Advanced Search

Adaptive Kernel Methods Using the Balancing Principle

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Tomaso Poggio Rosasco, Lorenzo en_US Pereverzyev, Sergei en_US De Vito, Ernesto en_US
dc.contributor.other Center for Biological and Computational Learning (CBCL) en_US 2008-10-17T15:30:10Z 2008-10-17T15:30:10Z 2008-10-16
dc.description.abstract The regularization parameter choice is a fundamental problem in supervised learning since the performance of most algorithms crucially depends on the choice of one or more of such parameters. In particular a main theoretical issue regards the amount of prior knowledge on the problem needed to suitably choose the regularization parameter and obtain learning rates. In this paper we present a strategy, the balancing principle, to choose the regularization parameter without knowledge of the regularity of the target function. Such a choice adaptively achieves the best error rate. Our main result applies to regularization algorithms in reproducing kernel Hilbert space with the square loss, though we also study how a similar principle can be used in other situations. As a straightforward corollary we can immediately derive adaptive parameter choice for various kernel methods recently studied. Numerical experiments with the proposed parameter choice rules are also presented. en_US
dc.format.extent 24 p. en_US
dc.relation.ispartofseries MIT-CSAIL-TR-2008-062
dc.relation.ispartofseries CBCL-275
dc.subject Adaptive Model Selection en_US
dc.subject Learning Theory en_US
dc.subject Inverse Problems en_US
dc.subject Regularization en_US
dc.title Adaptive Kernel Methods Using the Balancing Principle en_US

Files in this item

Name Size Format Description
MIT-CSAIL-TR-2008 ... 406.4Kb PDF
MIT-CSAIL-TR-2008 ... 1.556Mb Postscript

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record