BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260516T154654EDT-7048HBsxNV@132.216.98.100
DTSTAMP:20260516T194654Z
DESCRIPTION:\n	Dynamic Games and Applications Seminar\n	Speaker: Vivek Borkar
  – Department of Electrical Engineering\, IIT Bombay\, India\n\n	Webinar li
 nk\n		Webinar ID: 881 6070 4034\n		Passcode: 095916\n\n	In this talk\, I introd
 uce a model of graph-constrained dynamic choice with reinforcement modeled
  by positively α-homogeneous rewards. Its empirical process\, which can be
  written as a stochastic approximation recursion with Markov noise\, has t
 he same probability law as a certain vertex reinforced random walk. Thus\,
  the limiting differential equation that it tracks coincides with the forw
 ard Kolmogorov equation for the latter\, which in turn is a scaled version
  of a special instance of replicator dynamics with potential. This equival
 ence is exploited to show that for α>0\, the asymptotic outcome concentrat
 es around the optimum in a certain limiting sense when 'annealed' by letti
 ng α↑∞ slowly. \n\n	(Joint work with Konstantin Avrachenkov\, Sharayu Mohar
 ir and Suhail Mohmad Shah.)\n\n
DTSTART:20210520T150000Z
DTEND:20210520T160000Z
LOCATION:CA\, ZOOM
SUMMARY:Graph-constrained dynamic choice
URL:https://www.mcgill.ca/cim/channels/event/graph-constrained-dynamic-choi
 ce-331138
END:VEVENT
END:VCALENDAR