BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Information-Greedy Global Optimisation - Philipp Hennig\, Max Plan
 ck Institute for Intelligent Systems
DTSTART:20110913T130000Z
DTEND:20110913T140000Z
UID:TALK32854@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Optimisation is about inferring the location of the optimum of
  a function. An information-optimal optimiser should thus aim to collapse 
 its belief about the location of the optimum towards a point-distribution\
 , as fast as possible. But the state of the art rarely addresses this infe
 rence problem. Instead\, it usually relies on some heuristic predicting fu
 nction optima\, then evaluates at the maximum of the heuristic. The reason
  there are no truly probabilistic optimisers yet is that they are intracta
 ble in several ways. In this talk\, I will present tractable approximation
 s for each of these issues\, and arrive at a flexible global optimiser for
  functions under Gaussian process priors\, which empirically outperforms t
 he state of the art.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR