Optimizing The Integrator Step Size for Hamiltonian Monte Carlo

Abstract

Hamiltonian Monte Carlo can provide powerful inference in complex statistical problems, but ultimately its performance is sensitive to various tuning parameters. In this paper we use the underlying geometry of Hamiltonian Monte Carlo to construct a universal optimization criteria for tuning the step size of the symplectic integrator crucial to any implementation of the algorithm as well as diagnostics to monitor for any signs of invalidity. An immediate outcome of this result is that the suggested target average acceptance probability of 0.651 can be relaxed to $0.6\lesssim a\lesssim 0.9$ with larger values more robust in practice.

36 pages, 5 figures

References in corpus (2)

• The Geometric Foundations of Hamiltonian Monte Carlo
• Generalizing the No-U-Turn Sampler to Riemannian Manifolds

Cited by in corpus (5)

• The Fundamental Incompatibility of Hamiltonian Monte Carlo and Data Subsampling
• Bayesian computation: a perspective on the current state, and sampling backwards and forwards
• K-CLASH: Strangulation and Ram Pressure Stripping in Galaxy Cluster Members at 0.3 < z < 0.6
• A scalable optimal-transport based local particle filter
• A Bayesian Approach to Spherical Factor Analysis for Binary Data