BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Lookahead in Sequential Monte Carlo - Prof Rong Chen\, Department 
 of Statistics\, Rutgers University
DTSTART:20091125T143000Z
DTEND:20091125T151500Z
UID:TALK21155@talks.cam.ac.uk
CONTACT:Rachel Fogg
DESCRIPTION:Dynamic systems and state space models are widely used in many
  fields of applications. Most of them are nonlinear and non-Gaussian. Sequ
 ential Carlo methods (Monte Carlo filters) have been developed for dealing
  with such systems efficiently.  It is noticed that most of the dynamic sy
 stems process strong memory. In such systems\, future observations often c
 ontain significant amount of information on the current system state. Henc
 e\, lookahead (estimation with future observations) can often produce more
  accurate inferences on the current state. In this talk we present several
  efficient lookahead Sequential Monte Carlo algorithms that utilize the fu
 ture information with manageable computational cost. Some theoretical just
 ifications and applications in signal processing will be presented.
LOCATION:LR4\, Engineering\, Department of
END:VEVENT
END:VCALENDAR