Show simple item record

dc.contributor.advisorTomaso Poggio
dc.contributor.authorPoggio, Tomasoen_US
dc.contributor.authorRosasco, Lorenzoen_US
dc.contributor.authorWibisono, Andreen_US
dc.contributor.otherCenter for Biological and Computational Learning (CBCL)en_US
dc.date.accessioned2009-12-01T21:15:05Z
dc.date.available2009-12-01T21:15:05Z
dc.date.issued2009-12-01
dc.identifier.urihttp://hdl.handle.net/1721.1/49868
dc.description.abstractIn 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.extent16 p.en_US
dc.relation.ispartofseriesCBCL-284
dc.relation.ispartofseriesMIT-CSAIL-TR-2009-060
dc.subjectartificial intelligenceen_US
dc.subjecttheoryen_US
dc.subjectcomputationen_US
dc.subjectlearningen_US
dc.titleSufficient Conditions for Uniform Stability of Regularization Algorithmsen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record