Advanced Search

Sufficient Conditions for Uniform Stability of Regularization Algorithms

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Tomaso Poggio Poggio, Tomaso en_US Rosasco, Lorenzo en_US Wibisono, Andre en_US
dc.contributor.other Center for Biological and Computational Learning (CBCL) en_US 2009-12-01T21:15:05Z 2009-12-01T21:15:05Z 2009-12-01
dc.description.abstract In this paper, we study the stability and generalization properties of penalized empirical-risk minimization algorithms. We propose a set of properties of the penalty term that is sufficient to ensure uniform ?-stability: we show that if the penalty function satisfies a suitable convexity property, then the induced regularization algorithm is uniformly ?-stable. In particular, our results imply that regularization algorithms with penalty functions which are strongly convex on bounded domains are ?-stable. In view of the results in [3], uniform stability implies generalization, and moreover, consistency results can be easily obtained. We apply our results to show that â p regularization for 1 < p <= 2 and elastic-net regularization are uniformly ?-stable, and therefore generalize. en_US
dc.format.extent 16 p. en_US
dc.relation.ispartofseries CBCL-284
dc.relation.ispartofseries MIT-CSAIL-TR-2009-060
dc.subject artificial intelligence en_US
dc.subject theory en_US
dc.subject computation en_US
dc.subject learning en_US
dc.title Sufficient Conditions for Uniform Stability of Regularization Algorithms en_US

Files in this item

Name Size Format Description
MIT-CSAIL-TR-2009 ... 284.7Kb PDF

This item appears in the following Collection(s)

Show simple item record