BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Scalable statistical inference with INLA - Havard Rue (Norwegian U
 niversity of Science and Technology)
DTSTART:20170703T151500Z
DTEND:20170703T160000Z
UID:TALK73132@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:INLA do approximate Bayesian inference for the class of latent
  Gaussian models. It has shown sucessful allowing statisticians and applie
 d scientists to fast and reliable Bayesian inference for a huge class of a
 dditve models\, within reasonable time. Especially\, the use of spatial Ga
 ussian models using the SPDE approach has been particularly popular. Altho
 ugh most models runs within reasonable time\, we are facing with the curre
 nt implementation\, limitations for really huge models like large space ti
 me models. In this talk I will discuss the current situation and possible 
 strategies to improve the situation.<br>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR