Discriminative variable selection for clustering with the sparse Fisher-EM algorithm

Abstract : The interest in variable selection for clustering has increased recently due to the growing need in clustering high-dimensional data. Variable selection allows in particular to ease both the clustering and the interpretation of the results. Existing approaches have demonstrated the efficiency of variable selection for clustering but turn out to be either very time consuming or not sparse enough in high-dimensional spaces. This work proposes to perform a selection of the discriminative variables by introducing sparsity in the loading matrix of the Fisher-EM algorithm. This clustering method has been recently proposed for the simultaneous visualization and clustering of high-dimensional data. It is based on a latent mixture model which fits the data into a low-dimensional discriminative subspace. Three different approaches are proposed in this work to introduce sparsity in the orientation matrix of the discriminative subspace through \ell_{1} -type penalizations. Experimental comparisons with existing approaches on simulated and real-world data sets demonstrate the interest of the proposed methodology. An application to the segmentation of hyperspectral images of the planet Mars is also presented.
Type de document :
Article dans une revue
Computational Statistics, Springer Verlag, 2014, 29 (3-4), pp.489-513. <10.1007/s00180-013-0433-6>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00685183
Contributeur : Charles Bouveyron <>
Soumis le : mardi 10 avril 2012 - 09:10:29
Dernière modification le : jeudi 16 mars 2017 - 01:07:48
Document(s) archivé(s) le : mercredi 11 juillet 2012 - 02:50:11

Fichier

article_sparseFEM.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Collections

Citation

Charles Bouveyron, Camille Brunet-Saumard. Discriminative variable selection for clustering with the sparse Fisher-EM algorithm. Computational Statistics, Springer Verlag, 2014, 29 (3-4), pp.489-513. <10.1007/s00180-013-0433-6>. <hal-00685183v2>

Partager

Métriques

Consultations de
la notice

428

Téléchargements du document

308