login

On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA

IEEE Transactions on Information TheoryPublished 28 June 2005
John Shawe‐Taylor, Chris K. Williams, Nello Cristianini, Jaz Kandola
Citations151
SJR quartileQ1
SJR score1.46
SNIP1.76

TL;DR

The differences between the two spectra are bounded and a performance bound on kernel principal component analysis (PCA) is provided showing that good performance can be expected even in very-high-dimensional feature spaces provided the sample eigenvalues fall sufficiently quickly.

Abstract

In this paper, the relationships between the eigenvalues of the m/spl times/m Gram matrix K for a kernel /spl kappa/(/spl middot/,/spl middot/) corresponding to a sample x/sub 1/,...,x/sub m/ drawn from a density p(x) and the eigenvalues of the corresponding continuous eigenproblem is analyzed. The differences between the two spectra are bounded and a performance bound on kernel principal component analysis (PCA) is provided showing that good performance can be expected even in very-high-dimensional feature spaces provided the sample eigenvalues fall sufficiently quickly.

Keywords

Computer ScienceMathematicsEngineering