Nonasymptotic bounds on the estimation error of MCMC algorithms

DOI10.3150/12-BEJ442zbMath1412.60110arXiv1106.4739OpenAlexW3099337807WikidataQ96748970 ScholiaQ96748970MaRDI QIDQ2435233

Wojciech Niemiro, Krzysztof Łatuszyński, Błażej Miasojedow

Publication date: 4 February 2014

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1106.4739

zbMATH Keywords

asymptotic variancemean square errorgeometric ergodicitypolynomial ergodicityregenerationcomputable boundsconfidence estimationdrift conditions

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Monte Carlo methods (65C05)

Related Items

Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms, Markov Kernels Local Aggregation for Noise Vanishing Distribution Sampling, Rare Event Simulation Using Reversible Shaking Transformations, Information geometry approach to parameter estimation in Markov chains, Hit-and-Run for Numerical Integration, Geometric ergodicity of a more efficient conditional Metropolis-Hastings algorithm, Nonasymptotic Bounds on the Mean Square Error for MCMC Estimates via Renewal Techniques, On a Metropolis-Hastings importance sampling estimator, Orlicz Integrability of Additive Functionals of Harris Ergodic Markov Chains, Complexity results for MCMC derived from quantitative bounds, Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings, Dimension‐independent Markov chain Monte Carlo on the sphere, On the convergence time of some non-reversible Markov chain Monte Carlo methods, Multilevel Monte Carlo Estimation of the Expected Value of Sample Information, Markov chain Monte Carlo estimation of quantiles, Exponential concentration inequalities for additive functionals of Markov chains, Convergence analysis of a collapsed Gibbs sampler for Bayesian vector autoregressions, Convergence complexity analysis of Albert and Chib's algorithm for Bayesian probit regression, A hybrid scan Gibbs sampler for Bayesian models with latent variables, A weighted discrepancy bound of quasi-Monte Carlo importance sampling, Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings, Unnamed Item, Computation of Expectations by Markov Chain Monte Carlo Methods, Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms, Error bounds of MCMC for functions with unbounded stationary variance

Cites Work

• Unnamed Item
• Quantitative non-geometric convergence bounds for independence samplers
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Rigorous confidence bounds for MCMC under a geometric drift condition
• Markov chains and stochastic stability
• Bounds on regeneration times and limit theorems for subgeometric Markov chains
• On Monte Carlo methods for Bayesian multivariate regression models with heavy-tailed errors
• General state space Markov chains and MCMC algorithms
• Explicit error bounds for lazy reversible Markov chain Monte Carlo
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• Random generation of combinatorial structures from a uniform distribution
• Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
• Computable bounds for geometric convergence rates of Markov chains
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains
• Convergence of the Monte Carlo expectation maximization for curved exponential families.
• \(V\)-subgeometric ergodicity for a Hastings-Metropolis algorithm
• Bounds on regeneration times and convergence rates for Markov chains
• Moment and probability inequalities for sums of bounded additive functionals of regular Markov chains via the Nummelin splitting technique
• Hoeffding's inequality for uniformly ergodic Markov chains
• Quantitative bounds on convergence of time-inhomogeneous Markov chains
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Quantitative convergence rates of Markov chains: A simple account
• Polynomial convergence rates of Markov chains
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• Optimal Hoeffding bounds for discrete reversible Markov chains.
• Practical drift conditions for subgeometric rates of convergence.
• Sufficient burn-in for Gibbs samplers for a hierarchical random effects model.
• Markov chains for exploring posterior distributions. (With discussion)
• Rates of convergence for Gibbs sampling for variance component models
• A measure concentration inequality for contracting Markov chains
• Gibbs sampling for a Bayesian hierarchical general linear model
• Simple Monte Carlo and the Metropolis algorithm
• Computable convergence rates for sub-geometric ergodic Markov chains
• Stability of the Gibbs sampler for Bayesian hierarchical models
• Concentration inequalities for dependent random variables via the martingale method
• Polynomial ergodicity of Markov transition kernels.
• SMALL AND PSEUDO-SMALL SETS FOR MARKOV CHAINS
• Sharp Bounds for the Tails of Functionals of Markov Chains
• On the Markov Chain Simulation Method for Uniform Combinatorial Distributions and Simulated Annealing
• Fixed-Width Output Analysis for Markov Chain Monte Carlo
• Sampling-Based Approaches to Calculating Marginal Densities
• A splitting technique for Harris recurrent Markov chains
• A New Approach to the Limit Theory of Recurrent Markov Chains
• A Chernoff Bound for Random Walks on Expander Graphs
• On the geometric ergodicity of hybrid samplers
• MC's for MCMC'ists
• Regeneration in Markov Chain Samplers
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Geometric Convergence Rates for Stochastically Ordered Markov Chains
• Fixed Precision MCMC Estimation by Median of Products of Averages
• Nonasymptotic Bounds on the Mean Square Error for MCMC Estimates via Renewal Techniques
• Geometric Ergodicity of van Dyk and Meng's Algorithm for the Multivariate Student'stModel
• On Excess Over the Boundary
• A regeneration proof of the central limit theorem for uniformly ergodic Markov chains