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:Modern Bayesian machine learning methods and their
application to finance and econometrics - Ghahram
ani\, Z (University of Cambridge)
DTSTART;TZID=Europe/London:20131119T115000
DTEND;TZID=Europe/London:20131119T124000
UID:TALK48895AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/48895
DESCRIPTION:Uncertainty\, data\, and inference play a fundamen
tal role in modelling. Probabilistic approaches to
modelling have transformed scientific data analys
is\, artificial intelligence and machine learning\
, and have made it possible to exploit the many op
portunities arising from the recent explosion of b
ig data problems arising in the sciences\, society
and commerce. Once a probabilistic model is defin
ed\, Bayesian statistics (which used to be called
"inverse probability") can be used to make inferen
ces and predictions from the model. Bayesian metho
ds work best when they are applied to models that
are flexible enough to capture the complexity of r
eal-world data. Recent work on non-parametric Baye
sian machine learning provides this flexibility. \
n\nI will give an overview of some of our recent w
ork in nonparametric Bayesian modelling\, with an
emphasis on models that might be useful in compute
rised trading\, finance and econometrics. Some top
ics I will cover include scalable and interpretabl
e time series forecasting with Gaussian process re
gression models\, modelling switching and non-stat
ionarity in time series with infinite HMMs\, and m
ultivariate stochastic volatility via Wishart proc
esses and dynamic covariance models. \n
LOCATION:Seminar Room 2\, Newton Institute Gatehouse
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR