Random matrix asymptotics of inner product kernel spectral clustering

Abstract : We study in this article the asymptotic performance of spectral clustering with inner product kernel for Gaussian mixture models of high dimension with numerous samples. As is now classical in large dimensional spectral analysis, we establish a phase transition phenomenon by which a minimum distance between the class means and covariances is required for clustering to be possible from the dominant eigenvectors. Beyond this phase transition, we evaluate the asymptotic content of the dominant eigenvectors thus allowing for a full characterization of clustering performance. However, a surprising finding is that in some particular scenarios, the phase transition does not occur and clustering can be achieved irrespective of the class means and covariances. This is evidenced here in the case of the mixture of two Gaussian datasets having the same means and arbitrary difference between covariances.
Type de document :
Communication dans un congrès
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2018, Calgary, Canada. 〈10.1109/icassp.2018.8462052 〉
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01812005
Contributeur : Hafiz Tiomoko Ali <>
Soumis le : lundi 11 juin 2018 - 10:21:15
Dernière modification le : mercredi 21 novembre 2018 - 12:18:56
Document(s) archivé(s) le : mercredi 12 septembre 2018 - 21:23:16

Fichier

article_update_version3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Hafiz Tiomoko Ali, Abla Kammoun, Romain Couillet. Random matrix asymptotics of inner product kernel spectral clustering. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2018, Calgary, Canada. 〈10.1109/icassp.2018.8462052 〉. 〈hal-01812005〉

Partager

Métriques

Consultations de la notice

97

Téléchargements de fichiers

39