Parameter-based reduction of Gaussian mixture models with a variational-Bayes approach

Abstract : This paper proposes a technique for simplifying a given Gaussian mixture model, i.e. reformulating the density in a more parcimonious manner, if possible (less Gaussian components in the mixture). Numerous applications requiring aggregation of models from various sources, or index structures over sets of mixture models for fast access, may benefit from the technique. Variational Bayesian estimation of mixtures is known to be a powerful technique on punctual data. We derive herein a new version of the Variational-Bayes EM algorithm that operates on Gaussian components of a given mixture and suppresses redundancy, if any, while preserving structure of the underlying generative process. A main feature of the present scheme is that it merely resorts to the parameters of the original mixture, ensuring low computational cost. Experimental results are reported on real data.
Type de document :
Communication dans un congrès
IAPR. International Conference on Pattern Recognition (ICPR'2008), 2008, Tampa, United States. IEEE, pp.450-453, 2008
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00368883
Contributeur : Marc Gelgon <>
Soumis le : mardi 17 mars 2009 - 19:46:13
Dernière modification le : mercredi 11 avril 2018 - 01:57:16
Document(s) archivé(s) le : vendredi 12 octobre 2012 - 13:45:39

Fichier

ICPR.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : inria-00368883, version 1

Citation

Pierrick Bruneau, Marc Gelgon, Fabien Picarougne. Parameter-based reduction of Gaussian mixture models with a variational-Bayes approach. IAPR. International Conference on Pattern Recognition (ICPR'2008), 2008, Tampa, United States. IEEE, pp.450-453, 2008. 〈inria-00368883〉

Partager

Métriques

Consultations de la notice

204

Téléchargements de fichiers

186