PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Feature space perspectives for learning the kernel
Charles Micchelli and Massimiliano Pontil
Machine Learning 2007.

Abstract

In this paper, we continue our study of learning an optimal kernel in a prescribed convex set of kernels, [18]. We present a reformulation of this problem within a feature space environment. This leads us to study regularization in the dual space of all continuous functions on a compact domain with values in a Hilbert space with a mix norm. We also relate this problem in a special case to Lp regularization.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:3783
Deposited By:Massimiliano Pontil
Deposited On:22 February 2008