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

Part of Advances in Neural Information Processing Systems 15 (NIPS 2002)

Bibtex Metadata Paper

Authors

Christopher Williams, John Shawe-taylor

Abstract

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel k(ยท, .) corresponding to a sample Xl, ... ,Xm drawn from a density p(x) and the eigenvalues of the corresponding continuous eigenproblem. We bound the dif(cid:173) ferences between the two spectra and provide a performance bound on kernel peA.