Beyond Pham's algorithm for joint diagonalization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Beyond Pham's algorithm for joint diagonalization

Résumé

The approximate joint diagonalization of a set of matrices consists in finding a basis in which these matrices are as diagonal as possible. This problem naturally appears in several statistical learning tasks such as blind signal separation. We consider the diagonalization criterion studied in a seminal paper by Pham (2001), and propose a new quasi-Newton method for its optimization. Through numerical experiments on simulated and real datasets, we show that the proposed method outper-forms Pham's algorithm. An open source Python package is released.

Domaines

Autres [stat.ML]
Fichier principal
Vignette du fichier
main.pdf (329.66 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01936887 , version 1 (27-11-2018)

Identifiants

Citer

Pierre A Ablin, Jean-François Cardoso, Alexandre Gramfort. Beyond Pham's algorithm for joint diagonalization. ESSAN 2019 - 27th European symposium on artificial neural networks, Apr 2019, Bruges, Belgium. ⟨hal-01936887⟩
500 Consultations
761 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More