Ensemble preconditioning for Markov chain Monte Carlo simulation
From MaRDI portal
Publication:1702007
DOI10.1007/S11222-017-9730-1zbMATH Open1384.65004arXiv1607.03954OpenAlexW2962885101MaRDI QIDQ1702007FDOQ1702007
Authors: Charles Matthews, Jonathan Weare, Benedict Leimkuhler 
Publication date: 27 February 2018
Published in: Statistics and Computing (Search for Journal in Brave)
Abstract: We describe parallel Markov chain Monte Carlo methods that propagate a collective ensemble of paths, with local covariance information calculated from neighboring replicas. The use of collective dynamics eliminates multiplicative noise and stabilizes the dynamics thus providing a practical approach to difficult anisotropic sampling problems in high dimensions. Numerical experiments with model problems demonstrate that dramatic potential speedups, compared to various alternative schemes, are attainable.
Full work available at URL: https://arxiv.org/abs/1607.03954
Recommendations
Markov chain Monte Carlomachine learningMCMCcomputational statisticsBrownian dynamicsstochastic samplingBFGSLangevin methods
Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)
Cites Work
- MCMC using Hamiltonian dynamics
- A general purpose sampling algorithm for continuous distributions (the t-walk)
- An adaptive Metropolis algorithm
- Optimization theory and methods. Nonlinear programming
- Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
- Ensemble samplers with affine invariance
- Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
- Title not available (Why is that?)
- Accelerating diffusions
- Title not available (Why is that?)
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- Accelerating Gaussian diffusions
- Irreversible Langevin samplers and variance reduction: a large deviations approach
- Variance reduction using nonreversible Langevin samplers
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
- Free energy methods for Bayesian inference: efficient exploration of univariate Gaussian mixture posteriors
- Scaling Limits for the Transient Phase of Local Metropolis–Hastings Algorithms
- Improved diffusion Monte Carlo
- Pathwise accuracy and ergodicity of metropolized integrators for SDEs
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Molecular dynamics. With deterministic and stochastic numerical methods
- Metropolis integration schemes for self-adjoint diffusions
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Convergence of adaptive direction sampling
Cited In (27)
- A new bi-fidelity model reduction method for Bayesian inverse problems
- Efficient derivative-free Bayesian inference for large-scale inverse problems
- Constructing sampling schemes via coupling: Markov semigroups and optimal transport
- Title not available (Why is that?)
- Consensus‐based sampling
- Constrained ensemble Langevin Monte Carlo
- Interacting Langevin diffusions: gradient structure and ensemble Kalman sampler
- Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions
- Iterated Kalman methodology for inverse problems
- Potential-decomposition strategy in Markov chain Monte Carlo sampling algorithms
- Ensemble Markov chain Monte Carlo with teleporting walkers
- Extended ensemble Monte Carlo approach to hardly relaxing problems
- The parallel replica method for computing equilibrium averages of Markov chains
- EnsembleQN
- Affine invariant interacting Langevin dynamics for Bayesian inference
- Ensemble slice sampling. Parallel, black-box and gradient-free inference for correlated \& multimodal distributions
- Preconditioning Markov Chain Monte Carlo Simulations Using Coarse-Scale Models
- Sequential Kalman tuning of the \(t\)-preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
- Fokker-Planck particle systems for Bayesian inference: computational approaches
- Covariance-modulated optimal transport and gradient flows
- Ensemble transport adaptive importance sampling
- Ensemble Monte Carlo calculations with five novel moves
- Calibrate, emulate, sample
- Derivative-Free Bayesian Inversion Using Multiscale Dynamics
- Ensemble samplers with affine invariance
- Ensemble inference methods for models with noisy and expensive likelihoods
- Affine-invariant ensemble transform methods for logistic regression
Uses Software
This page was built for publication: Ensemble preconditioning for Markov chain Monte Carlo simulation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1702007)
