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. 19021908. ISBN 9781467320658 (2012)
This is the latest version of this item.
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 finitehorizon 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.
Item Type:  Book Section 

Identification Number:  10.1109/CDC.2012.6426656 
Additional Information:  51st IEEE International Conference on Decision and Control (IEEE CDC 2012) held in Maui, Hawaii, December 10th12th, 2012 
Uncontrolled Keywords:  Complexity theory, Function approximation, Optimal control, Optimization, Stochastic processes, Vectors 
Subjects:  Q Science > QA Mathematics > QA75 Electronic computers. Computer science 
Research Area:  Computer Science and Applications 
Depositing User:  Giorgio Gnecco 
Date Deposited:  17 Sep 2013 07:43 
Last Modified:  17 Sep 2013 07:43 
URI:  http://eprints.imtlucca.it/id/eprint/1750 
Available Versions of this Item

Approximation structures with moderate complexity in functional optimization and dynamic programming. (deposited 11 Sep 2013 14:40)
 Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming. (deposited 17 Sep 2013 07:43) [Currently Displayed]
Actions (login required)
Edit Item 