On the performance of kernel classes
Abstract
We present sharp bounds on the localized Rademacher averages of the unit ball in a reproducing kernel Hubert space in terms of the eigenvalues of the integral operator associated with the kernel. We use this result to estimate the performance of the empirical minimization algorithm when the base class is the unit ball of the reproducing kernel Hilbert space.
Description
Keywords
Citation
Collections
Source
Journal of Machine Learning Research