BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20240327T102903Z
DTSTART:20240327T103000Z
DTEND:20240327T113000Z
SUMMARY:AI-Fun Seminar | Gavin Brown: Bias/Variance is not the same as Ap
 proximation/Estimation
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}n2xv-lt4bo1
 0e-qk055w
DESCRIPTION:The Manchester Centre for AI Fundamentals is hosting a series
  of seminars featuring expert researchers working in the fundamentals of
  AI and our speaker on 27 March is Professor Gavin Brown.\n\nTitle: \nBi
 as/Variance is not the same as Approximation/Estimation\n\nAbstract:\nWe
  study the relation between two classical results: the bias-variance dec
 omposition\, and the approximation-estimation decomposition. Both are im
 portant conceptual tools in Machine Learning\, helping us describe the n
 ature of model fitting. It is commonly stated that they are “closely rel
 ated”\, or “similar in spirit”. However\, sometimes it is said they are 
 equivalent. In fact\, they are different but have subtle connections cut
 ting across learning theory\, classical statistics\, and information geo
 metry\, that (very surprisingly) have not been previously observed. We p
 resent several results for losses expressible as Bregman divergences: a 
 broad family with a known bias-variance decomposition. Discussion and fu
 ture directions are presented for more general losses\, including the 0/
 1 classification loss.\n\nGavin Brown is Professor of Machine Learning a
 t Manchester. Find him at: profgavinbrown.github.io
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:6.207\, University Place\, Manchester
END:VEVENT
END:VCALENDAR