BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Convex Relaxation for Community Detection with Covariates - Purna 
 Sarkar (University of Texas at Austin)
DTSTART:20160715T150000Z
DTEND:20160715T153000Z
UID:TALK66779@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Community detection in networks is an important problem in man
 y applied areas. We investigate this in the presence of node covariates. R
 ecently\, an emerging body of theoretical work has been focused on &nbsp\;
 leveraging information from both the edges in the network and the node cov
 ariates to infer community memberships. However\, in most parameter regime
 s\, one of the sources of information provides enough information to infer
  the hidden clusters\, thereby making the other source redundant. We show&
 nbsp\;that when the network and the covariates carry ``orthogonal&#39\;&#3
 9\; pieces of information about the cluster memberships\, one can get asym
 ptotically consistent clustering by using them both\, while each of them f
 ails individually.&nbsp\;<br><br>This is joint work with Bowei Yan\, Unive
 rsity of Texas at Austin.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR