BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bayesians turn to experts for advice! - Dr Steven de Rooij\, Stati
 stical Laboratory\, University of Cambridge
DTSTART:20081112T141500Z
DTEND:20081112T151500Z
UID:TALK14588@talks.cam.ac.uk
CONTACT:Rachel Fogg
DESCRIPTION:In Bayesian model selection and model averaging\, inference is
  normally based on a posterior distribution on the models\, usually interp
 reted as a measure of how likely we consider each of the models to be "tru
 e"\, or at least in some sense close to true\, given the observations.\n  
    Rather than with truth\, I will be concerned with the more practical go
 al of finding a "useful" model\, in the sense that it predicts future outc
 omes of the underlying process well. As it turns out\, the most useful mod
 el may well vary depending on the number of available observations! For in
 stance\, given ten samples from some continuous density\, a seven-bin hist
 ogram model is more useful than a 1\,000-bin model\, even though the latte
 r is arguably closer to being "true".\n     As it turns out\, methods for 
 tracking transient performance of prediction strategies have already been 
 developed in the learning theory literature under the heading "prediction 
 with expert advice". I will illustrate how these methods can improve model
  selection performace using results from computer simulations on density e
 stimation problems.\n
LOCATION:LR12\, Engineering\, Department of
END:VEVENT
END:VCALENDAR