A vanilla Rao-Blackwellization of Metropolis-Hastings algorithms
From MaRDI portal
Publication:2429930
Abstract: Casella and Robert [Biometrika 83 (1996) 81--94] presented a general Rao--Blackwellization principle for accept-reject and Metropolis--Hastings schemes that leads to significant decreases in the variance of the resulting estimators, but at a high cost in computation and storage. Adopting a completely different perspective, we introduce instead a universal scheme that guarantees variance reductions in all Metropolis--Hastings-based estimators while keeping the computation cost under control. We establish a central limit theorem for the improved estimators and illustrate their performances on toy examples and on a probit model estimation.
Recommendations
- Rao–Blackwellisation in the Markov Chain Monte Carlo Era
- Markov chain Monte Carlo and Rao-Blackwellization
- Rao-Blackwellisation of sampling schemes
- Rao-Blackwellization of Particle Markov Chain Monte Carlo Methods Using Forward Filtering Backward Sampling
- Metropolis-Hastings algorithms with acceptance ratios of nearly 1
- On variance stabilisation in population Monte Carlo by double Rao-Blackwellisation
- A modified conditional Metropolis-Hastings sampler
- Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
Cites work
- Beyond accept-reject sampling
- Does waste recycling really improve the multi-proposal Metropolis-Hastings algorithm? An analysis based on control variates
- scientific article; zbMATH DE number 5133222 (Why is no real title available?)
- Limit theorems for weighted samples with applications to sequential Monte Carlo methods
- On convergence of properly weighted samples to the target distribution
- Rao-Blackwellisation of sampling schemes
- Self-regenerative Markov chain Monte Carlo with adaptation
- Statistical Analysis of Financial Data in S-Plus
Cited in
(20)- On parallelizable Markov chain Monte Carlo algorithms with waste-recycling
- Which ergodic averages have finite asymptotic variance?
- Efficient estimation of the link function parameter in a robust Bayesian binary regression model
- On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
- Markov chain Monte Carlo and Rao-Blackwellization
- Jump Markov chains and rejection-free Metropolis algorithms
- On a Metropolis-Hastings importance sampling estimator
- Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
- Sampling constrained probability distributions using spherical augmentation
- Rao-Blackwellisation of sampling schemes
- scientific article; zbMATH DE number 2148859 (Why is no real title available?)
- Beyond accept-reject sampling
- Markov Chain Importance Sampling—A Highly Efficient Estimator for MCMC
- Bayesian computation: a summary of the current state, and samples backwards and forwards
- Optimization via rejection-free partial neighbor search
- Rao–Blackwellisation in the Markov Chain Monte Carlo Era
- The importance Markov chain
- Computing Bayes: from then `til now
- Variance reduction of estimators arising from Metropolis-Hastings algorithms
- On variance stabilisation in population Monte Carlo by double Rao-Blackwellisation
This page was built for publication: A vanilla Rao-Blackwellization of Metropolis-Hastings algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2429930)
