BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Convergence of the Expectation Maximization algorithm revisited
DTSTART:20260908T091500Z
DTEND:20260908T101500Z
DTSTAMP:20260704T063800Z
UID:indico-event-16695@indico.math.cnrs.fr
DESCRIPTION:Speakers: Dominikus Noll (IMT)\n\nThe EM-algorithm assures mon
 otone increase of the incomplete data likelihood\, but does not in general
  guarantee convergence of the parameter estimates. We take a fresh look at
  the situation and present novel sufficient conditions for convergence tha
 t are conveniently verifiable in practical situations. Illustrations with 
 typical applications of the EM-algorithm are given.\nKey words: Kullback-L
 eibler divergence\, Fisher information\, exponential family\, proximal poi
 nt method\, definability\, information geometry \n\nhttps://indico.math.c
 nrs.fr/event/16695/
LOCATION:Salle K. Johnson (1R3\, 1er étage)
URL:https://indico.math.cnrs.fr/event/16695/
END:VEVENT
END:VCALENDAR