A Primer on PAC-Bayesian Learning

Benjamin Guedj (1, 2, 3, 4, 5)

1 MODAL - MOdel for Data Analysis and Learning
2 UCL - University College of London [London]
3 UCL-CS - Department of Computer science [University College of London]
4 Inria-CWI - Inria-CWI
5 Inria-London - The Inria London Programme

Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalisation 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.

Domaines: Machine Learning [stat.ML]; Apprentissage [cs.LG]; Théorie [stat.TH]

Benjamin Guedj. A Primer on PAC-Bayesian Learning. 2019. ⟨hal-01983732v3⟩