This Article Full Text (PDF) References Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Kurková, V. Articles by Sanguineti, M. Search for Related Content

Approximate Minimization of the Regularized Expected Error over Kernel Models

Vra Krková, Marcello Sanguineti

Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic
Department of Communications, Computer, and System Sciences (DIST), University of Genoa, 16145 Genova, Italy
vera{at}cs.cas.cz, http://www.cs.cas.cz/vera/
marcello{at}dist.unige.it, http://www.dist.unige.it/msanguineti/

Learning from data under constraints on model complexity is studied in terms of rates of approximate minimization of the regularized expected error functional. For kernel models with an increasing number n of kernel functions, upper bounds on such rates are derived. The bounds are of the form a/n+b/n, where a and b depend on the regularization parameter and on properties of the kernel, and of the probability measure defining the expected error. As a special case, estimates of rates of approximate minimization of the regularized empirical error are derived.

Key Words: suboptimal solutions; expected error; convex functionals; kernel methods; model complexity; rates of convergence
History: Received: January 10, 2007; revision received: February 15, 2008;