Communication Dans Un Congrès Année : 2005

On the Convergence of Eigenspaces in Kernel Principal Component Analysis

Résumé

This paper presents a non-asymptotic statistical analysis of Kernel-PCA with a focus different from the one proposed in previous work on this topic (\cite{ShaWilCriKan02CDL}, chapter \ref{KPCA1chap}). Here instead of considering the reconstruction error of KPCA we are interested in approximation error bounds for the eigenspaces themselves. We prove an upper bound depending on the spacing between eigenvalues but not on the dimensionality of the eigenspace. As a consequence this allows to infer stability results for these estimated spaces.

Fichier principal
Vignette du fichier
Nips2005mod.pdf (107.73 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-00373803 , version 1 (07-04-2009)

Licence

Identifiants

  • HAL Id : hal-00373803 , version 1

Citer

Laurent Zwald, Gilles Blanchard. On the Convergence of Eigenspaces in Kernel Principal Component Analysis. NIPS, 2005, Vancouver, BC, Canada. ⟨hal-00373803⟩

Collections

300 Consultations
280 Téléchargements

Partager

  • More