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:Tutorial 2: Defining &\;lsquo\;privacy&\;rsq
uo\; for statistical databases - Adam Smith (Penns
ylvania State University)
DTSTART;TZID=Europe/London:20160705T153000
DTEND;TZID=Europe/London:20160705T170000
UID:TALK66664AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/66664
DESCRIPTION:The tutorial will introduce differential privacy\,
a widely studied definition of privacy for statis
tical databases.
We will begin with t
he motivation for rigorous definitions of privacy
in statistical databases\, covering several exampl
es of how seemingly aggregate\, high-level statist
ics can leak information about individuals in a da
ta set. We will then define differential privacy\,
illustrate the definition with several examples\,
and discuss its properties. The bulk of the tutor
ial will cover the principal techniques used for t
he design of differentially private algorithms. Ti
me permitting\, we will touch on applications of d
ifferential privacy to problems having no immediat
e connection to privacy\, such as equilibrium sele
ction in game theory and adaptive data analysis in
statistics and machine learning.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR