Feature space perspectives for learning the kernel

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. 1 This work was supported by NSF Grant ITR-0312113, EPSRC Grant GR/T18707/01 and by the IST Programme of the European Community, under the PASCAL Network of Excellence IST-2002-506778. 

• Type: Journal
• Year: 2007
• Where: ML
• Authors: Charles A. Micchelli, Massimiliano Pontil
• Keywords: Feature Space Environment, Machine Learning, ML 2007, Prescribed Convex, Space