Cellular Tree Classifiers

Abstract : The cellular tree classifier model addresses a fundamental problem in the design of classifiers for a parallel or distributed computing world: Given a data set, is it sufficient to apply a majority rule for classification, or shall one split the data into two or more parts and send each part to a potentially different computer (or cell) for further processing? At first sight, it seems impossible to define with this paradigm a consistent classifier as no cell knows the ''original data size'', $n$. However, we show that this is not so by exhibiting two different consistent classifiers. The consistency is universal but is only shown for distributions with nonatomic marginals.
Type de document :
Pré-publication, Document de travail
2013
Liste complète des métadonnées

Littérature citée [49 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00778520
Contributeur : Gérard Biau <>
Soumis le : lundi 24 juin 2013 - 21:19:37
Dernière modification le : lundi 29 mai 2017 - 14:26:02
Document(s) archivé(s) le : mercredi 25 septembre 2013 - 04:12:11

Fichiers

articlegreedy6.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00778520, version 2
  • ARXIV : 1301.4679

Collections

INRIA | INSMI | UPMC | LSTA | PSL | USPC | PMA

Citation

Gérard Biau, Luc Devroye. Cellular Tree Classifiers. 2013. 〈hal-00778520v2〉

Partager

Métriques

Consultations de
la notice

350

Téléchargements du document

145