Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
AGGREGATED ESTIMATORS AND EMPIRICAL COMPLEXITY FOR LEAST SQUARE REGRESSION
 

Summary: AGGREGATED ESTIMATORS AND EMPIRICAL COMPLEXITY
FOR LEAST SQUARE REGRESSION
JEAN-YVES AUDIBERT
jyaudibe@ccr.jussieu.fr
Universit´e Paris VI Pierre et Marie Curie
Laboratoire de Probabilit´es et Mod`eles al´eatoires
175 rue du Chevaleret
75013 Paris
FRANCE
and
Centre de Recherche en ´Economie et Statistique
Laboratoire de Finance et Assurance
15 Bd Gabriel P´eri
92245 Malakoff Cedex
FRANCE
Abstract. Numerous empirical results have shown that combining regression
procedures can be a very efficient method. This work provides PAC bounds
for the L2 generalization error of such methods. The interest of these bounds
are twofold.
First, it gives for any aggregating procedure a bound for the expected risk

  

Source: Audibert, Jean-Yves - Département d'Informatique, École Normale Supérieure

 

Collections: Computer Technologies and Information Sciences