Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
From MaRDI portal
Publication:2093317
Abstract: We establish the geometric ergodicity of the preconditioned Hamiltonian Monte Carlo (HMC) algorithm defined on an infinite-dimensional Hilbert space, as developed in [Beskos et al., Stochastic Process. Appl., 2011]. This algorithm can be used as a basis to sample from certain classes of target measures which are absolutely continuous with respect to a Gaussian measure. Our work addresses an open question posed in [Beskos et al., Stochastic Process. Appl., 2011], and provides an alternative to a recent proof based on exact coupling techniques given in arXiv:1909.07962. The approach here establishes convergence in a suitable Wasserstein distance by using the weak Harris theorem together with a generalized coupling argument. We also show that a law of large numbers and central limit theorem can be derived as a consequence of our main convergence result. Moreover, our approach yields a novel proof of mixing rates for the classical finite-dimensional HMC algorithm. As such, the methodology we develop provides a flexible framework to tackle the rigorous convergence of other Markov Chain Monte Carlo algorithms. Additionally, we show that the scope of our result includes certain measures that arise in the Bayesian approach to inverse PDE problems, cf. [Stuart, Acta Numer., 2010]. Particularly, we verify all of the required assumptions for a certain class of inverse problems involving the recovery of a divergence free vector field from a passive scalar, arXiv:1808.01084v3.
Recommendations
- A function space HMC algorithm with second order Langevin diffusion limit
- Hybrid Monte Carlo on Hilbert spaces
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- On L^2 convergence of the Hamiltonian Monte Carlo
Cites work
- A Bayesian Approach to Estimating Background Flows from a Passive Scalar
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- A function space HMC algorithm with second order Langevin diffusion limit
- A note on Metropolis-Hastings kernels for general state spaces
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- Advanced MCMC methods for sampling on diffusion pathspace
- An analysis of infinite dimensional Bayesian inverse shape acoustic scattering and its numerical approximation
- Analysis of SPDEs arising in path sampling. I: The Gaussian case
- Analysis of SPDEs arising in path sampling. II: The nonlinear case
- Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
- Central limit theorem for Markov processes with spectral gap in the Wasserstein metric
- Equation of state calculations by fast computing machines
- Ergodic behavior of Markov processes. With applications to limit theorems
- Exponential convergence for the stochastically forced Navier-Stokes equations and other partially dissipative dynamics
- FEM-based discretization-invariant MCMC methods for PDE-constrained Bayesian inverse problems
- Fluctuations in Markov processes. Time symmetry and martingale approximation.
- Geometric integrators and the Hamiltonian Monte Carlo method
- Geometric MCMC for infinite-dimensional inverse problems
- scientific article; zbMATH DE number 3121180 (Why is no real title available?)
- scientific article; zbMATH DE number 1223843 (Why is no real title available?)
- scientific article; zbMATH DE number 646825 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- Hybrid Monte Carlo on Hilbert spaces
- Introduction to nonparametric estimation
- Invariant measures of stochastic partial differential equations and conditioned diffusions
- Inverse problems: a Bayesian perspective
- Markov chains and stochastic stability
- Mathematics of two-dimensional turbulence.
- MCMC METHODS FOR DIFFUSION BRIDGES
- MCMC methods for functions: modifying old algorithms to make them faster
- MCMC using Hamiltonian dynamics
- Monte Carlo sampling methods using Markov chains and their applications
- Monte Carlo strategies in scientific computing.
- Navier-Stokes equations. Theory and numerical analysis. Repr. with corr
- On a Strong Law of Large Numbers for Martingales
- On Bayesian consistency for flows observed through a passive scalar
- On the geometric ergodicity of Hamiltonian Monte Carlo
- On unique ergodicity in nonlinear stochastic partial differential equations
- Optimal Transport
- Optimal tuning of the hybrid Monte Carlo algorithm
- Probability
- Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm
- Randomized Hamiltonian Monte Carlo
- Sampling conditioned diffusions
- Signal processing problems on function space: Bayesian formulation, stochastic PDEs and effective MCMC methods
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Spectral gaps in Wasserstein distances and the 2D stochastic Navier-Stokes equations
- Statistical and computational inverse problems.
- Stochastic Equations in Infinite Dimensions
- Stochastic spectral methods for efficient Bayesian solution of inverse problems
- Subgeometric rates of convergence in Wasserstein distance for Markov chains
- Subgeometric rates of convergence of Markov processes in the Wasserstein metric
- Sur le comportement global des solutions non-stationnaires des équations de Navier-Stokes en dimension 2
- The Convergence of Markov Chain Monte Carlo Methods: From the Metropolis Method to Hamiltonian Monte Carlo
- The explosion problem in a flow
- The geometric foundations of Hamiltonian Monte Carlo
- The Monte Carlo Method
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(13)- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
- On L^2 convergence of the Hamiltonian Monte Carlo
- scientific article; zbMATH DE number 7249109 (Why is no real title available?)
- A function space HMC algorithm with second order Langevin diffusion limit
- Geometric Ergodicity for Hamiltonian Monte Carlo on Compact Manifolds
- On \(L^\mathfrak{q}\) convergence of the Hamiltonian Monte Carlo
- On the accept-reject mechanism for Metropolis-Hastings algorithms
- Polynomial mixing of a stochastic wave equation with dissipative damping
- Convergence of preconditioned Hamiltonian Monte Carlo on Hilbert spaces
- On the long-time statistical behavior of smooth solutions of the weakly damped, stochastically-driven KdV equation
- Long-term accuracy of numerical approximations of SPDEs with the stochastic Navier-Stokes equations as a paradigm
- Hybrid Monte Carlo on Hilbert spaces
This page was built for publication: Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2093317)
