithm

DOI10.1016/j.csda.2012.03.005zbMath1254.65018MaRDI QIDQ1927191

Christophe Roland, Alain F. Berlinet

Publication date: 30 December 2012

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2012.03.005

zbMATH Keywords

convergence; EM algorithm; acceleration; fixed point iteration; epsilon algorithm

Mathematics Subject Classification ID

62F10: Point estimation

Related Items

Accelerated Estimation of Switching Algorithms: The Cointegrated VAR Model and Other Applications, Geometric approach to the parallel sum of vectors and application to the vector \(\varepsilon \)-algorithm, Modeling discrete stock price changes using a mixture of Poisson distributions, A multivariate linear regression analysis using finite mixtures of \(t\) distributions, Improving mixture tree construction using better EM algorithms, Estimating random-intercept models on data streams

Uses Software

• SQUAREM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Acceleration of the EM algorithm using the vector epsilon algorithm
• Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models
• Accelerating the convergence of the EM algorithm using the vector \(\varepsilon \) algorithm
• On the convergence properties of the EM algorithm
• Extrapolation methods theory and practice
• Accélération de la convergence en analyse numérique
• Acceleration Techniques for Iterated Vector and Matrix Problems
• The EM Algorithm and Extensions, 2E
• Parameter expansion to accelerate EM: the PX-EM algorithm
• A curious likelihood identity for the multivariate t-distribution