Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2006

Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation

Résumé

We construct a classifier which attains the rate of convergence $\log n/n$ under sparsity and margin assumptions. An approach close to the one met in approximation theory for the estimation of function is used to obtain this result. The idea is to develop the Bayes rule in a fundamental system of $L^2([0,1]^d)$ made of indicator of dyadic sets and to assume that coefficients, equal to $-1,0 \mbox{ or } 1$, belong to a kind of $L^1-$ball. This assumption can be seen as a sparsity assumption, in the sense that the proportion of coefficients non equal to zero decreases as "frequency" grows. Finally, rates of convergence are obtained by using an usual trade-off between a bias term and a variance term.
Fichier principal
Vignette du fichier
ApproximationTheoryClassification.pdf (284.32 Ko) Télécharger le fichier
ApproximationTheoryClassification.ps (456.91 Ko) Télécharger le fichier
Format : Autre
Loading...

Dates et versions

hal-00086510 , version 1 (18-07-2006)

Identifiants

Citer

Guillaume Lecué. Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation. 2006. ⟨hal-00086510⟩
96 Consultations
90 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More