BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Diffusive behaviour of non-reversible MCMC with application to Sim
 ulated Tempering. - Gareth Roberts (University of Warwick)
DTSTART:20241121T140000Z
DTEND:20241121T150000Z
UID:TALK224008@talks.cam.ac.uk
DESCRIPTION:Non-reversible Markov chain Monte Carlo algorithms such as Pie
 cewise Deterministic Markov Processes are becoming increasingly popular in
  Bayesian computation as well as Physics. One of the attractions of these 
 methods is that they provide momentum which facilitates mixing through the
  state space. This talk will discuss some results which describe the exten
 t to which the advantages of non-reversible MCMC persist in high-dimension
 al problems. In some cases the momentum can be homogenised in the high-dim
 ensional limit to give diffusive behaviour. This work is applied to a comp
 arison of reversible and non-reversible simulated (and parallel) tempering
  algorithms. Practical implementational guidance for these algorithms is g
 iven by the theory.\nThis is joint work with Jeff Rosenthal.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR