An invariance property of predictors in kernel- induced hypothesis spaces (Articolo in rivista)

Type

• Prodotto della ricerca (Classe)
• Articolo in rivista (Classe)

Label

• An invariance property of predictors in kernel- induced hypothesis spaces (Articolo in rivista) (literal)

Anno

• 2006-01-01T00:00:00+01:00 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi

• 10.1162/089976606775774660 (literal)

Alternative label

• N. Ancona and S. Stramaglia (2006)
  An invariance property of predictors in kernel- induced hypothesis spaces
  in Neural computation
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• N. Ancona and S. Stramaglia (literal)

Pagina inizio

• 749 (literal)

Pagina fine

• 759 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url

• http://www.mitpressjournals.org/doi/abs/10.1162/neco.2006.18.4.749 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume

• 18 (literal)

Rivista

• Neural computation (Rivista)

Note

• ISI Web of Science (WOS) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• Institute of Intelligent Systems for Automation - C.N.R. \ Via Amendola 122/D-I - 70126 Bari - Italy Dipartimento Interateneo di Fisica, University of Bari, Italy (literal)

Titolo

• An invariance property of predictors in kernel- induced hypothesis spaces (literal)

Abstract

• We consider kernel-based learning methods for regression and analyze what happens to the risk minimizer when new variables, statistically independent of input and target variables, are added to the set of input variables. This problem arises, for example, in the detection of causality relations between two time series. We find that the risk minimizer remains unchanged if we constrain the risk minimization to hypothesis spaces induced by suitable kernel functions. We show that not all kernel-induced hypothesis spaces enjoy this property. We present sufficient conditions ensuring that the risk minimizer does not change and show that they hold for inhomogeneous polynomial and gaussian radial basis function kernels. We also provide examples of kernel-induced hypothesis spaces whose risk minimizer changes if independent variables are added as input. (literal)

Prodotto di

• Sistemi Sensoriali per il Controllo di Qualità e Diagnostica (SP.P03.002.001) (Modulo)
• Institute of intelligent systems for automation (ISSIA) (Istituto)

Autore CNR

• NICOLA ANCONA (Unità di personale interno)

Incoming links:

Prodotto

• Institute of intelligent systems for automation (ISSIA) (Istituto)
• Sistemi Sensoriali per il Controllo di Qualità e Diagnostica (SP.P03.002.001) (Modulo)

Autore CNR di

• NICOLA ANCONA (Unità di personale interno)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi

• Neural computation (Rivista)