BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient implementation of Markov chain Monte Carlo when using an
  unbiased likelihood estimator - Pitt\, M (University of Warwick)
DTSTART:20140422T124500Z
DTEND:20140422T132000Z
UID:TALK52088@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:When an unbiased estimator of the likelihood is used within an
  Metropolis-Hastings scheme\, it is necessary to tradeoff the number of sa
 mples used to evaluate the likelihood against the computing time. Many sam
 ples will result in a scheme which has similar properties to the case wher
 e the likelihood is exactly known but will be expensive. Few samples will 
 result in faster estimation but at the expense of slower mixing of the Mar
 kov chain. We explore the relationship between the number of samples and t
 he efficiency of the resulting Metropolis-Hastings estimates. Under the as
 sumption that the distribution of the additive noise introduced by the log
 -likelihood estimator is independent of the point at which this log-likeli
 hood is evaluated and other relatively mild assumptions\, we provide guide
 lines on the number of samples to select for a general Metropolis-Hastings
  proposal. We illustrate on a complex stochastic volatility model that the
 se assumptions are approximately satisfied experimentally and that the the
 oretical insights with regards to inefficiency and computational time hold
  true. \n\nKeywords: Bayesian inference\; Estimated likelihood\; Metropoli
 s-Hastings\; Particle filtering.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR