PAC-Bayesian Theorems for Multiview Learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

PAC-Bayesian Theorems for Multiview Learning

Résumé

We tackle the issue of multiview learning which aims to take advantages of multiple represen-tations/views of the data. In this context, many machine learning algorithms exist. However, the majority of the theoretical studies focus on learning with exactly two representations. In this paper, we propose a general PAC-Bayesian theory for multiview learning with more than two views. We focus our study to binary classification models that take the form of a majority vote. We derive PAC-Bayesian generalization bounds allowing to consider different relations between empirical and true risks by taking into account a notion of diversity of the voters and views, and that can be naturally extended to semi-supervised learning.
Fichier principal
Vignette du fichier
main_report.pdf (447.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01336260 , version 1 (22-06-2016)
hal-01336260 , version 2 (17-11-2016)

Identifiants

Citer

Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini. PAC-Bayesian Theorems for Multiview Learning. 2016. ⟨hal-01336260v2⟩
332 Consultations
206 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More