Title: Adjustable Randomized Time Integrators for Hamiltonian Monte Carlo
Abstract: Hamiltonian Monte Carlo is a gradient-based Metropolis-Hastings algorithm with a proposal distribution that involves ceil(T/h) steps of a time integrator of Hamiltonian dynamics; where T and h are the duration and time-step-size hyperparameters. Here we show how to incorporate time integrator randomization into the proposal distribution and present L^2 Wasserstein mixing time guarantees for the corresponding unadjusted algorithm. These guarantees illustrate the potential role of time integrator randomization in HMC.