Result: Variational approximations in Bayesian model selection for finite mixture distributions

Title:
Variational approximations in Bayesian model selection for finite mixture distributions
Authors:
MCGRORY, C. A, TITTERINGTON, D. M
Source:
Advances in mixture modelsComputational statistics & data analysis. 51(11):5352-5367
Publisher Information:
Amsterdam: Elsevier Science, 2007.
Publication Year:
2007
Physical Description:
print, 3/4 p
Original Material:
INIST-CNRS
Subject Terms:
Mathematics, Mathématiques, Sciences exactes et technologie, Exact sciences and technology, Sciences et techniques communes, Sciences and techniques of general use, Mathematiques, Mathematics, Probabilités et statistiques, Probability and statistics, Statistiques, Statistics, Généralités, General topics, Inférence paramétrique, Parametric inference, Analyse multivariable, Multivariate analysis, Analyse numérique. Calcul scientifique, Numerical analysis. Scientific computation, Analyse numérique, Numerical analysis, Probabilités et statistiques numériques, Numerical methods in probability and statistics, Analyse donnée, Data analysis, Análisis datos, Apprentissage, Learning, Aprendizaje, Approximation, Aproximación, Calcul automatique, Computing, Cálculo automático, Calcul statistique, Statistical computation, Cálculo estadístico, Estimation Bayes, Bayes estimation, Estimación Bayes, Estimation paramètre, Parameter estimation, Estimación parámetro, Fonction répartition, Distribution function, Función distribución, Loi grand nombre, Law of large numbers, Ley gran número, Loi normale, Gaussian distribution, Curva Gauss, Mélange loi probabilité, Mixed distribution, Mezcla ley probabilidad, Sélection modèle, Model selection, Selección modelo, 49R50, 60E05, 60J20, 62F07, Analyse bayésienne, Critère information, Information criterion, Méthode sélection, Selection method, Bayesian analysis, Deviance information criterion (DIC), Mixtures, Variational approximations
Document Type:
Conference Conference Paper
File Description:
text
Language:
English
Author Affiliations:
University of Glasgow, United Kingdom
ISSN:
0167-9473
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=18830897
Rights:
Copyright 2007 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Mathematics
Accession Number:
edscal.18830897
Database:
PASCAL Archive

Further Information

Variational methods, which have become popular in the neural computing/machine learning literature, are applied to the Bayesian analysis of mixtures of Gaussian distributions. It is also shown how the deviance information criterion, (DIC), can be extended to these types of model by exploiting the use of variational approximations. The use of variational methods for model selection and the calculation of a DIC are illustrated with real and simulated data. The variational approach allows the simultaneous estimation of the component parameters and the model complexity. It is found that initial selection of a large number of components results in superfluous components being eliminated as the method converges to a solution. This corresponds to an automatic choice of model complexity. The appropriateness of this is reflected in the DIC values.