BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Piecewise deterministic Markov processes and effic
iency gains through exact subsampling for MCMC - J
oris Bierkens (Delft University of Technology)
DTSTART;TZID=Europe/London:20170718T102000
DTEND;TZID=Europe/London:20170718T110000
UID:TALK73961AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/73961
DESCRIPTION:Markov chain Monte Carlo methods provide an essent
ial tool in statistics for sampling from complex p
robability distributions. While the standard appro
ach to MCMC involves constructing discrete-time re
versible Markov chains whose transition kernel is
obtained via the Metropolis- Hastings algorithm\,
there has been recent interest in alternative sche
mes based on piecewise deterministic Markov proces
ses (PDMPs). One such approach is based on the Zig
-Zag process\, introduced in Bierkens and Roberts
(2016)\, which proved to provide a highly scalable
sampling scheme for sampling in the big data regi
me (Bierkens\, Fearnhead and Roberts (2016)). In t
his talk we will present a broad overview of these
methods along with some theoretical results.

LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR