Nonparametric estimation of composite functions

Abstract : We study the problem of nonparametric estimation of a multivariate function g: ℝd→ℝ that can be represented as a composition of two unknown smooth functions f: ℝ→ℝ and G: ℝd→ℝ. We suppose that f and G belong to known smoothness classes of functions, with smoothness γ and β, respectively. We obtain the full description of minimax rates of estimation of g in terms of γ and β, and propose rate-optimal estimators for the sup-norm loss. For the construction of such estimators, we first prove an approximation result for composite functions that may have an independent interest, and then a result on adaptation to the local structure. Interestingly, the construction of rate-optimal estimators for composite functions (with given, fixed smoothness) needs adaptation, but not in the traditional sense: it is now adaptation to the local structure. We prove that composition models generate only two types of local structures: the local single-index model and the local model with roughness isolated to a single dimension (i.e., a model containing elements of both additive and single-index structure). We also find the zones of (γ, β) where no local structure is generated, as well as the zones where the composition modeling leads to faster rates, as compared to the classical nonparametric rates that depend only to the overall smoothness of g.
Type de document :
Article dans une revue
Annals of Statistics, Institute of Mathematical Statistics, 2009, 37 (3), pp.1360-1404. <10.1214/08-AOS611>


https://hal.archives-ouvertes.fr/hal-00148063
Contributeur : Guillaume Lecué <>
Soumis le : lundi 21 mai 2007 - 20:00:37
Dernière modification le : vendredi 25 novembre 2016 - 01:03:15
Document(s) archivé(s) le : jeudi 8 avril 2010 - 17:18:50

Fichier

ilt_fin_rep.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Anatoli Juditsky, Oleg Lepski, Alexandre Tsybakov. Nonparametric estimation of composite functions. Annals of Statistics, Institute of Mathematical Statistics, 2009, 37 (3), pp.1360-1404. <10.1214/08-AOS611>. <hal-00148063>

Exporter

Partager

Métriques

Consultations de
la notice

389

Téléchargements du document

184