Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo

DOI10.1214/19-AOS1941zbMath1460.65005OpenAlexW3111797293WikidataQ109553611 ScholiaQ109553611MaRDI QIDQ1996782

Eric Moulines, Eero Saksman, Alain Durmus

Publication date: 26 February 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aos/1607677246

zbMATH Keywords

Markov chain Monte Carloirreducibilitygeometric ergodicityHamiltonian Monte Carlo

Mathematics Subject Classification ID

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

Related Items (11)

Stochastic approximation Hamiltonian Monte Carlo ⋮ Cauchy Markov random field priors for Bayesian inversion ⋮ Monte Carlo Simulation on the Stiefel Manifold via Polar Expansion ⋮ Couplings for Andersen dynamics ⋮ Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models ⋮ Simulating Coulomb and log-gases with hybrid Monte Carlo algorithms ⋮ Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics ⋮ Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions ⋮ Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo ⋮ Hybrid Monte Carlo methods for sampling probability measures on submanifolds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Exponential convergence of Langevin distributions and their discrete approximations
• Randomized Hamiltonian Monte Carlo
• Rates of convergence of the Hastings and Metropolis algorithms
• On the geometric ergodicity of Hamiltonian Monte Carlo
• The geometric foundations of Hamiltonian Monte Carlo
• Monte Carlo strategies in scientific computing.
• Geodesic Monte Carlo on Embedded Manifolds
• Markov Chains and Stochastic Stability
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Markov Chains
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Kinetic energy choice in Hamiltonian/hybrid Monte Carlo
• Geometric integrators and the Hamiltonian Monte Carlo method
• Theoretical and numerical comparison of some sampling methods for molecular dynamics

This page was built for publication: Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo