PAC-Bayes Bounds for the Risk of the Majority Vote - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

PAC-Bayes Bounds for the Risk of the Majority Vote

Alexandre Lacasse
  • Fonction : Auteur
François Laviolette
  • Fonction : Auteur
Mario Marchand
  • Fonction : Auteur
Pascal Germain
Nicolas Usunier
  • Fonction : Auteur
  • PersonId : 933831

Résumé

We propose new PAC-Bayes bounds for the risk of the weighted majority vote that depend on the mean and variance of the error of its associated Gibbs classifier. We show that these bounds can be smaller than the risk of the Gibbs classifier and can be arbitrarily close to zero even if the risk of the Gibbs classifier is close to 1/2. Moreover, we show that these bounds can be uniformly estimated on the training data for all possible posteriors Q. Moreover, they can be improved by using a large sample of unlabelled data.
Fichier non déposé

Dates et versions

hal-01352012 , version 1 (05-08-2016)

Identifiants

  • HAL Id : hal-01352012 , version 1

Citer

Alexandre Lacasse, François Laviolette, Mario Marchand, Pascal Germain, Nicolas Usunier. PAC-Bayes Bounds for the Risk of the Majority Vote. Advances in Neural Information Processing Systems (NIPS'06), Dec 2006, Vancouver, Canada. pp.769-776. ⟨hal-01352012⟩
47 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More