BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Monte Carlo is Bayesian - John Skilling\, ex-DAMTP
DTSTART:20051109T150000Z
DTEND:20051109T160000Z
UID:TALK4498@talks.cam.ac.uk
CONTACT:Phil Cowans
DESCRIPTION:Cox was right\, Kolmogorov was wrong.  The attempt to found pr
 obability calculus upon set theory seems to be misguided\, because it is n
 ecessary to exclude sets of measure zero in order to avoid paradox.  It is
  better to start with unit measure of probabilistic belief\, to be distrib
 uted among relevant hypotheses regardless of any measure they may possess.
   This improved viewpoint shows that\, contrary to the folklore of the sub
 ject\, Monte Carlo integration is properly probabilistic (as an algorithm 
 for Bayesian computation should be).  Nested sampling is an extension to p
 roblems of larger scale: it is an algorithm of wider scope that can deal w
 ith a variety of multi-modal problems better than conventional annealing.
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR