BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Greedy Algorithm for Subspace Clustering from Corrupted and Incom
 plete Data - Alexander Petukhov (University of Georgia\, USA)
DTSTART:20150909T140000Z
DTEND:20150909T150000Z
UID:TALK60632@talks.cam.ac.uk
CONTACT:34282
DESCRIPTION:We describe the Fast Greedy Sparse Subspace Clustering (FGSSC)
  algorithm providing an efficient method for clustering data belonging to 
 a few low-dimensional linear or affine subspaces. The main difference of o
 ur algorithm from predecessors is its ability to work with noisy data havi
 ng a high rate of erasures (missed entries at the known locations) and err
 ors (corrupted entries at unknown locations). \n\nThe algorithm has signif
 icant advantage over predecessor on synthetic models as well as for the Ex
 tended Yale B dataset of facial images. In particular\, the face recogniti
 on misclassification rate turned out to be 6--20 times lower than for the 
 SSC algorithm.  
LOCATION:MR 14\, CMS
END:VEVENT
END:VCALENDAR