BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Encrypted Inference for Arbitrary Models - Louis Aslett (U
 niversity of Oxford)
DTSTART:20170705T151500Z
DTEND:20170705T160000Z
UID:TALK73160@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:There has been substantial progress in development of statisti
 cal methods which are amenable to computation with modern cryptographic te
 chniques\, such as homomorphic encryption. &nbsp\;This has enabled fitting
  and/or prediction of models in areas from classification and regression t
 hrough to genome wide association studies. &nbsp\;However\, these are tech
 niques devised to address specific models in specific settings\, with the 
 broader challenge of an approach to inference for arbitrary models and arb
 itrary data sets receiving less attention. &nbsp\;This talk will discuss v
 ery recent results from ongoing work towards an approach which may allow t
 heoretically arbitrary low dimensional models to be fitted fully encrypted
 \, keeping the model and prior secret from data owners and vice-versa. &nb
 sp\;The methodology will be illustrated with a variety of examples\, toget
 her with a discussion of the ongoing direction of the work.<br><br>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR