relation: http://eprints.imtlucca.it/1707/
title: Estimates of the Approximation Error Using Rademacher Complexity: Learning Vector-Valued Functions
creator: Gnecco, Giorgio
creator: Sanguineti, Marcello
subject: QA75 Electronic computers. Computer science
description: For certain families of multivariable vector-valued functions to be approximated, the accuracy of approximation schemes made up of linear combinations of computational units containing adjustable parameters is investigated. Upper bounds on the approximation error are derived that depend on the Rademacher complexities of the families. The estimates exploit possible relationships among the components of the multivariable vector-valued functions. All such components are approximated simultaneously in such a way to use, for a desired approximation accuracy, less computational units than those required by componentwise approximation. An application to -stage optimization problems is discussed. 
publisher: Springer
date: 2008
type: Article
type: PeerReviewed
format: application/pdf
language: en
rights: cc_by
identifier: http://eprints.imtlucca.it/1707/1/J.%20Inequalities%20and%20Applications_Gnecco_2008.pdf
identifier:   Gnecco, Giorgio and Sanguineti, Marcello  Estimates of the Approximation Error Using Rademacher Complexity: Learning Vector-Valued Functions.  Journal of Inequalities and Applications, 2008.  pp. 1-16.  ISSN 1025-5834      (2008)  
relation: http://www.journalofinequalitiesandapplications.com/content/2008/1/640758
relation: 10.1155/2008/640758