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:Applied and Computational Analysis
SUMMARY:Convergence analysis of non-stationary and deep Ga
ussian process regression - Aretha Teckentrup (Uni
versity of Edinburgh)
DTSTART;TZID=Europe/London:20230126T150000
DTEND;TZID=Europe/London:20230126T160000
UID:TALK196093AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/196093
DESCRIPTION:We are interested in the task of estimating an unk
nown function from data\, given as a set of point
evaluations. In this context\, Gaussian process re
gression is often used as a Bayesian inference pro
cedure\, and we are interested in the convergence
as the number of data points goes to infinity. Usi
ng results from scattered data approximation\, we
provide a convergence analysis of the method appli
ed to a given\, unknown function of interest. We a
re particularly interested in the case of non-stat
ionary covariance kernels\, and the extension of t
he results to deep Gaussian processes.\n\nThis is
joint work with Conor Osborne (University of Edinb
urgh).\n
LOCATION:Centre for Mathematical Sciences\, MR14
CONTACT:Matthew Colbrook
END:VEVENT
END:VCALENDAR