Couplings for Andersen Dynamics

Abstract

Andersen dynamics is a standard method for molecular simulations, and a precursor of the Hamiltonian Monte Carlo algorithm used in MCMC inference. The stochastic process corresponding to Andersen dynamics is a PDMP (piecewise deterministic Markov process) that iterates between Hamiltonian flows and velocity randomizations of randomly selected particles. Both from the viewpoint of molecular dynamics and MCMC inference, a basic question is to understand the convergence to equilibrium of this PDMP particularly in high dimension. Here we present couplings to obtain sharp convergence bounds in the Wasserstein sense that do not require global convexity of the underlying potential energy.

arXiv comment36 pages, 8 figures

References in corpus (20)

• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
• Reflection couplings and contraction rates for diffusions
• On the Geometric Ergodicity of Hamiltonian Monte Carlo
• Hypocoercivity and exponential time decay for the linear inhomogeneous relaxation Boltzmann equation
• Underdamped Langevin MCMC: A non-asymptotic analysis
• Randomized Hamiltonian Monte Carlo
• Rapid Mixing of Hamiltonian Monte Carlo on Strongly Log-Concave Distributions
• Ergodicity of the zigzag process
• Coupling and Convergence for Hamiltonian Monte Carlo
• Numerical integrators for the Hybrid Monte Carlo method
• On the convergence of Hamiltonian Monte Carlo
• Convergence to the equilibria for self-stabilizing processes in double-well landscape
• Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
• Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
• Optimal Convergence Rate of Hamiltonian Monte Carlo for Strongly Logconcave Distributions
• Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
• Cores for Piecewise-Deterministic Markov Processes used in Markov Chain Monte Carlo
• Randomized Hamiltonian Monte Carlo as Scaling Limit of the Bouncy Particle Sampler and Dimension-Free Convergence Rates
• On sampling from a log-concave density using kinetic Langevin diffusions

Cited by in corpus (4)

• Contraction and Convergence Rates for Discretized Kinetic Langevin Dynamics
• Mixing of Metropolis-Adjusted Markov Chains via Couplings: The High Acceptance Regime
• Unadjusted Hamiltonian MCMC with Stratified Monte Carlo Time Integration
• Randomized Runge-Kutta-Nyström Methods for Unadjusted Hamiltonian and Kinetic Langevin Monte Carlo