We investigate the problem of model selection for learning algorithms depending on a continuous parameter. We propose a model selection procedure based on a worst-case analysis and on a data-independent choice of the parameter. For the regularized least-squares algorithm we bound the generalization error of the solution by a quantity depending on a few known constants and we show that the corresponding model selection procedure reduces to solving a bias-variance problem. Under suitable smoothness conditions on the regression function, we estimate the optimal parameter as a function of the number of data and we prove that this choice ensures consistency of the algorithm.

Model selection for regularized least-squares algorithm in learning theory / DE VITO, Ernesto; Caponnetto, A; Rosasco, L.. - In: FOUNDATIONS OF COMPUTATIONAL MATHEMATICS. - ISSN 1615-3375. - STAMPA. - 5:(2005), pp. 59-85.

Model selection for regularized least-squares algorithm in learning theory

DE VITO, Ernesto;
2005

Abstract

We investigate the problem of model selection for learning algorithms depending on a continuous parameter. We propose a model selection procedure based on a worst-case analysis and on a data-independent choice of the parameter. For the regularized least-squares algorithm we bound the generalization error of the solution by a quantity depending on a few known constants and we show that the corresponding model selection procedure reduces to solving a bias-variance problem. Under suitable smoothness conditions on the regression function, we estimate the optimal parameter as a function of the number of data and we prove that this choice ensures consistency of the algorithm.
5
59
85
Model selection for regularized least-squares algorithm in learning theory / DE VITO, Ernesto; Caponnetto, A; Rosasco, L.. - In: FOUNDATIONS OF COMPUTATIONAL MATHEMATICS. - ISSN 1615-3375. - STAMPA. - 5:(2005), pp. 59-85.
DE VITO, Ernesto; Caponnetto, A; Rosasco, L.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11380/3745
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 119
  • ???jsp.display-item.citation.isi??? 105
social impact