Random forests and kernel methods

Abstract : Random forests are ensemble methods which grow trees as base learners and combine their predictions by averaging. Random forests are known for their good practical performance, particularly in high dimensional set-tings. On the theoretical side, several studies highlight the potentially fruitful connection between random forests and kernel methods. In this paper, we work out in full details this connection. In particular, we show that by slightly modifying their definition, random forests can be rewrit-ten as kernel methods (called KeRF for Kernel based on Random Forests) which are more interpretable and easier to analyze. Explicit expressions of KeRF estimates for some specific random forest models are given, together with upper bounds on their rate of consistency. We also show empirically that KeRF estimates compare favourably to random forest estimates.
Type de document :
Pré-publication, Document de travail
2015
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01116158
Contributeur : Erwan Scornet <>
Soumis le : mercredi 16 septembre 2015 - 17:18:55
Dernière modification le : jeudi 21 mars 2019 - 14:16:44
Document(s) archivé(s) le : mardi 29 décembre 2015 - 07:37:01

Fichiers

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

Identifiants

  • HAL Id : hal-01116158, version 2
  • ARXIV : 1502.03836

Citation

Erwan Scornet. Random forests and kernel methods. 2015. 〈hal-01116158v2〉

Partager

Métriques

Consultations de la notice

317

Téléchargements de fichiers

586