BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Dantzig selector for high dimensional statistical problems - R
 ivoirard\, V (Paris-Dauphine)
DTSTART:20110322T160000Z
DTEND:20110322T170000Z
UID:TALK30342@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:The Dantzig selector has been introduced by Emmanuel Candes an
 d Terence Tao in an outstanding paper that deals with prediction and varia
 ble selection in the setting of the curse of dimensionality extensively co
 nsidered in statistics recently. Using sparsity assumptions\, variable sel
 ection performed by the Dantzig selector can improve estimation accuracy b
 y effectively identifying the subset of important predictors\, and then en
 hance model interpretability allowed by parsimonious representations. The 
 goal of this talk is to present the main ideas of the paper by Candes and 
 Tao and the remarkable results they obtained. We also wish to emphasize so
 me of the extensions proposed in different settings and in particular for 
 density estimation considered in the dictionary approach. Finally\, connec
 tions between the Dantzig selector and the popular lasso procedure will be
  also highlighted.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR