BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Variable clustering: optimal bounds and a convex approach - Nicola
 s Verzelen (INRA)
DTSTART:20170609T140000Z
DTEND:20170609T150000Z
UID:TALK71963@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:The problem of variable clustering is that of grouping similar
  components of a p-dimensional vector X = (X_1 \, ... \, X_p)\, and estima
 ting these groups from n independent copies of X. Although K-means is a na
 tural strategy for this problem\, I will explain why it cannot lead to per
 fect cluster recovery. Then\, I will  introduce a correction that can be v
 iewed as a penalized convex relaxation of K-means. The clusters estimated 
 by this method are shown to recover the partition G at a minimax optimal c
 luster separation rate.
LOCATION:MR12\, Centre for Mathematical Sciences\, Wilberforce Road\, Camb
 ridge.
END:VEVENT
END:VCALENDAR