eprintid: 1750
rev_number: 4
eprint_status: archive
userid: 46
dir: disk0/00/00/17/50
datestamp: 2013-09-17 07:43:42
lastmod: 2013-09-17 07:43:42
status_changed: 2013-09-17 07:43:42
type: book_section
succeeds: 1690
metadata_visibility: show
creators_name: Gaggero, Mauro
creators_name: Gnecco, Giorgio
creators_name: Parisini, Thomas
creators_name: Sanguineti, Marcello
creators_name: Zoppoli, Riccardo
creators_id: 
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
title: Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: Complexity theory, Function approximation, Optimal control, Optimization, Stochastic processes, Vectors
note: 51st IEEE International Conference on Decision and Control (IEEE CDC 2012) held in Maui, Hawaii, December 10th-12th, 2012
abstract: Connections between function approximation and classes of functional optimization problems, whose admissible solutions may depend on a large number of variables, are investigated. The insights obtained in this context are exploited to analyze families of nonlinear approximation schemes containing tunable parameters and enjoying the following property: when they are used to approximate the (unknown) solutions to optimization problems, the number of parameters required to guarantee a desired accuracy grows at most polynomially with respect to the number of variables in admissible solutions. Both sigmoidal neural networks and networks with kernel units are considered as approximation structures to which the analysis applies. Finally, it is shown how the approach can be applied for the solution of finite-horizon optimal control problems via approximate dynamic programming enhancing the potentialities of recent developments in nonlinear approximation in the framework of the solution of sequential decision problems with continuous state spaces.
date: 2012
date_type: published
publisher: IEEE
pagerange: 1902-1908
event_title: Decision and Control (CDC), 2012 IEEE 51st Annual Conference on
id_number: 10.1109/CDC.2012.6426656
refereed: TRUE
isbn: 978-1-4673-2065-8 
book_title: Proceedings of the 51st IEEE International Conference on Decision and Control (IEEE CDC 2012)
official_url: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6426656&isnumber=6425800
citation:   Gaggero, Mauro and Gnecco, Giorgio and Parisini, Thomas and Sanguineti, Marcello and Zoppoli, Riccardo  Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming.   In:  Proceedings of the 51st IEEE International Conference on Decision and Control (IEEE CDC 2012).   IEEE, pp. 1902-1908.  ISBN 978-1-4673-2065-8       (2012)