BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical inference for compound regression - Alexandre Tsybakov
 \, Université Paris VI
DTSTART:20120518T150000Z
DTEND:20120518T160000Z
UID:TALK38172@talks.cam.ac.uk
CONTACT:Richard Samworth
DESCRIPTION:This talk considers a general nonparametric regression model c
 alled the compound model. It contains as two special cases sparse additive
  regression and nonparametric regression with many covariates but possibly
  a small number of relevant covariates. A compound model is characterized 
 by three main parameters: the "microscopic" sparsity parameter indicating 
 the number of relevant covariates\, the structure parameter\, i.e.\, a bin
 ary sequence describing the "macroscopic" structure of the compound functi
 on and the usual smoothness parameter corresponding to the complexity of t
 he members of the compound.  We find non-asymptotic minimax rate of conver
 gence of estimators in such a model as a function of these three parameter
 s. We also show that this rate can be attained in an adaptive way. This is
  a joint work with Arnak Dalalyan and Yuri Ingster.
LOCATION:MR5\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB
END:VEVENT
END:VCALENDAR