BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Three Small Steps ... to Reconceiving Machine Learning - Prof. Bob
  Williamson\, Australian National University
DTSTART:20101108T110000Z
DTEND:20101108T120000Z
UID:TALK27894@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:I will show by way of three separate illustrations my work on 
 my long term project of reconceiving machine learning. After a brief intro
 duction to the project\, I will show a new and explicit characterisation o
 f the convexity of proper composite losses (the composition of a proper bi
 nary loss or scoring rule with a link function). Such losses are the appro
 priate choice for binary class probability estimation. Second I will show 
 an apparently novel relationship between M-estimators (where one maximises
  an objective function) and L-estimators (linear combinations of order sta
 tistics). Finally I will merely sketch an intriguing connection between th
 e design of loss functions for prediction problems and different uncertain
 ty calculi that have been developed in the economics literature. Intriguin
 gly\, there are results that show that even if one starts from a pure “B
 ayesian” perspective\, one is inexorably lead to nonlinear expectations 
 that do not fit within the framework of probability theory. The conclusion
  is that to do a proper job of being the “new science of uncertainty” 
 machine learning needs to look well beyond the theory of probability.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR