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:The International Year of Statistics 2013 - Series
of Public Lectures
SUMMARY:The Bayesian Approach To Inverse Problems - Andrew
Stuart\, University of Warwick
DTSTART;TZID=Europe/London:20130308T160000
DTEND;TZID=Europe/London:20130308T170000
UID:TALK43907AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/43907
DESCRIPTION:Many problems in the physical sciences require the
determination of an unknown field from a finite s
et of indirect measurements. Examples include ocea
nography\, oil recovery\, water resource managemen
t and weather forecasting. The Bayesian approach t
o these problems is natural for many reasons\, inc
luding the under-determined and ill-posed nature o
f the inversion\, the noise in the data and the un
certainty in the differential equation models used
to describe complex mutiscale physics.\n\nIn this
talk I will describe the advantages of formulatin
g Bayesian inversion on function space in order to
solve these problems. I will overview theoretical
results concerning well-posedness of the posterio
r distribution\, approximation theorems for the po
sterior distribution\, and specially constructed M
CMC methods to explore the posterior distribution
when the prior is a Gaussian random field. I will
also highlight the widespread use by practitioners
of various ad hoc algorithms such as the Ensemble
Kalman Filter\, and the need for mathematical and
statistical analysis of these ad hoc algorithms.\
n\nIntroductory reading and references may be foun
d in:\n\nhttp://arxiv.org/abs/1202.0709 [arxiv.org
] http://arxiv.org/abs/1209.2736 [arxiv.org]
LOCATION:CMS\, MR12
CONTACT:
END:VEVENT
END:VCALENDAR