Seminar: A primer on PAC-Bayesian learning

SpeakerBenjamin Guedj
AffiliationINRIA - UCL
DateFriday, 17 May 2019
Time13:00 - 14:00
LocationRoberts G08
Event seriesDeepMind CSML Seminar Series
Description

Generalized Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalization properties and flexibility. I will present a self-contained introduction on generalized Bayesian learning and the PAC-Bayes theory, and discuss their theoretical and algorithmic ins and outs (as presented in Guedj, 2019). I will then focus on the recent paper Alquier and Guedj (2018), and present how PAC-Bayesian ideas may be used to efficiently learn with dependent and/or heavy-tailed (aka hostile) data.

References:
* Alquier and Guedj (2018), Simpler PAC-Bayesian Bounds for Hostile Data, Machine Learning. https://link.springer.com/article/10.1007%2Fs10994-017-5690-0
* Guedj (2019), A primer on PAC-Bayesian learning, arXiv preprint. https://arxiv.org/abs/1901.05353

iCalendar csml_id_379.ics