Conservative Hamiltonian Monte Carlo
From MaRDI portal
Publication:6402064
arXiv2206.06901MaRDI QIDQ6402064FDOQ6402064
Authors: Geoffrey McGregor, Andy T. S. Wan
Publication date: 14 June 2022
Abstract: We introduce a new class of Hamiltonian Monte Carlo (HMC) algorithm called Conservative Hamiltonian Monte Carlo (CHMC), where energy-preserving integrators, derived from the Discrete Multiplier Method, are used instead of symplectic integrators. Due to the volume being no longer preserved under such a proposal map, a correction involving the determinant of the Jacobian of the proposal map is introduced within the acceptance probability of HMC. For a -th order accurate energy-preserving integrator using a time step size , we show that CHMC satisfies stationarity without detailed balance. Moreover, we show that CHMC satisfies approximate stationarity with an error of if the determinant of the Jacobian is truncated to its first terms of its Taylor polynomial in . We also establish a lower bound on the acceptance probability of CHMC which depends only on the desired tolerance for the energy error and approximate determinant. In particular, a cost-effective and gradient-free version of CHMC is obtained by approximating the determinant of the Jacobian as unity, leading to an error to the stationary distribution and a lower bound on the acceptance probability depending only on . Furthermore, numerical experiments show increased performance in acceptance probability and convergence to the stationary distribution for the Gradient-free CHMC over HMC in high dimensional problems.
Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Numerical methods for Hamiltonian systems including symplectic integrators (65P10)
This page was built for publication: Conservative Hamiltonian Monte Carlo
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6402064)