BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On Gradient-Based Optimization: Accelerated\, Stochastic and Nonco
 nvex - Michael Jordan (University of California\, Berkeley)
DTSTART:20180115T100000Z
DTEND:20180115T104500Z
UID:TALK97564@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Many new theoretical challenges have arisen in the area of gra
 dient-based optimization for large-scale statistical data analysis\, drive
 n by the needs of applications and the opportunities provided by new hardw
 are and software platforms. I discuss several related\, recent results in 
 this area: (1) a new framework for understanding Nesterov acceleration\, o
 btained by taking a continuous-time\, Lagrangian/Hamiltonian/symplectic pe
 rspective\, (2) a discussion of how to escape saddle points efficiently in
  nonconvex optimization\, and (3) the acceleration of Langevin diffusion.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR