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:Towards Encrypted Inference for Arbitrary Models -
Louis Aslett (University of Oxford)
DTSTART;TZID=Europe/London:20170705T161500
DTEND;TZID=Europe/London:20170705T170000
UID:TALK73160AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/73160
DESCRIPTION:There has been substantial progress in development
of statistical methods which are amenable to comp
utation with modern cryptographic techniques\, suc
h as homomorphic encryption.  \;This has enabl
ed fitting and/or prediction of models in areas fr
om classification and regression through to genome
wide association studies.  \;However\, these
are techniques devised to address specific models
in specific settings\, with the broader challenge
of an approach to inference for arbitrary models a
nd arbitrary data sets receiving less attention. &
nbsp\;This talk will discuss very recent results f
rom ongoing work towards an approach which may all
ow theoretically arbitrary low dimensional models
to be fitted fully encrypted\, keeping the model a
nd prior secret from data owners and vice-versa. &
nbsp\;The methodology will be illustrated with a v
ariety of examples\, together with a discussion of
the ongoing direction of the work.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR