On the geometric ergodicity of Hamiltonian Monte Carlo

DOI10.3150/18-BEJ1083zbMath1428.62375arXiv1601.08057OpenAlexW2972588190MaRDI QIDQ2325354

Samuel Livingstone, Simon Byrne, Michael Betancourt, Mark A. Girolami

Publication date: 25 September 2019

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1601.08057

zbMATH Keywords

Markov chainsMarkov chain Monte CarloHamiltonian dynamicshybrid Monte Carlostochastic simulationgeometric ergodicityHamiltonian Monte Carlo

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05)

Related Items (26)

Stochastic approximation Hamiltonian Monte Carlo ⋮ HMC: reducing the number of rejections by not using leapfrog and some results on the acceptance rate ⋮ Geometric ergodicity of Gibbs samplers for the horseshoe and its regularized variants ⋮ Monte Carlo Simulation on the Stiefel Manifold via Polar Expansion ⋮ Fast Markov Chain Monte Carlo for High-Dimensional Bayesian Regression Models With Shrinkage Priors ⋮ Couplings for Andersen dynamics ⋮ Variance bounding of delayed-acceptance kernels ⋮ Geometric Ergodicity for Hamiltonian Monte Carlo on Compact Manifolds ⋮ Convergence of Position-Dependent MALA with Application to Conditional Simulation in GLMMs ⋮ Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems ⋮ On \(L^\mathfrak{q}\) convergence of the Hamiltonian Monte Carlo ⋮ Bayesian modelling of time-varying conditional heteroscedasticity ⋮ Speed up Zig-Zag ⋮ Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models ⋮ Efficient shape-constrained inference for the autocovariance sequence from a reversible Markov chain ⋮ Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics ⋮ Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo ⋮ Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions ⋮ Modified Hamiltonian Monte Carlo for Bayesian inference ⋮ Recycling intermediate steps to improve Hamiltonian Monte Carlo ⋮ Emulation-accelerated Hamiltonian Monte Carlo algorithms for parameter estimation and uncertainty quantification in differential equation models ⋮ On \(L^2\) convergence of the Hamiltonian Monte Carlo ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo ⋮ Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions ⋮ Approximations of geometrically ergodic reversible markov chains ⋮ \(\pi\) VAE: a stochastic process prior for Bayesian deep learning with MCMC

Uses Software

• Stan
• NUTS

Cites Work

• Unnamed Item
• Unnamed Item
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Information-geometric Markov chain Monte Carlo methods using diffusions
• Some things we've learned (about Markov chain Monte Carlo)
• Markov chains and stochastic stability
• Hybrid Monte Carlo on Hilbert spaces
• Extra chance generalized hybrid Monte Carlo
• General state space Markov chains and MCMC algorithms
• Ricci curvature of Markov chains on metric spaces
• A note on Metropolis-Hastings kernels for general state spaces
• Exponential convergence of Langevin distributions and their discrete approximations
• Geometric ergodicity and hybrid Markov chains
• An introduction to MCMC for machine learning
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains
• Geometric ergodicity of Metropolis algorithms
• Randomized Hamiltonian Monte Carlo
• Markov chains for exploring posterior distributions. (With discussion)
• Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo
• On the geometric ergodicity of Hamiltonian Monte Carlo
• The geometric foundations of Hamiltonian Monte Carlo
• Optimal tuning of the hybrid Monte Carlo algorithm
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Geodesic Monte Carlo on Embedded Manifolds
• Inverse problems: A Bayesian perspective
• Simulating Hamiltonian Dynamics
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Iterated Random Functions
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Nonasymptotic mixing of the MALA algorithm
• Equation of State Calculations by Fast Computing Machines
• Geometric integrators and the Hamiltonian Monte Carlo method
• A General Metric for Riemannian Manifold Hamiltonian Monte Carlo
• Connections and Extensions: A Discussion of the Paper by Girolami and Byrne
• Theoretical and numerical comparison of some sampling methods for molecular dynamics
• Monte Carlo sampling methods using Markov chains and their applications
• A function space HMC algorithm with second order Langevin diffusion limit
• Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm

This page was built for publication: On the geometric ergodicity of Hamiltonian Monte Carlo