BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using transformed domains to sparsify Gaussian Processes - Dr Migu
 el Lázaro-Gredilla (Universidad Carlos III de Madrid)
DTSTART:20100712T103000Z
DTEND:20100712T113000Z
UID:TALK25362@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:One of the main limitations associated to the use of Gaussian 
 Processes (GPs) to model data is their high computational cost\, which is 
 O(n^3) for n training samples. In this talk\, I will discuss several recen
 tly proposed GP models that rely on the use of a _transformed domain_ to a
 chieve sparsity and make computation for large data sets affordable. These
  proposals are comparable in terms of computational cost to previous appro
 aches\, such as the celebrated Sparse Pseudo-Input GP (also known as FITC)
 \, but typically offer superior performance. In particular\, I will presen
 t the Sparse Spectrum GP (SSGP) as a very fast tool to model stationary pr
 ocesses and the Inter-Domain GP (IDGP) as a general framework for inferenc
 e that can be used both to understand previous sparse GP models and to des
 ign new ones. A variational extension of the latter framework that rigorou
 sly addresses the overfilling problem will also be discussed.\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR