Learning theory estimates via integral operators and their approximations

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

428 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)153-172
Journal / PublicationConstructive Approximation
Volume26
Issue number2
Publication statusPublished - Aug 2007

Abstract

The regression problem in learning theory is investigated with least square Tikhonov regularization schemes in reproducing kernel Hilbert spaces (RKHS). We follow our previous work and apply the sampling operator to the error analysis in both the RKHS norm and the L2 norm. The tool for estimating the sample error is a Bennet inequality for random variables with values in Hilbert spaces. By taking the Hilbert space to be the one consisting of Hilbert-Schmidt operators in the RKHS, we improve the error bounds in the L2 metric, motivated by an idea of Caponnetto and de Vito. The error bounds we derive in the RKHS norm, together with a Tsybakov function we discuss here, yield interesting applications to the error analysis of the (binary) classification problem, since the RKHS metric controls the one for the uniform convergence. © 2007 Springer.

Research Area(s)

  • Learning theory, Regularization scheme, Reproducing kernel Hilbert space, Sampling operator, Vector-valued random variable

Citation Format(s)