BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Spectral Clustering for Dynamic Stochastic Block Model - Sharmodee
 p  Bhattacharyya (Oregon State University)
DTSTART:20160714T080000Z
DTEND:20160714T083000Z
UID:TALK66749@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>Co-author: Shirshendu Chatterjee (CUNY) <br></span> <spa
 n><br>One of the most common and crucial aspect of many network data sets 
 is the  dependence of network link structure on time or other attributes. 
 There is a  long history of researchers proposing networks for dynamic tim
 e-evolving  formation of networks. Most complex networks\, starting from b
 iological networks  like genetic or neurological networks to social\, co-a
 uthorship and citation  networks are time-varying. This has led the resear
 chers to study dynamic\,  time-evolving networks. In this work\, we consid
 er the problem of finding a  common clustering structure in time-varying n
 etworks. We consider three simple  extension of spectral clustering method
 s to dynamic settings and give  theoretical justification that the spectra
 l clustering methods produce  consistent community detection for such dyna
 mic networks. We also propose an  extension of the static version of nonpa
 rametric latent variable models to the  dynamic setting and use a special 
 case of the model to justify the spectral  clusteri ng methods. We show th
 e validity of the theoretical results via  simulations too and apply the c
 lustering methods to real-world dynamic  biological networks.</span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR