BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An Introduction to PAC-Bayes - Andrew Foong\, David Burt and Javie
 r Antoran (University of Cambridge)
DTSTART:20210421T100000Z
DTEND:20210421T113000Z
UID:TALK157393@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:PAC-Bayes is a frequentist framework for obtaining generalisat
 ion error bounds. It has been used to derive learning algorithms\, provide
  explanations for generalisation in deep learning\, and form connections b
 etween Bayesian and frequentist inference. This reading group will cover a
  broad introduction to PAC bounds\, the proof ideas in PAC-Bayes\, and a d
 iscussion of some recent applications.\n \nSuggested reading:\n# Computing
  Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks wi
 th Many More Parameters than Training Data: https://arxiv.org/abs/1703.110
 08\n# PAC-Bayesian Theory Meets Bayesian Inference: https://arxiv.org/abs/
 1605.08636\n# Learning under Model Misspecification: Applications to Varia
 tional and Ensemble Methods: https://arxiv.org/abs/1912.08335
LOCATION:https://eng-cam.zoom.us/j/82019956685?pwd=WUNSVVcrdC9IZGxQOHFhSTh
 jUjd2dz09
END:VEVENT
END:VCALENDAR