BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On the convergence of the Hamiltonian Monte Carlo algorithm and ot
 her  irreversible MCMC methods - Alain Durmus — École Normale Superieur
 e\, Cachan
DTSTART:20191129T140000Z
DTEND:20191129T150000Z
UID:TALK130072@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION:Hamiltonian Monte Carlo is a very popular MCMC method amongst 
 Bayesian statisticians to get samples from a posterior distribution. This 
 algorithm relies on the discretization of Hamiltonian dynamics which leave
  the target density invariant combined with a Metropolis step. In this tal
 k\, we will discuss convergence properties of this method to sample from a
  positive target density p on $R^d$ with either a fixed or a random number
 s of integration steps. More precisely\, we will present some mild conditi
 ons on p to ensure φ-irreducibility and ergodicity of the associated chai
 n. We will also present verifiable conditions which imply geometric conver
 gence. We will conclude with the introduction of new exact continuous time
  MCMC methods\, and in particular the Bouncy Particle Sampler for which ne
 w theoretical results will be given.
LOCATION:MR12
END:VEVENT
END:VCALENDAR