On the asymptotics of random forests

Abstract : The last decade has witnessed a growing interest in random forest models which are recognized to exhibit good practical performance, especially in high-dimensional settings. On the theoretical side, however, their predictive power remains largely unexplained, thereby creating a gap between theory and practice. The aim of this paper is twofold. Firstly, we provide theoretical guarantees to link finite forests used in practice (with a finite number M of trees) to their asymptotic counterparts. Using empirical process theory, we prove a uniform central limit theorem for a large class of random forest estimates, which holds in particular for Breiman's original forests. Secondly, we show that infinite forest consistency implies finite forest consistency and thus, we state the consistency of several infinite forests. In particular, we prove that q quantile forests---close in spirit to Breiman's forests but easier to study---are able to combine inconsistent trees to obtain a final consistent prediction, thus highlighting the benefits of random forests compared to single trees.
Type de document :
Pré-publication, Document de travail
2014
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01061506
Contributeur : Erwan Scornet <>
Soumis le : dimanche 7 septembre 2014 - 03:30:56
Dernière modification le : vendredi 23 novembre 2018 - 09:52:31
Document(s) archivé(s) le : lundi 8 décembre 2014 - 10:10:50

Fichiers

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

Identifiants

  • HAL Id : hal-01061506, version 1
  • ARXIV : 1409.2090

Collections

Citation

Erwan Scornet. On the asymptotics of random forests. 2014. 〈hal-01061506〉

Partager

Métriques

Consultations de la notice

234

Téléchargements de fichiers

239