BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251224T235415EST-0658dw4hp8@132.216.98.100
DTSTAMP:20251225T045415Z
DESCRIPTION:\n	Adaptive MCMC For Everyone\n\n	Abstract:\n\n\nMarkov chain Mon
 te Carlo (MCMC) algorithms\, such as the Metropolis Algorithm and the Gibb
 s Sampler\, are an extremely useful and popular method of approximately sa
 mpling from complicated probability distributions. Adaptive MCMC attempts 
 to automatically modify the algorithm while it runs\, to improve its perfo
 rmance on the fly. However\, such adaptation often destroys the ergodicity
  properties necessary for the algorithm to be valid. In this talk\, we fir
 st illustrate MCMC algorithms using simple graphical examples. We then dis
 cuss adaptive MCMC\, and present examples and theorems concerning its ergo
 dicity and efficiency.\n\n\n	Speaker\n\n\nJeffrey Rosenthal is a professor 
 of statistics\, specialising in Markov chain Monte Carlo (MCMC) algorithms
 . He received his bachelor degree from the University of Toronto\, and his
  PhD in Mathematics from Harvard University. He was awarded the 2006 CRM-S
 SC Prize\, the 2007 COPSS Presidents’ Award\, the 2013 SSC Gold Medal\, an
 d teaching awards at both Harvard and Toronto. He is a fellow of the Insti
 tute of Mathematical Statistics and of the Royal Society of Canada. His bo
 ok for the general public\, Struck by Lightning\, was published in sixteen
  editions and ten languages\, and was a bestseller in Canada.\n\nZoom Link
 \n\nMeeting ID: 924 5390 4989\n\nPasscode: 690084\n
DTSTART:20201016T193000Z
DTEND:20201016T203000Z
SUMMARY:Jeffrey Rosenthal (University of Toronto)
URL:/mathstat/channels/event/jeffrey-rosenthal-univers
 ity-toronto-325345
END:VEVENT
END:VCALENDAR