Abstract: This EM review article focuses on parameter expansion, a simple technique introduced in the PX-EM algorithm to make EM converge faster while maintaining its simplicity and stability. The primary objective concerns the connection between parameter expansion and efficient inference. It reviews the statistical interpretation of the PX-EM algorithm, in terms of efficient inference via bias reduction, and further unfolds the PX-EM mystery by looking at PX-EM from different perspectives. In addition, it briefly discusses potential applications of parameter expansion to statistical inference and the broader impact of statistical thinking on understanding and developing other iterative optimization algorithms.
Recommendations
- Parameter expansion to accelerate EM: the PX-EM algorithm
- Parameter Expansion for Data Augmentation
- scientific article; zbMATH DE number 7128886
- An example of algorithm mining: Covariance adjustment to accelerate EM and Gibbs
- Computational aspects of fitting mixture models via the expectation-maximization algorithm
Cites work
- scientific article; zbMATH DE number 5816767 (Why is no real title available?)
- scientific article; zbMATH DE number 3567782 (Why is no real title available?)
- scientific article; zbMATH DE number 1086057 (Why is no real title available?)
- scientific article; zbMATH DE number 5274820 (Why is no real title available?)
- A remark on the shape of the logistic distribution
- A theoretical comparison of the data augmentation, marginal augmentation and PX-DA algorithms
- Alternating Subspace-Spanning Resampling to Accelerate Markov Chain Monte Carlo Simulation
- Bayesian Analysis of Binary and Polychotomous Response Data
- Cross-fertilizing strategies for better EM mountain climbing and DA field exploration: a graphical guide book
- Dempster-Shafer inference with weak beliefs
- Dempster-Shafer theory and statistical inference with weak beliefs
- Ellipsoidally symmetric extensions of the general location model for mixed categorical and continuous data
- ML estimation of the multivariate t distribution and the EM algorithm
- Maximum likelihood estimation via the ECM algorithm: A general framework
- Parameter Expansion for Data Augmentation
- Parameter expansion to accelerate EM: the PX-EM algorithm
- Parameterization and Bayesian Modeling
- Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)
- Seeking efficient data augmentation schemes via conditional and marginal augmentation
- Statistical Quasi-Newton: A New Look at Least Change
- THE ESTIMATION FROM INDIVIDUAL RECORDS OF THE RELATIONSHIP BETWEEN DOSE AND QUANTAL RESPONSE
- The ECME algorithm: A simple extension of EM and ECM with faster monotone convergence
Cited in
(2)
This page was built for publication: Parameter expansion and efficient inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q906525)
