BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Predictive Consistency
DTSTART:20220318T151500
DTEND:20220318T170000
DTSTAMP:20260411T082801Z
UID:9a9a757d9369806efc0b2b3c1336565c436f981b5f7e4985546f353d
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Philip Dawid\, Technical University of Cambridge\nWe con
 sider modelling a stream of data arriving sequentially\, but making no ass
 umptions of independence\, identical distribution\, etc.\nMany standard co
 ncepts such as parametric consistency are not wholly adequate in this cont
 ext\, and need to be replaced by suitable predictive versions. We describe
  the concept of prequential (predictive sequential) consistency\, and show
  how it holds more generally than parametric consistency. Extension is mad
 e to deal with misspecified models\, and connections are drawn with statis
 tical learning theory\, and prediction with expert advice.
LOCATION:https://epfl.zoom.us/j/66136073806
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR