Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming (Contributo in atti di convegno)

Type
Label
  • Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming (Contributo in atti di convegno) (literal)
Anno
  • 2012-01-01T00:00:00+01:00 (literal)
Alternative label
  • M. Gaggero; G. Gnecco; T. Parisini; M. Sanguineti; R. Zoppoli (2012)
    Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming
    in 51st IEEE Conference on Decision and Control, Maui (USA), 10-13 December 2012
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • M. Gaggero; G. Gnecco; T. Parisini; M. Sanguineti; R. Zoppoli (literal)
Pagina inizio
  • 1902 (literal)
Pagina fine
  • 1908 (literal)
Rivista
Note
  • ISI Web of Science (WOS) (literal)
  • Scopu (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • 1. Institute of Intelligent Systems for Au- tomation, National Research Council of Italy, Genova, Italy. 2. DIBRIS Department, University of Genoa, Genova, Italy. 3. Dept. of Electrical and Electronic Engineer- ing at the Imperial College London, UK and also with the Dept. of Engineering and Architecture at the University of Trieste, Italy. 4. DIBRIS Department, University of Genoa, Genova, Italy. 5. DIBRIS Department, University of Genoa, Genova, Italy. (literal)
Titolo
  • Approximation Structures with Moderate Complexity in Functional Optimization and Dynamic Programming (literal)
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 contain- ing 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 potentiali- ties of recent developments in nonlinear approximation in the framework of the solution of sequential decision problems with continuous state spaces. (literal)
Editore
Prodotto di
Autore CNR

Incoming links:


Prodotto
Autore CNR di
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi
Editore di
data.CNR.it