Nonasymptotic bounds on the estimation error of MCMC algorithms
From MaRDI portal
Publication:2435233
DOI10.3150/12-BEJ442zbMATH Open1412.60110arXiv1106.4739OpenAlexW3099337807WikidataQ96748970 ScholiaQ96748970MaRDI QIDQ2435233FDOQ2435233
Wojciech Niemiro, Krzysztof Łatuszyński, Błażej Miasojedow
Publication date: 4 February 2014
Published in: Bernoulli (Search for Journal in Brave)
Abstract: We address the problem of upper bounding the mean square error of MCMC estimators. Our analysis is nonasymptotic. We first establish a general result valid for essentially all ergodic Markov chains encountered in Bayesian computation and a possibly unbounded target function . The bound is sharp in the sense that the leading term is exactly , where is the CLT asymptotic variance. Next, we proceed to specific additional assumptions and give explicit computable bounds for geometrically and polynomially ergodic Markov chains under quantitative drift conditions. As a corollary, we provide results on confidence estimation.
Full work available at URL: https://arxiv.org/abs/1106.4739
Recommendations
- Error bounds of MCMC for functions with unbounded stationary variance
- Rigorous confidence bounds for MCMC under a geometric drift condition
- Explicit error bounds for Markov chain Monte Carlo
- Nonasymptotic bounds on the mean square error for MCMC estimates via renewal techniques
- Explicit error bounds for lazy reversible Markov chain Monte Carlo
asymptotic variancemean square errorregenerationgeometric ergodicitycomputable boundsconfidence estimationpolynomial ergodicitydrift conditions
Computational methods in Markov chains (60J22) Bayesian inference (62F15) Monte Carlo methods (65C05)
Cites Work
- Markov chains for exploring posterior distributions. (With discussion)
- Sampling-Based Approaches to Calculating Marginal Densities
- On the geometric ergodicity of hybrid samplers
- Title not available (Why is that?)
- MC's for MCMC'ists
- Markov chains and stochastic stability
- General state space Markov chains and MCMC algorithms
- Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
- Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains
- Polynomial convergence rates of Markov chains
- Sufficient burn-in for Gibbs samplers for a hierarchical random effects model.
- Gibbs sampling for a Bayesian hierarchical general linear model
- Stability of the Gibbs sampler for Bayesian hierarchical models
- Fixed-Width Output Analysis for Markov Chain Monte Carlo
- Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
- Nonasymptotic Bounds on the Mean Square Error for MCMC Estimates via Renewal Techniques
- Rigorous confidence bounds for MCMC under a geometric drift condition
- Random generation of combinatorial structures from a uniform distribution
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- Computable bounds for geometric convergence rates of Markov chains
- Bounds on regeneration times and convergence rates for Markov chains
- Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
- Geometric Convergence Rates for Stochastically Ordered Markov Chains
- Convergence of the Monte Carlo expectation maximization for curved exponential families.
- Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
- A splitting technique for Harris recurrent Markov chains
- Fixed Precision MCMC Estimation by Median of Products of Averages
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- On Monte Carlo methods for Bayesian multivariate regression models with heavy-tailed errors
- Explicit error bounds for lazy reversible Markov chain Monte Carlo
- A measure concentration inequality for contracting Markov chains
- Polynomial ergodicity of Markov transition kernels.
- Optimal Hoeffding bounds for discrete reversible Markov chains.
- Quantitative convergence rates of Markov chains: A simple account
- Sharp Bounds for the Tails of Functionals of Markov Chains
- A Chernoff Bound for Random Walks on Expander Graphs
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Concentration inequalities for dependent random variables via the martingale method
- A New Approach to the Limit Theory of Recurrent Markov Chains
- Regeneration in Markov Chain Samplers
- On Excess Over the Boundary
- Hoeffding's inequality for uniformly ergodic Markov chains
- Quantitative bounds on convergence of time-inhomogeneous Markov chains
- Rates of convergence for Gibbs sampling for variance component models
- On the Markov Chain Simulation Method for Uniform Combinatorial Distributions and Simulated Annealing
- SMALL AND PSEUDO-SMALL SETS FOR MARKOV CHAINS
- Geometric Ergodicity of van Dyk and Meng's Algorithm for the Multivariate Student'stModel
- Practical drift conditions for subgeometric rates of convergence.
- Moment and probability inequalities for sums of bounded additive functionals of regular Markov chains via the Nummelin splitting technique
- Bounds on regeneration times and limit theorems for subgeometric Markov chains
- \(V\)-subgeometric ergodicity for a Hastings-Metropolis algorithm
- Computable convergence rates for sub-geometric ergodic Markov chains
- Quantitative non-geometric convergence bounds for independence samplers
- Simple Monte Carlo and the Metropolis algorithm
- A regeneration proof of the central limit theorem for uniformly ergodic Markov chains
Cited In (26)
- A weighted discrepancy bound of quasi-Monte Carlo importance sampling
- Markov Kernels Local Aggregation for Noise Vanishing Distribution Sampling
- Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
- Convergence analysis of a collapsed Gibbs sampler for Bayesian vector autoregressions
- On a Metropolis-Hastings importance sampling estimator
- Title not available (Why is that?)
- Error bounds of MCMC for functions with unbounded stationary variance
- A hybrid scan Gibbs sampler for Bayesian models with latent variables
- Hit-and-Run for Numerical Integration
- Information geometry approach to parameter estimation in Markov chains
- Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
- Exponential concentration inequalities for additive functionals of Markov chains
- Computation of Expectations by Markov Chain Monte Carlo Methods
- Multilevel Monte Carlo Estimation of the Expected Value of Sample Information
- Orlicz Integrability of Additive Functionals of Harris Ergodic Markov Chains
- Rare Event Simulation Using Reversible Shaking Transformations
- Convergence complexity analysis of Albert and Chib's algorithm for Bayesian probit regression
- Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings
- Geometric ergodicity of a more efficient conditional Metropolis-Hastings algorithm
- Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors
- Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms
- Complexity results for MCMC derived from quantitative bounds
- Dimension‐independent Markov chain Monte Carlo on the sphere
- On the convergence time of some non-reversible Markov chain Monte Carlo methods
- Markov chain Monte Carlo estimation of quantiles
- Nonasymptotic Bounds on the Mean Square Error for MCMC Estimates via Renewal Techniques
This page was built for publication: Nonasymptotic bounds on the estimation error of MCMC algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2435233)
