eprintid: 1749 rev_number: 4 eprint_status: archive userid: 46 dir: disk0/00/00/17/49 datestamp: 2013-09-17 07:39:34 lastmod: 2013-09-17 07:39:34 status_changed: 2013-09-17 07:39:34 type: article succeeds: 1701 metadata_visibility: show creators_name: Gnecco, Giorgio creators_name: Sanguineti, Marcello creators_id: giorgio.gnecco@imtlucca.it creators_id: title: Approximation Error Bounds via Rademacher's Complexity ispublished: pub subjects: QA75 divisions: CSA full_text_status: public keywords: approximation error, model complexity, curse of dimensionality, Rademacher's complexity, Talagrand's inequality, union bounds, VC dimension. abstract: Approximation properties of some connectionistic models, commonly used to construct approximation schemes for optimization problems with multivariable functions as admissible solutions, are investigated. Such models are made up of linear combinations of computational units with adjustable parameters. The relationship between model complexity (number of computational units) and approximation error is investigated using tools from Statistical Learning Theory, such as Talagrand's inequality, fat-shattering dimension, and Rademacher's complexity. For some families of multivariable functions, estimates of the approximation accuracy of models with certain computational units are derived in dependence of the Rademacher's complexities of the families. The estimates improve previously-available ones, which were expressed in terms of V C dimension and derived by exploiting union-bound techniques. The results are applied to approximation schemes with certain radial-basis-functions as computational units, for which it is shown that the estimates do not exhibit the curse of dimensionality with respect to the number of variables. date: 2008 date_type: published publication: Applied Mathematical Sciences volume: 2 number: 4 publisher: Hikari Ltd pagerange: 153-176 refereed: TRUE issn: 1312-885X official_url: http://www.m-hikari.com/ams/ams-password-2008/ams-password1-4-2008/ citation: Gnecco, Giorgio and Sanguineti, Marcello Approximation Error Bounds via Rademacher's Complexity. Applied Mathematical Sciences, 2 (4). pp. 153-176. ISSN 1312-885X (2008) document_url: http://eprints.imtlucca.it/1749/1/Applied%20Mathematical%20Sciences_Gnecco_Sanguinetti_2008.pdf