Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions

DOI10.1214/11-AAP828zbMath1272.60053arXiv1103.0542MaRDI QIDQ1931320

Natesh S. Pillai, Andrew M. Stuart, Alexandre H. Thiery

Publication date: 25 January 2013

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

Full work available at URL: https://arxiv.org/abs/1103.0542

zbMATH Keywords

diffusion approximationMarkov chain Monte Carloscaling limitmetropolis-adjusted Langevin algorithm

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items (34)

Asymptotic analysis of the random walk metropolis algorithm on ridged densities ⋮ Designing simple and efficient Markov chain Monte Carlo proposal kernels ⋮ An adaptive multiple-try Metropolis algorithm ⋮ Proximal Markov chain Monte Carlo algorithms ⋮ Dimension-independent likelihood-informed MCMC ⋮ Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction ⋮ Unnamed Item ⋮ On sampling from a log-concave density using kinetic Langevin diffusions ⋮ Sampling Constrained Probability Distributions Using Spherical Augmentation ⋮ Optimal scaling of the MALA algorithm with irreversible proposals for Gaussian targets ⋮ Optimal scaling of random-walk Metropolis algorithms on general target distributions ⋮ Efficient and generalizable tuning strategies for stochastic gradient MCMC ⋮ Optimal tuning of the hybrid Monte Carlo algorithm ⋮ A Bayesian Approach to Estimating Background Flows from a Passive Scalar ⋮ Multimodal, high-dimensional, model-based, Bayesian inverse problems with applications in biomechanics ⋮ Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions ⋮ Optimal scaling for the transient phase of Metropolis Hastings algorithms: the longtime behavior ⋮ Noisy gradient flow from a random walk in Hilbert space ⋮ Bayesian Inference Using Intermediate Distribution Based on Coarse Multiscale Model for Time Fractional Diffusion Equations ⋮ Study of new rare event simulation schemes and their application to extreme scenario generation ⋮ On the stability of sequential Monte Carlo methods in high dimensions ⋮ Asymptotic variance for random walk Metropolis chains in high dimensions: logarithmic growth via the Poisson equation ⋮ A function space HMC algorithm with second order Langevin diffusion limit ⋮ Bayesian computation: a summary of the current state, and samples backwards and forwards ⋮ Randomize-Then-Optimize for Sampling and Uncertainty Quantification in Electrical Impedance Tomography ⋮ MCMC methods for functions: modifying old algorithms to make them faster ⋮ Non-asymptotic guarantees for sampling by stochastic gradient descent ⋮ Some Remarks on Preconditioning Molecular Dynamics ⋮ Accelerated Dimension-Independent Adaptive Metropolis ⋮ Non-stationary phase of the MALA algorithm ⋮ Diffusion limit for the random walk Metropolis algorithm out of stationarity ⋮ On the efficiency of pseudo-marginal random walk Metropolis algorithms ⋮ Stochastic Gradient Markov Chain Monte Carlo ⋮ Optimal scaling for the transient phase of the random walk Metropolis algorithm: the mean-field limit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Besov priors for Bayesian inverse problems
• Hybrid Monte Carlo on Hilbert spaces
• The random walk Metropolis: linking theory and practice through a case study
• Asymptotic behaviour of a class of stochastic approximation procedures
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling for various Metropolis-Hastings algorithms.
• From Metropolis to diffusions: Gibbs states and optimal scaling.
• Optimal scaling of MaLa for nonlinear regression.
• Discretization-invariant Bayesian inversion and Besov space priors
• Optimal scalings for local Metropolis-Hastings chains on nonproduct targets in high dimensions
• Optimal tuning of the hybrid Monte Carlo algorithm
• Weak convergence of Metropolis algorithms for non-I.I.D. target distributions
• Analysis of SPDEs arising in path sampling. II: The nonlinear case
• Analysis of SPDEs arising in path sampling. I: The Gaussian case
• Sparse deterministic approximation of Bayesian inverse problems
• Inverse problems: A Bayesian perspective
• MCMC METHODS FOR DIFFUSION BRIDGES
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Scaling Limits for the Transient Phase of Local Metropolis–Hastings Algorithms
• Stochastic Equations in Infinite Dimensions

This page was built for publication: Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions