BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Approximate Bayesian Inference for Stochastic Processes - Stumph\,
  M (Imperial College London)
DTSTART:20140425T085000Z
DTEND:20140425T092500Z
UID:TALK52188@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Co-authors: Paul Kirk (Imperial College London)\, Angelique Al
 e (Imperial College London)\, Ann Babtie (Imperial College London)\, Sarah
  Filippi (Imperial College London)\, Eszter Lakatos (Imperial College Lond
 on)\, Daniel Silk (Imperial College London)\, Thomas Thorn (University of 
 Edinburgh) \n\nWe consider approximate Bayesian computation (ABC) approach
 es to model the dynamics and evolution of molecular networks. Initially co
 nceived to cope with problems with intractable likelihoods\, ABC has gaine
 d popularity over the past decade. But there are still considerable proble
 ms in applying ABC to real-world problems\, some of which are shared with 
 exact Bayesian inference\, but some are due to the nature of ABC. Here we 
 will present some recent advances that allow us to apply ABC sequential Mo
 nte Carlo (SMC) to real biological problems. The rate of convergence of AB
 C-SMC depends crucially on the schedule of thresholds\, ?t\, t=1\,2\,\,T\,
  and the perturbation kernels used to generate proposals from the previous
  population of parameters. We show how both of these can be tuned individu
 ally\, and jointly. Careful calibration of the ABC-SMC approach can result
  in a 10-fold reduction in the computational burden (or more). I will also
  provide an overview of an alternative approach where\, rather than approx
 imating the likelihood in an ABC framework\, we provide approximations to 
 the master equation that describes the evolution of the stochastic system\
 , that go beyond the conventional linear noise approximation (LNA). This a
 llows us to tackle systems with ``interesting dynamics"\, that are typical
 ly beyond the scope of the LNA\, and we will show how to use such approach
 es in exact Bayesian inference procedures (including nested sampling and S
 MC).\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR