Show simple item record

dc.contributor.authorYing, Yiming
dc.contributor.authorCampbell, Colin
dc.date.accessioned2013-07-22T14:33:24Z
dc.date.issued2009
dc.description.abstractIn this paper we develop a novel probabilistic generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning algorithms reduces to investigation of the suprema of the Rademacher chaos process of order two over candidate kernels, which we refer to as Rademacher chaos complexity. Next, we show how to estimate the empirical Rademacher chaos complexity by well-established metric entropy integrals and pseudo-dimension of the set of candidate kernels. Our new methodology mainly depends on the principal theory of U-processes. Finally, we establish satisfactory excess generalization bounds and misclassification error rates for learning Gaussian kernels and general radial basis kernels.en_GB
dc.identifier.citation22nd Annual Conference on Learning Theory (COLT 2009), Montreal, Canada, 18-21 June 2009en_GB
dc.identifier.urihttp://hdl.handle.net/10871/11921
dc.language.isoenen_GB
dc.titleGeneralization bounds for learning the kernelen_GB
dc.typeConference paperen_GB
dc.date.available2013-07-22T14:33:24Z


Files in this item

This item appears in the following Collection(s)

Show simple item record