A Primer on PAC-Bayesian Learning
Résumé
Generalized Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalization properties and flexibility. The present paper aims at providing a self-contained survey on the resulting PAC-Bayes framework and some of its main theoretical and algorithmic developments.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...