BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On the convergence of Adaptive sequential Monte Carlo Methods - Dr
  Ajay Jasra\, Department of Statistics and Applied Probability\, National 
 University of Singapore
DTSTART:20130603T130000Z
DTEND:20130603T140000Z
UID:TALK45523@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION:In several implementations of Sequential Monte Carlo (SMC) met
 hods\, it is natural and important in terms of algorithmic efficiency\, to
  exploit the information on the history of the particles to optimally tune
  their subsequent propagations. In the following talk we provide an asympt
 otic theory for a class of such adaptive SMC methods. Our theoretical fram
 ework developed here will cover for instance\, under assumptions\, the alg
 orithms in Chopin (2002)\, Jasra et al (2011)\, Schafer & Chopin (2013). T
 here are limited results about the theoretical underpinning of such adapti
 ve methods: we will bridge this gap by providing a weak law of large numbe
 rs (WLLN) and a central limit theorem (CLT) for some of the algorithms. Th
 e latter seems to be the first result of its kind in the literature and pr
 ovides a formal justification of algorithms that are used in many practica
 l scenarios. This is a joint work with Alex Beskos (NUS/UCL).
LOCATION:LR11\, Engineering\, Department of
END:VEVENT
END:VCALENDAR