PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On the Eigenspectrum of the Gram Matrix and the Generalisation Error of Kernel PCA
John Shawe-Taylor, Christopher Williams, Nello Cristianini and Jaz Kandola
IEEE Transactions on Information Theory 239, 2004. ISSN 0018-9448

Abstract

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel ·(.;.) corresponding to a sample x1,...,xm drawn from a density p(x) and the eigenvalues of the corresponding continuous eigenproblem. We bound the differences between the two spectra and provide a performance bound on kernel PCA showing that we can expect good performance even in very high dimensional feature spaces provided the sample eigenvalues fall sufficiently quickly.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:962
Deposited By:John Shawe-Taylor
Deposited On:02 April 2005