A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization

Fixed-basis and variable-basis approximation schemes are compared for the problems of function approximation and functional optimization (also known as infinite programming). Classes of problems are investigated for which variable-basis schemes with sigmoidal computational units perform better than...

Full description

Saved in:
Bibliographic Details
Main Author: Giorgio Gnecco
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:Journal of Applied Mathematics
Online Access:http://dx.doi.org/10.1155/2012/806945
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173938894635008
author Giorgio Gnecco
author_facet Giorgio Gnecco
author_sort Giorgio Gnecco
collection DOAJ
description Fixed-basis and variable-basis approximation schemes are compared for the problems of function approximation and functional optimization (also known as infinite programming). Classes of problems are investigated for which variable-basis schemes with sigmoidal computational units perform better than fixed-basis ones, in terms of the minimum number of computational units needed to achieve a desired error in function approximation or approximate optimization. Previously known bounds on the accuracy are extended, with better rates, to families of d-variable functions whose actual dependence is on a subset of d′≪d variables, where the indices of these d′ variables are not known a priori.
format Article
id doaj-art-c87fe3107a1b4eb3a8551d79ebd6b249
institution OA Journals
issn 1110-757X
1687-0042
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series Journal of Applied Mathematics
spelling doaj-art-c87fe3107a1b4eb3a8551d79ebd6b2492025-08-20T02:19:45ZengWileyJournal of Applied Mathematics1110-757X1687-00422012-01-01201210.1155/2012/806945806945A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional OptimizationGiorgio Gnecco0Department of Communication, Computer and System Sciences (DIST), University of Genova, Via Opera Pia 13, 16145 Genova, ItalyFixed-basis and variable-basis approximation schemes are compared for the problems of function approximation and functional optimization (also known as infinite programming). Classes of problems are investigated for which variable-basis schemes with sigmoidal computational units perform better than fixed-basis ones, in terms of the minimum number of computational units needed to achieve a desired error in function approximation or approximate optimization. Previously known bounds on the accuracy are extended, with better rates, to families of d-variable functions whose actual dependence is on a subset of d′≪d variables, where the indices of these d′ variables are not known a priori.http://dx.doi.org/10.1155/2012/806945
spellingShingle Giorgio Gnecco
A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
Journal of Applied Mathematics
title A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
title_full A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
title_fullStr A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
title_full_unstemmed A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
title_short A Comparison between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization
title_sort comparison between fixed basis and variable basis schemes for function approximation and functional optimization
url http://dx.doi.org/10.1155/2012/806945
work_keys_str_mv AT giorgiognecco acomparisonbetweenfixedbasisandvariablebasisschemesforfunctionapproximationandfunctionaloptimization
AT giorgiognecco comparisonbetweenfixedbasisandvariablebasisschemesforfunctionapproximationandfunctionaloptimization