Constructing Sampling Schemes via Coupling: Markov Semigroups and Optimal Transport

DOI10.1137/18M119896XzbMATH Open1454.60118arXiv1806.11026OpenAlexW2963521170WikidataQ128175677 ScholiaQ128175677MaRDI QIDQ5228360FDOQ5228360

Nikolas Nüsken, G. A. Pavliotis

Publication date: 12 August 2019

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Abstract: In this paper we develop a general framework for constructing and analysing coupled Markov chain Monte Carlo samplers, allowing for both (possibly degenerate) diffusion and piecewise deterministic Markov processes. For many performance criteria of interest, including the asymptotic variance, the task of finding efficient couplings can be phrased in terms of problems related to optimal transport theory. We investigate general structural properties, proving a singularity theorem that has both geometric and probabilistic interpretations. Moreover, we show that those problems can often be solved approximately and support our findings with numerical experiments. For the particular objective of estimating the variance of a Bayesian posterior, our analysis suggests using novel techniques in the spirit of antithetic variates. Addressing the convergence to equilibrium of coupled processes we furthermore derive a modified Poincar'e inequality.

Full work available at URL: https://arxiv.org/abs/1806.11026

zbMATH Keywords

samplingMCMCoptimal transportMarkov semigroupsparticle methods

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Markov semigroups and applications to diffusion processes (47D07) Transition functions, generators and resolvents (60J35) Stochastic particle methods (65C35) PDEs in connection with statistics (35Q62)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Ensemble preconditioning for Markov chain Monte Carlo simulation
• Multiprocess parallel antithetic coupling for backward and forward Markov chain Monte Carlo
• Optimal Transport
• Stochastic differential equations. An introduction with applications.
• The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
• The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
• Markov chain Monte Carlo and irreversibility
• Particle Markov Chain Monte Carlo for Efficient Numerical Simulation
• One-Parameter Semigroups for Linear Evolution Equations
• One-parameter semigroups of positive operators
• A Liapounov bound for solutions of the Poisson equation
• Pseudo differential operators and Markov processes. In 3 vol. Vol. 1: Fourier analysis and semigroups
• Ergodicity for Infinite Dimensional Systems
• On the functional central limit theorem and the law of the iterated logarithm for Markov processes
• Eigenvalues, Inequalities, and Ergodic Theory
• Analysis and Geometry of Markov Diffusion Operators
• Accelerating diffusions
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Reflection couplings and contraction rates for diffusions
• Mean field simulation for Monte Carlo integration
• Variance reduction using nonreversible Langevin samplers
• Handbook of Monte Carlo Methods
• Control Variates for Estimation Based on Reversible Markov Chain Monte Carlo Samplers
• Stochastic Processes and Applications
• Fluctuations in Markov Processes
• Rectifiability of optimal transportation plans
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• Spectral methods for Langevin dynamics and associated error estimates
• Partial differential equations and stochastic methods in molecular dynamics
• Recurrence and invariant measures for degenerate diffusions
• Lévy matters III. Lévy-type processes: construction, approximation and sample path properties
• Improving the convergence of reversible samplers
• Density Functional Theory and Optimal Transportation with Coulomb Cost
• Conservativeness and extensions of Feller semigroups
• Antithetic coupling of two Gibbs sampler chains.
• Parallel hierarchical sampling: a general-purpose interacting Markov chains Monte Carlo algorithm
• Multilevel Monte Carlo Methods
• Randomized Hamiltonian Monte Carlo
• A consensus-based model for global optimization and its mean-field limit
• Introduction to Uncertainty Quantification
• Coupling control variates for Markov chain Monte Carlo
• Handbook of Uncertainty Quantification
• Exact estimation for Markov chain equilibrium expectations
• Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions
• Invariant measure of duplicated diffusions and application to Richardson-Romberg extrapolation
• Piecewise deterministic Markov processes and their invariant measures
• On tensor products of Banach spaces
• Studying Convergence of Markov Chain Monte Carlo Algorithms Using Coupled Sample Paths
• Computation of sensitivities for the invariant measure of a parameter dependent diffusion
• Piecewise deterministic Markov processes for continuous-time Monte Carlo
• Limit theorems for the zig-zag process
• On the Poisson equation for Metropolis-Hastings chains
• Probabilistic Forecasting and Bayesian Data Assimilation
• Lévy matters VI. Lévy-type processes: moments, construction and heat kernel estimates
• Coupling and convergence for Hamiltonian Monte Carlo
• Unbiased Hamiltonian Monte Carlo with couplings
• Ergodicity of the zigzag process
• A Coupling-Regeneration Scheme for Diagnosing Convergence in Markov Chain Monte Carlo Algorithms
• Gibbs Flow for Approximate Transport with Applications to Bayesian Computation

Cited In (1)

• Nonasymptotic bounds for sampling algorithms without log-concavity

Uses Software

• EnsembleQN

This page was built for publication: Constructing Sampling Schemes via Coupling: Markov Semigroups and Optimal Transport

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5228360)