BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Topics in Expectation Propagation - Yingzhen Li (University of Cam
 bridge)\, Rich Turner
DTSTART:20160428T133000Z
DTEND:20160428T150000Z
UID:TALK65403@talks.cam.ac.uk
CONTACT:Yingzhen Li
DESCRIPTION:Approximate inference is key to modern probabilistic modeling\
 , since exact inference/learning is intractable for many models used in re
 al-world applications. In this talk we present expectation propagation (EP
 ) as a general framework for fast and accurate approximate inference. We g
 ive a wide range of applications of EP for both posterior approximation an
 d marginal inference. We also show the flexibility of algorithm design wit
 hin the EP framework by introducing factor graphs\, approximate distributi
 on families and projection operators. Finally we provide a justification o
 f EP from a variational viewpoint and connect it to the Bethe free energy 
 approximation.\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR