Error bounds of MCMC for functions with unbounded stationary variance
arXiv:1312.4344 · doi:10.1016/j.spl.2014.07.035
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 so that the functions have finite -norm. For uniformly ergodic Markov chains we obtain error bounds with the optimal order of convergence 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.
arXiv comment13 pages
References in corpus (8)
- MCMC using Hamiltonian dynamics
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Explicit error bounds for Markov chain Monte Carlo
- On the Computational Complexity of MCMC-based Estimators in Large Samples
- Explicit error bounds for lazy reversible Markov Chain Monte Carlo
- Nonasymptotic bounds on the estimation error of MCMC algorithms
- Positivity of hit-and-run and related algorithms
- Rigorous confidence bounds for MCMC under a geometric drift condition