Classification via local multi-resolution projections (extended version)

Abstract : We focus on the supervised binary classification problem, which consists in guessing the label $Y$ associated to a co-variate $X \in \R^d$, given a set of $n$ independent and identically distributed co-variates and associated labels $(X_i,Y_i)$. We assume that the law of the random vector $(X,Y)$ is unknown and the marginal law of $X$ admits a density supported on a set $\A$. In the particular case of plug-in classifiers, solving the classification problem boils down to the estimation of the regression function $\eta(X) = \Exp[Y|X]$. Assuming first $\A$ to be known, we show how it is possible to construct an estimator of $\eta$ by localized projections onto a multi-resolution analysis (MRA). In a second step, we show how this estimation procedure generalizes to the case where $\A$ is unknown. Interestingly, this novel estimation procedure presents similar theoretical performances as the celebrated local-polynomial estimator (LPE). In addition, it benefits from the lattice structure of the underlying MRA and thus outperforms the LPE from a computational standpoint, which turns out to be a crucial feature in many practical applications. Finally, we prove that the associated plug-in classifier can reach super-fast rates under a margin assumption.
Liste complète des métadonnées
Contributeur : Jean-Baptiste Monnier <>
Soumis le : mardi 13 décembre 2011 - 11:20:45
Dernière modification le : mardi 11 octobre 2016 - 14:10:52
Document(s) archivé(s) le : mercredi 14 mars 2012 - 02:21:43


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00637010, version 2



Jean-Baptiste Monnier. Classification via local multi-resolution projections (extended version). 2011. <hal-00637010v2>



Consultations de
la notice


Téléchargements du document