English

Error bounds for Approximations of Markov chains used in Bayesian Sampling

Probability 2018-07-09 v2

Abstract

We give a number of results on approximations of Markov kernels in total variation and Wasserstein norms weighted by a Lyapunov function. The results are applied to examples from Bayesian statistics where approximations to transition kernels are made to reduce computational costs.

Keywords

Cite

@article{arxiv.1711.05382,
  title  = {Error bounds for Approximations of Markov chains used in Bayesian Sampling},
  author = {James E. Johndrow and Jonathan C. Mattingly},
  journal= {arXiv preprint arXiv:1711.05382},
  year   = {2018}
}
R2 v1 2026-06-22T22:46:19.056Z