The Stability of Kernel Principal Components Analysis and its Relation to the Process Eigenspectrum

Christopher Williams, John S. Shawe-taylor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we analyze the relationships between the eigenvaluesof the m x m Gram matrix K for a kernel k(·, .) corresponding to asample Xl, ... ,Xm drawn from a density p(x) and the eigenvaluesof the corresponding continuous eigenproblem. We bound the differencesbetween the two spectra and provide a performance boundon kernel PCA.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 15 (NIPS 2002)
EditorsS. Becker, S. Thrun, K. Obermayer
PublisherMIT Press
Pages383-390
Number of pages8
Publication statusPublished - 2003

Fingerprint

Dive into the research topics of 'The Stability of Kernel Principal Components Analysis and its Relation to the Process Eigenspectrum'. Together they form a unique fingerprint.

Cite this