A Bound on the Maximal Marginal Degrees of Freedom

arXiv:2402.12885v1 Announce Type: cross
Abstract: Common kernel ridge regression is expensive in memory allocation and computation time. This paper addresses low rank approximations and surrogates for kernel ridge regression, which bridge these difficulties. The fundamental contribution of the paper is a lower bound on the rank of the low dimensional approximation, which is required such that the prediction power remains reliable. The bound relates the effective dimension with the largest statistical leverage score. We characterize the effective dimension and its …

abstract approximation arxiv bridge computation cs.lg freedom kernel low memory paper regression ridge stat.ml type