Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound

Résumé

We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties. While our approach holds for arbitrary distributions, we instantiate it with Dirichlet distributions: this allows for a closed-form and differentiable expression for the expected risk, which then turns the generalization bound into a tractable training objective. The resulting stochastic majority vote learning algorithm achieves state-of-the-art accuracy and benefits from (non-vacuous) tight generalization bounds, in a series of numerical experiments when compared to competing algorithms which also minimize PAC-Bayes objectives-both with uninformed (data-independent) and informed (data-dependent) priors.
Fichier principal
Vignette du fichier
2106.12535.pdf (2.16 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03278470 , version 1 (05-07-2021)

Identifiants

Citer

Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, et al.. Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound. NeurIPS, 2021, Online, France. ⟨hal-03278470⟩
55 Consultations
101 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More