BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalize
 d Eigenvector Computation - Dr Nicolas Flammarion
DTSTART:20181126T140000Z
DTEND:20181126T150000Z
UID:TALK114910@talks.cam.ac.uk
CONTACT:J.W.Stevens
DESCRIPTION:In this talk\, we study the problems of principal Generalized 
 Eigenvector computation and Canonical Correlation Analysis in the stochast
 ic setting. We propose a simple and efficient algorithm\, Gen-Oja\, for th
 ese problems. We prove the global convergence of our algorithm\, borrowing
  ideas from the theory of fast-mixing Markov chains and two-time-scale sto
 chastic approximation\, showing that it achieves the optimal rate of conve
 rgence.
LOCATION:CMS\, MR11
END:VEVENT
END:VCALENDAR