PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach

Anil Goyal 1, 2 Emilie Morvant 2 Pascal Germain 3 Massih-Reza Amini 1
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
Abstract : We study a two-level multiview learning with more than two views under the PAC-Bayesian framework. This approach, sometimes referred as late fusion, consists in learning sequentially multiple view-specific classifiers at the first level, and then combining these view-specific classifiers at the second level. Our main theoretical result is a generalization bound on the risk of the majority vote which exhibits a term of diversity in the predictions of the view-specific classifiers. From this result it comes out that controlling the trade-off between diversity and accuracy is a key element for multiview learning, which complements other results in multiview learning. Finally, we experiment our principle on multiview datasets extracted from the Reuters RCV1/RCV2 collection.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01336260
Contributeur : Emilie Morvant <>
Soumis le : jeudi 13 juillet 2017 - 15:14:21
Dernière modification le : dimanche 15 octobre 2017 - 22:44:06

Fichiers

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

Identifiants

  • HAL Id : hal-01336260, version 3
  • ARXIV : 1606.07240

Collections

Citation

Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini. PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach. 2017. 〈hal-01336260v3〉

Partager

Métriques

Consultations de
la notice

164

Téléchargements du document

36