BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251121T161650EST-3117jwGKAa@132.216.98.100
DTSTAMP:20251121T211650Z
DESCRIPTION:(Sparse) Exchangeable Graphs\n\nMany popular statistical models
  for network valued datasets fall under the remit of the graphon framework
 \, which (implicitly) assumes the networks are densely connected. However\
 , this assumption rarely holds for the real-world networks of practical in
 terest. We introduce a new class of models for random graphs that generali
 ses the dense graphon models to the sparse graph regime\, and we argue tha
 t this meets many of the desiderata one would demand of a model to serve a
 s the foundation for a statistical analysis of real-world networks. The ke
 y insight is to define the models by way of a novel notion of exchangeabil
 ity\; this is analogous to the specification of conditionally i.i.d. model
 s by way of de Finetti's representation theorem. We further develop this m
 odel class by explaining the foundations of sampling and estimation of net
 work models in this setting. The later result can be can be understood as 
 the (sparse) graph analogue of estimation via the empirical distribution i
 n the i.i.d. sequence setting.\n\n \n
DTSTART:20170113T203000Z
DTEND:20170113T213000Z
LOCATION:Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue Sherbrooke 
 Ouest
SUMMARY:Victor Veitch\, PhD Candidate University of Toronto
URL:/mathstat/channels/event/victor-veitch-phd-candida
 te-university-toronto-265014
END:VEVENT
END:VCALENDAR