For interpolating kernel machines, the minimum norm ERM solution is the most stable

Title	For interpolating kernel machines, the minimum norm ERM solution is the most stable
Publication Type	CBMM Memos
Year of Publication	2020
Authors	Rangamani, A, Rosasco, L, Poggio, T
Number	108
Date Published	06/2020
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.
arXiv	https://arxiv.org/abs/2006.15522
DSpace@MIT	https://hdl.handle.net/1721.1/125927