BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Inference as Learning - George Papamakarios (University of Edinbur
 gh)
DTSTART:20160808T100000Z
DTEND:20160808T110000Z
UID:TALK66984@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:How can we do Bayesian inference if the likelihood is not avai
 lable? This situation arises in simulator-based models\, where the model c
 an be easily simulated but its likelihood is intractable. One can learn to
  perform inference in such models based only on simulation data\, by casti
 ng inference as a learning problem. In this talk\, I will describe a strat
 egy for doing this efficiently using Bayesian conditional density estimati
 on\, and compare it with established likelihood-free inference techniques 
 such as Approximate Bayesian Computation.
LOCATION:CBL Room BE-438
END:VEVENT
END:VCALENDAR