Sparse classification boundaries - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2009

Sparse classification boundaries

Résumé

Given a training sample of size $m$ from a $d$-dimensional population, we wish to allocate a new observation $Z\in \R^d$ to this population or to the noise. We suppose that the difference between the distribution of the population and that of the noise is only in a shift, which is a sparse vector. For the Gaussian noise, fixed sample size $m$, and the dimension $d$ that tends to infinity, we obtain the sharp classification boundary and we propose classifiers attaining this boundary. We also give extensions of this result to the case where the sample size $m$ depends on $d$ and satisfies the condition $(\log m)/\log d \to \gamma$, $0\le \gamma<1$, and to the case of non-Gaussian noise satisfying the Cramér condition.
Fichier principal
Vignette du fichier
IngsterPouetTsybakov2009.pdf (328.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00371237 , version 1 (27-03-2009)

Identifiants

Citer

Yuri I. Ingster, Christophe Pouet, Alexandre B. Tsybakov. Sparse classification boundaries. 2009. ⟨hal-00371237⟩
271 Consultations
183 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More