BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bayesian Hierarchical Community Discovery - Yee Whye Teh (Universi
 ty of Oxford\; The Alan Turing Institute)
DTSTART:20160726T130000Z
DTEND:20160726T133000Z
UID:TALK66852@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>Co-author: Charles Blundell (Google DeepMind) <br></span
 > <br>We propose an efficient Bayesian nonparametric model for discovering
   hierarchical community structure in social networks. Our model is a  tre
 e-structured mixture of potentially exponentially many stochastic  blockmo
 dels. We describe a family of greedy agglomerative model selection  algori
 thms whose worst case scales quadratically in the number of vertices of  t
 he network\, but independent of the number of communities. Our algorithms 
 are  two orders of magnitude faster than the infinite relational model\, a
 chieving  comparable or better accuracy. <br><br>Related Links <ul> <li><a
  target="_blank" rel="nofollow">http://papers.nips.cc/paper/5048-bayesian-
 hierarchical-community-discovery</a>  - NIPS paper page&nbsp\;</li></ul>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR