On the Convergence of Eigenspaces in Kernel Principal Component Analysis

Part of Advances in Neural Information Processing Systems 18 (NIPS 2005)

Bibtex Metadata Paper


Laurent Zwald, Gilles Blanchard


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. 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.