Probabilistic Approximately Correct frameworkThe generalization error of an hypothesis is at most something we can control and even compute for any Probabilistic Approximately Correct NotionVC dimensionPAC Bayes theoremPAC Bounds A Primer on PAC-Bayesian LearningGeneralised Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalisation properties and flexibility. The present paper aims at providing a...https://arxiv.org/abs/1901.05353arxiv.orghttps://arxiv.org/pdf/2309.04381