BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The aggregation problems in learning theory - Guillaume Lecue\,  C
 NRS\, Universite Paris-Est Marne-la-vallee
DTSTART:20111118T160000Z
DTEND:20111118T170000Z
UID:TALK32518@talks.cam.ac.uk
CONTACT:Richard Samworth
DESCRIPTION:Given a finite class F of functions there are three aggregatio
 n problems:\n1) the problem of Model Selection aggregation: construct a pr
 ocedure having\na risk as close as possible to the best element in F\,\n2)
  the problem of Convex aggregation: construct a procedure having a risk as
 \nclose as possible to the best element in the convex hull of F\,\n3) the 
 problem of Linear aggregation: construct a procedure having a risk as\nclo
 se as possible to the best element in the linear span of F.\n\nWe will pro
 ve that empirical risk minimization is optimal for the Convex and\nLinear 
 aggregation problems but sub-optimal for the Model Selection\naggregation 
 problem. Then we will construct an optimal aggregation procedure\nfor the 
 Model Selection aggregation.\n
LOCATION:MR12\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB
END:VEVENT
END:VCALENDAR