Error bounds of MCMC for functions with unbounded stationary variance

DOI10.1016/J.SPL.2014.07.035MaRDI QIDQ2344860zbMATH OpenOpenAlexFDO

Authors Daniel Rudolf, Nikolaus Schweizer

Publication date 18 May 2015

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1312.4344

zbMATH Keywords

absolute mean errorMarkov chain Monte Carlo methodsspectral gapuniform ergodicity

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

Abstract: We prove explicit error bounds for Markov chain Monte Carlo (MCMC) methods to compute expectations of functions with unbounded stationary variance. We assume that there is a $pin(1,2)$ so that the functions have finite $L_p$-norm. For uniformly ergodic Markov chains we obtain error bounds with the optimal order of convergence $n^{1/p-1}$ and if there exists a spectral gap we almost get the optimal order. Further, a burn-in period is taken into account and a recipe for choosing the burn-in is provided.

Recommendations

• Nonasymptotic bounds on the estimation error of MCMC algorithms
• Explicit error bounds for Markov chain Monte Carlo
• Error bounds for computing the expectation by Markov chain Monte Carlo
• Non-asymptotic error bounds for sequential MCMC methods
• Nonasymptotic bounds on the mean square error for MCMC estimates via renewal techniques
• Error bounds and normalising constants for sequential Monte Carlo samplers in high dimensions
• Error bounds for sequential Monte Carlo samplers for multimodal distributions
• Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions

Cites work

• A new proof of convergence of MCMC via the ergodic theorem
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Deterministic and stochastic error bounds in numerical analysis
• Explicit error bounds for lazy reversible Markov chain Monte Carlo
• Explicit error bounds for Markov chain Monte Carlo
• scientific article; zbMATH DE number 192914 (Why is no real title available?)
• scientific article; zbMATH DE number 515830 (Why is no real title available?)
• Implementing MCMC: estimating with confidence
• Limit theorems for some functionals with heavy tails of a discrete time Markov chain
• Markov chains and stochastic stability
• Nonasymptotic bounds on the estimation error of MCMC algorithms
• On the computational complexity of MCMC-based estimators in large samples
• On the Markov chain central limit theorem
• Rigorous confidence bounds for MCMC under a geometric drift condition

Cited in

(14)

• Solvable integration problems and optimal sample size selection
• Optimal confidence for Monte Carlo integration of smooth functions
• Perturbation bounds and degree of imprecision for uniquely convergent imprecise Markov chains
• Nonasymptotic bounds on the estimation error of MCMC algorithms
• Explicit error bounds for Markov chain Monte Carlo
• Error bounds for computing the expectation by Markov chain Monte Carlo
• A Strong Law of Large Numbers for Scrambled Net Integration
• Computation of expectations by Markov chain Monte Carlo methods
• Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms
• Dimension‐independent Markov chain Monte Carlo on the sphere
• Rigorous confidence bounds for MCMC under a geometric drift condition
• Optimal convergence rates of MCMC integration for functions with unbounded second moment
• On the particle approximation of lagged Feynman-Kac formulae
• Explicit error bounds for lazy reversible Markov chain Monte Carlo

This page was built for publication: Error bounds of MCMC for functions with unbounded stationary variance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2344860)