BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Metropolis-Coupled MCMC for Nested Sampling - Ratthachat (Jung)
DTSTART:20070307T140000Z
DTEND:20070307T150000Z
UID:TALK6770@talks.cam.ac.uk
CONTACT:David MacKay
DESCRIPTION:In this talk\, I will first introduce _nested sampling_\, whic
 h is a recent probabilistic numerical integration algorithm.\n\nAfter that
 \, I'll focus on the problem of _sampling a point from a truncated domain_
  which is essential to the accuracy of nested sampling. To solve this prob
 lem\, I propose the technique called _Metropolis-coupled_ MCMC (MCMCMC) wh
 ich can unify a random-walk MCMC and the ellipsoid method.\n\nThe key idea
  is to use the ellipsoid method to create an auxiliary distribution. The a
 uxiliary distribution then help the random-walk MCMC to converge faster. \
 nThe MCMCMC framework is general and theoretically correct as the MCMC fra
 mework.
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR