2017

On the convergence of Hamiltonian Monte Carlo

Durmus, Alain, Moulines, Eric, Saksman, Eero

Understand

This paper discusses the irreducibility and geometric ergodicity of the Hamiltonian Monte Carlo (HMC) algorithm.

  • We consider cases where the number of steps of the symplectic integrator is either fixed or random.
  • Under mild conditions on the potential $\F$ associated with target distribution $\pi$, we first show that the Markov kernel associated to the HMC algorithm is irreducible and recurrent.
  • Under more stringent conditions, we then establish that the Markov kernel is Harris recurrent.

Reading the bibliography…