A condensed primer on PAC-Bayesian learning

发布时间：2020-12-14 作者：浏览次数：

Speaker:	Benjamin Guedj	DateTime:	2020年12月17日（周四）下午16:30-17:30
Brief Introduction to Speaker: Benjamin Guedj is a principal research fellow in Machine learning at University College London (centre for Artificial intelligence, department of Computer Science) and a tenured research scientist at Inria. He is also a visiting researcher at The Alan Turing Institute, fellow of the Royal Statistical Society and member of the ELLIS Society.		Place:	腾讯会议（会议号请联系左国新老师索取）
Abstract:Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalisation properties and flexibility. This talk aims at providing a self-contained survey on the resulting PAC-Bayes framework and some of its main theoretical and algorithmic developments.