Open Access
Translator Disclaimer
February 2010 Regularization in kernel learning
Shahar Mendelson, Joseph Neeman
Ann. Statist. 38(1): 526-565 (February 2010). DOI: 10.1214/09-AOS728

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.

Citation

Download Citation

Shahar Mendelson. Joseph Neeman. "Regularization in kernel learning." Ann. Statist. 38 (1) 526 - 565, February 2010. https://doi.org/10.1214/09-AOS728

Information

Published: February 2010
First available in Project Euclid: 31 December 2009

zbMATH: 1191.68356
MathSciNet: MR2590050
Digital Object Identifier: 10.1214/09-AOS728

Subjects:
Primary: 68Q32
Secondary: 60G99

Keywords: least-squares , Model selection , regression , Regulation , ‎reproducing kernel Hilbert ‎space

Rights: Copyright © 2010 Institute of Mathematical Statistics

JOURNAL ARTICLE
40 PAGES


SHARE
Vol.38 • No. 1 • February 2010
Back to Top