BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Analysis of Monte Carlo estimators for parametric sensitivities in
  stochastic chemical kinetics - Muruhan Rathinam (University of Maryland\,
  Baltimore County)
DTSTART:20160405T084500Z
DTEND:20160405T093000Z
UID:TALK65379@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>Co-author: Ting Wang (University of Delaware) <br></span
 > <span><br>We provide an overview of some of the major Monte Carlo approa
 ches for  parametric sensitivities in stochastic chemical systems. The eff
 iciency of a  Monte Carlo approach depends in part on the variance of the 
 estimator. It has  been numerically observed that in several examples\, th
 at the finite difference  (FD) and the (regularized) pathwise differentiat
 ion (RPD) methods tend to have  lower variance than the Girsanov Tranforma
 tion (GT) estimator while the latter  has the advantage of being unbiased.
  We present a theoretical explanation in  terms of system volume asymptoti
 cs for the larger variance of the GT approach  when compared to the FD met
 hods. We also present an analysis of efficiency of  the FD and GT methods 
 in terms of desired error and system volume.</span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR