@article{2592,
  title = {Statistical Properties of Kernel Principal Component Analysis},
  journal = {Machine Learning},
  abstract = {We study the properties of the eigenvalues of Gram matrices in a non-asymptotic setting. Using local Rademacher averages, we
  provide data-dependent and tight bounds for their convergence towards
  eigenvalues of the corresponding kernel operator. We perform these computations in a functional analytic framework which allows to deal implicitly with reproducing kernel Hilbert spaces of infinite dimension. This can
  have applications to various kernel algorithms, such as Support Vector
  Machines (SVM). We focus on Kernel Principal Component Analysis
  (KPCA) and, using such techniques, we obtain sharp excess risk bounds
  for the reconstruction error. In these bounds, the dependence on the
  decay of the spectrum and on the closeness of successive eigenvalues is
  made explicit.},
  volume = {66},
  number = {2-3},
  pages = {259-294},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = mar,
  year = {2006},
  slug = {2592},
  author = {Blanchard, G. and Bousquet, O. and Zwald, L.},
  month_numeric = {3}
}