BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The role of invariance in learning from random graphs and structur
 ed data - Peter Orbanz (Columbia University)
DTSTART:20161020T130000Z
DTEND:20161020T140000Z
UID:TALK68403@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Graphon models can be derived from the concept of exchangeabil
 ity\, which has long played an important role in (Bayesian) statistics. Ex
 changeability is\, in turn\, a special case of probabilistic invariance\, 
 or symmetry. This talk will be an attempt to explain\, in as non-technical
  a manner as possible\, why and how invariance is useful in statistics. I 
 will cover some general results\, discuss how different notions of exchang
 eability fit into the picture\, and how invariance can be regarded as a co
 nsequence of assumptions on the process by which the data was sampled. All
  of this ultimately concerns the problem: What can we learn about an infin
 ite random structure if only a finite sample from a single realization is 
 observed?  <br><br><br>
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR