Particle Metropolis-adjusted Langevin algorithms

DOI10.1093/BIOMET/ASW020zbMATH Open1506.62135arXiv1412.7299OpenAlexW2963872333WikidataQ61434476 ScholiaQ61434476MaRDI QIDQ5384403FDOQ5384403

Authors: Christopher Nemeth, Chris Sherlock, Paul Fearnhead 

Publication date: 24 June 2019

Published in: Biometrika (Search for Journal in Brave)

Abstract: This paper proposes a new sampling scheme based on Langevin dynamics that is applicable within pseudo-marginal and particle Markov chain Monte Carlo algorithms. We investigate this algorithm's theoretical properties under standard asymptotics, which correspond to an increasing dimension of the parameters, $n$. Our results show that the behaviour of the algorithm depends crucially on how accurately one can estimate the gradient of the log target density. If the error in the estimate of the gradient is not sufficiently controlled as dimension increases, then asymptotically there will be no advantage over the simpler random-walk algorithm. However, if the error is sufficiently well-behaved, then the optimal scaling of this algorithm will be $O(n^{-1/6})$ compared to $O(n^{-1/2})$ for the random walk. Our theory also gives guidelines on how to tune the number of Monte Carlo samples in the likelihood estimate and the proposal step-size.

Full work available at URL: https://arxiv.org/abs/1412.7299

Recommendations

• On the efficiency of pseudo-marginal random walk Metropolis algorithms
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Large-sample asymptotics of the pseudo-marginal method

zbMATH Keywords

particle filteroptimal scalingparticle Markov chain Monte CarloMetropolis-adjusted Langevin algorithmpseudo-marginal Markov chain Monte Carlo

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Computational methods for problems pertaining to statistics (62-08) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

Cited In (18)

• Augmentation schemes for particle MCMC
• Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
• Particle Metropolis-Hastings using gradient and Hessian information
• Optimal volume-corrected Laplace-Metropolis method
• Efficiency of delayed-acceptance random walk metropolis algorithms
• Neglected chaos in international stock markets: Bayesian analysis of the joint return-volatility dynamical system
• Hamiltonian Monte Carlo with energy conserving subsampling
• A flexible particle Markov chain Monte Carlo method
• Machine learning meta-models for fast parameter identification of the lattice discrete particle model
• Constrained ensemble Langevin Monte Carlo
• Making inference of British household's happiness efficiency: a Bayesian latent model
• Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions
• On the efficiency of pseudo-marginal random walk Metropolis algorithms
• Accelerating inference for stochastic kinetic models
• Optimal scaling for the pseudo-marginal random walk Metropolis: insensitivity to the noise generating mechanism
• Stability of noisy Metropolis-Hastings
• Langevin diffusion for population based sampling with an application in Bayesian inference for pharmacodynamics
• Introduction to ``Particle Metropolis-Hastings using gradient and Hessian information by J. Dahlin, F. Lindsten, T. Schön

This page was built for publication: Particle Metropolis-adjusted Langevin algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5384403)