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:Scalable algorithms for Markov process parameter i
nference - Darren Wilkinson (Newcastle University)
DTSTART;TZID=Europe/London:20160408T094500
DTEND;TZID=Europe/London:20160408T103000
UID:TALK65377AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/65377
DESCRIPTION:Inferring the parameters of continuous-time Markov
process models using partial discrete-time obser
vations is an important practical problem in many
fields of scientific research. Such models are ve
ry often "intractable"\, in the sense that the tr
ansition kernel of the process cannot be described
in closed form\, and is difficult to approximate
well. Nevertheless\, it is often possible to for
ward simulate realisations of trajectories of the
process using stochastic simulation. There have b
een a number of recent developments in the literat
ure relevant to the parameter estimation problem\
, involving a mixture of approximate\, sequential
and Markov chain Monte Carlo methods. This talk w
ill compare some of the different "likelihood fre
e" algorithms that have been proposed\, including
sequential ABC and particle marginal Metropolis H
astings\, paying particular attention to how well
they scale with model complexity. Emphasis will
be placed on the problem of Bayesian pa rameter in
ference for the rate constants of stochastic bioc
hemical network models\, using noisy\, partial hi
gh-resolution time course data.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:info@newton.ac.uk
END:VEVENT
END:VCALENDAR