BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probabilistic Line Searches for Stochastic Optimisation. - Maren M
 ahsereci\, Max Planck Institute for Intelligent Systems (Tübingen)
DTSTART:20150921T100000Z
DTEND:20150921T110000Z
UID:TALK60783@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:In deterministic optimisation\, line searches are a standard t
 ool ensuring stability and efficiency. Where only stochastic gradients are
  available\, no direct equivalent has so far been formulated\, because unc
 ertain gradients do not allow for a strict sequence of decisions collapsin
 g the search space. We construct a probabilistic line search by combining 
 the structure of existing deterministic methods with notions from Bayesian
  optimization. Our method retains a Gaussian process surrogate of the univ
 ariate optimization objective\, and uses a probabilistic belief over the W
 olfe conditions to monitor the descent. The algorithm has very low computa
 tional cost\, and no user-controlled parameters. Experiments show that it 
 effectively removes the need to define a learning rate for stochastic grad
 ient descent.\nPaper available: http://arxiv.org/abs/1502.02846 
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR