When Kernel Ridge Regression Meets the Hölder-Zygmund Class: Minimax Optimality and Failure of Properness
Yuxuan Hou
stat.ML cs.LG math.ST
Abstract
We study kernel ridge regression for nonparametric regression over the Hölder-Zygmund class. Using an RKHS equivalent to a Sobolev space of smoothness s+d/2, we prove that misspecified KRR attains the minimax L2 rate n^{-2s/(2s+d)}. We also show that properness fails in the Hölder-Zygmund norm: even for the zero regression function with Gaussian noise, the expected squared Hölder-Zygmund norm of the KRR noise component grows as log n.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.