%0 Journal Article %@ 1557-9654 %A Shawe-Taylor, J %A Williams, CKI %A Cristianini, N %A Kandola, J %D 2005 %F discovery:13441 %I IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC %J IEEE TRANSACTIONS ON INFORMATION THEORY %K Science & Technology, Technology, Computer Science, Information Systems, Engineering, Electrical & Electronic, Computer Science, Engineering, concentration bounds, Gram matrices, kernel methods, principal components analysis (PCA), Rademacher complexity, spectra of random matrices, statistical learning theory, ASYMPTOTIC-DISTRIBUTION, LATENT ROOTS, INEQUALITIES, EIGENVALUES, COVARIANCE %N 7 %P 2510-2522 %T On the eigenspectrum of the Gram matrix and the generalization error of kernel-PCA %U https://discovery.ucl.ac.uk/id/eprint/13441/ %V 51