BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Learning from Strategic Agents
DTSTART:20151012T161500
DTEND:20151012T173000
DTSTAMP:20260407T113455Z
UID:eeda5ccb742678f6cf323f16aedcab476fef38e6fbf4f08cee9b9126
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Stratis Ioannidis - Northeastern UniversityVideo of his t
 alkAbstract :\nLearning from personal or sensitive data is a cornerstone o
 f several experimental sciences\, such as medicine and sociology. It has a
 lso become a commonplace\, and controversial\, aspect of the Internet econ
 omy. The monetary and societal benefits of learning from personal data are
  often off-set by privacy costs incurred by participating individuals. In 
 this talk\, we study these issues from the point of view of mechanism desi
 gn. We consider a learner that wishes to regress a linear function over se
 nsitive data provided by strategic agents. We show that\, when agents may 
 misreport their privacy costs\, or even purposefully distort their data ou
 t of privacy concerns\, a learner with a finite budget can still (a) incen
 tivize truthful reporting and (b) learn models that are asymptotically acc
 urate.\nThis is joint work with Rachel Cummings\, Thibaut Horel\, Patrick 
 Loiseau\, S. Muthukrishnan\, and Katrina Ligett.Bio :\nStratis Ioannidis i
 s an Assistant Professor in the E.C.E. department of Northeastern Universi
 ty. He received his B.Sc. (2002) in Electrical and Computer Engineering fr
 om the National Technical University of Athens\, and his M.Sc. (2004) and 
 Ph.D. (2009) in Computer Science from the University of Toronto. Prior to 
 joining Northeastern\, he was a research scientist at Yahoo Labs\, in Sunn
 yvale\, CA\, and at the Technicolor research centers in Paris\, France\, a
 nd Los Altos\, CA.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR