On some Variants of the EM Algorithm for the Fitting of Finite Mixture Models
Author(s)
Ng, Shu-Kay
J. McLachlan, Geoffrey
Griffith University Author(s)
Year published
2003
Metadata
Show full item recordAbstract
Finite mixture models are being increasingly used in statistical inference and to provide a model-based approach to cluster analysis. Mixture models can be fitted to independent data in a straightforward manner via the expectation-maximization (EM) algorithm. In this paper, we look at ways of speeding up the fitting of normal mixture models by using variants of the EM, including the so-called sparse and incremental versions. We also consider an incremental version based on imposing a multiresolution kd-tree structure on the data. Examples are given in which the EM algorithm can be speeded up by a factor of more than fifty ...
View more >Finite mixture models are being increasingly used in statistical inference and to provide a model-based approach to cluster analysis. Mixture models can be fitted to independent data in a straightforward manner via the expectation-maximization (EM) algorithm. In this paper, we look at ways of speeding up the fitting of normal mixture models by using variants of the EM, including the so-called sparse and incremental versions. We also consider an incremental version based on imposing a multiresolution kd-tree structure on the data. Examples are given in which the EM algorithm can be speeded up by a factor of more than fifty for large data sets of small dimension.
View less >
View more >Finite mixture models are being increasingly used in statistical inference and to provide a model-based approach to cluster analysis. Mixture models can be fitted to independent data in a straightforward manner via the expectation-maximization (EM) algorithm. In this paper, we look at ways of speeding up the fitting of normal mixture models by using variants of the EM, including the so-called sparse and incremental versions. We also consider an incremental version based on imposing a multiresolution kd-tree structure on the data. Examples are given in which the EM algorithm can be speeded up by a factor of more than fifty for large data sets of small dimension.
View less >
Journal Title
Austrian Journal of Statistics
Volume
32
Issue
1-2
Publisher URI
Subject
Statistics not elsewhere classified
Statistics