Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms

DOI10.1214/14-AAP1022zbMath1326.65012arXiv1210.1484OpenAlexW3098713583WikidataQ109998341 ScholiaQ109998341MaRDI QIDQ2341639

Christophe Andrieu, Matti Vihola

Publication date: 27 April 2015

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

Full work available at URL: https://arxiv.org/abs/1210.1484

zbMATH Keywords

weightsMarkov chain Monte Carlo methodconvergence ratecentral limit theoremasymptotic variancerandom walkMarkov kernelMetropolis-Hastings algorithmgeometric ergodicitypolynomial ergodicitypseudo-marginal algorithmmarginal algorithm

Mathematics Subject Classification ID

Related Items (40)

Which ergodic averages have finite asymptotic variance? ⋮ Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems ⋮ On the theoretical properties of the exchange algorithm ⋮ Exact convergence analysis of the independent Metropolis-Hastings algorithms ⋮ Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels ⋮ The Alive Particle Filter and Its Use in Particle Markov Chain Monte Carlo ⋮ The node-wise pseudo-marginal method: model selection with spatial dependence on latent graphs ⋮ Penalised t-walk MCMC ⋮ Stability of noisy Metropolis-Hastings ⋮ Quantitative Convergence Rates for Subgeometric Markov Chains ⋮ Uniform Ergodicity of the Particle Gibbs Sampler ⋮ A unified performance analysis of likelihood-informed subspace methods ⋮ Efficient inference for nonlinear state space models: an automatic sample size selection rule ⋮ Reflections on Bayesian inference and Markov chain Monte Carlo ⋮ Unbiased Markov chain Monte Carlo for intractable target distributions ⋮ Finding our way in the dark: approximate MCMC for approximate Bayesian methods ⋮ Accelerating Metropolis-within-Gibbs sampler with localized computations of differential equations ⋮ Metropolis–Hastings via Classification ⋮ Bayesian model calibration for diblock copolymer thin film self-assembly using power spectrum of microscopy data and machine learning surrogate ⋮ Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance ⋮ The importance Markov chain ⋮ On coupling particle filter trajectories ⋮ Barker's algorithm for Bayesian inference with intractable likelihoods ⋮ Sequential Monte Carlo as approximate sampling: bounds, adaptive resampling via \(\infty\)-ESS, and an application to particle Gibbs ⋮ A framework for adaptive MCMC targeting multimodal distributions ⋮ Comparison of asymptotic variances of inhomogeneous Markov chains with application to Markov chain Monte Carlo methods ⋮ Twisted particle filters ⋮ Bayesian model comparison with un-normalised likelihoods ⋮ Approximate Inference for Observation-Driven Time Series Models with Intractable Likelihoods ⋮ Particle Metropolis-Hastings using gradient and Hessian information ⋮ Bayesian computation: a summary of the current state, and samples backwards and forwards ⋮ On particle Gibbs sampling ⋮ Peskun-Tierney ordering for Markovian Monte Carlo: beyond the reversible scenario ⋮ Product-form estimators: exploiting independence to scale up Monte Carlo ⋮ Informed sub-sampling MCMC: approximate Bayesian inference for large datasets ⋮ On the efficiency of pseudo-marginal random walk Metropolis algorithms ⋮ Data-free likelihood-informed dimension reduction of Bayesian inverse problems ⋮ Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms ⋮ Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC ⋮ Bayesian estimation of long-run risk models using sequential Monte Carlo

Cites Work

• Unnamed Item
• Unnamed Item
• The pseudo-marginal approach for efficient Monte Carlo computations
• Establishing some order amongst exact approximations of MCMCs
• On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
• Markov chains and stochastic stability
• Variance bounding Markov chains
• A note on Metropolis-Hastings kernels for general state spaces
• Geometric ergodicity and hybrid Markov chains
• Geometric ergodicity of Metropolis algorithms
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Polynomial convergence rates of Markov chains
• Practical drift conditions for subgeometric rates of convergence.
• Rates of convergence of the Hastings and Metropolis algorithms
• Nonlocal Monte Carlo algorithm for self-avoiding walks with fixed endpoints.
• Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
• The spectrum of the independent Metropolis-Hastings algorithm
• Nonasymptotic bounds on the estimation error of MCMC algorithms
• Markovian stochastic approximation with expanding projections
• Computable convergence rates for sub-geometric ergodic Markov chains
• Quantitative Convergence Rates for Subgeometric Markov Chains
• Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation
• Optimum Monte-Carlo sampling using Markov chains
• Particle Markov Chain Monte Carlo for Efficient Numerical Simulation
• Exact and Computationally Efficient Likelihood-Based Estimation for Discretely Observed Diffusion Processes (with Discussion)
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• MC's for MCMC'ists
• Monte Carlo sampling methods using Markov chains and their applications

This page was built for publication: Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms