dc.contributor.author | Rangamani, Akshay | |
dc.contributor.author | Rosasco, Lorenzo | |
dc.contributor.author | Poggio, Tomaso | |
dc.date.accessioned | 2020-06-23T13:18:04Z | |
dc.date.available | 2020-06-23T13:18:04Z | |
dc.date.issued | 2020-06-22 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/125927 | |
dc.description.abstract | We 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.sponsorship | This 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.publisher | Center for Brains, Minds and Machines (CBMM) | en_US |
dc.relation.ispartofseries | CBMM Memo;108 | |
dc.title | For interpolating kernel machines, the minimum norm ERM solution is the most stable | en_US |
dc.type | Technical Report | en_US |
dc.type | Working Paper | en_US |
dc.type | Other | en_US |