Show simple item record

dc.contributor.authorRangamani, Akshay
dc.contributor.authorRosasco, Lorenzo
dc.contributor.authorPoggio, Tomaso
dc.date.accessioned2020-06-23T13:18:04Z
dc.date.available2020-06-23T13:18:04Z
dc.date.issued2020-06-22
dc.identifier.urihttps://hdl.handle.net/1721.1/125927
dc.description.abstractWe study the average CVloo stability of kernel ridge-less regression and derive corresponding risk bounds. We show that the interpolating solution with minimum norm has the best CVloo stability, which in turn is controlled by the condition number of the empirical kernel matrix. The latter can be characterized in the asymptotic regime where both the dimension and cardinality of the data go to infinity. Under the assumption of random kernel matrices, the corresponding test error follows a double descent curve.en_US
dc.description.sponsorshipThis material is based upon work supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216.en_US
dc.publisherCenter for Brains, Minds and Machines (CBMM)en_US
dc.relation.ispartofseriesCBMM Memo;108
dc.titleFor interpolating kernel machines, the minimum norm ERM solution is the most stableen_US
dc.typeTechnical Reporten_US
dc.typeWorking Paperen_US
dc.typeOtheren_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record