%N 7 %V 51 %J IEEE TRANSACTIONS ON INFORMATION THEORY %L discovery13441 %T On the eigenspectrum of the Gram matrix and the generalization error of kernel-PCA %C LUBECK, GERMANY %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 %A J Shawe-Taylor %A CKI Williams %A N Cristianini %A J Kandola %I IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC %P 2510-2522 %D 2005