Regularization in kernel learning
Statistics Theory
2010-01-14 v1 Statistics Theory
Abstract
Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one can use a regularization term that grows significantly slower than the standard quadratic growth in the RKHS norm.
Cite
@article{arxiv.1001.2094,
title = {Regularization in kernel learning},
author = {Shahar Mendelson and Joseph Neeman},
journal= {arXiv preprint arXiv:1001.2094},
year = {2010}
}
Comments
Published in at http://dx.doi.org/10.1214/09-AOS728 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)