BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Fast Variational Inference in the Conjugate Exponential Family - J
 ames Hensman\, The Sheffield Institute for Translational Neuroscience
DTSTART:20130325T110000Z
DTEND:20130325T120000Z
UID:TALK44226@talks.cam.ac.uk
CONTACT:David Duvenaud
DESCRIPTION:We present a general method for deriving collapsed variational
  inference algorithms for probabilistic models in the conjugate exponentia
 l family. Our method unifies many existing approaches to collapsed variati
 onal inference. Our collapsed variational inference leads to a new lower b
 ound on the marginal likelihood. We exploit the information geometry of th
 e bound to derive much faster optimization methods based on conjugate grad
 ients for these models. Our approach is very general and is easily applied
  to any model where the mean field update equations have been derived. Emp
 irically we show significant speed-ups for probabilistic inference using o
 ur bound.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR