中文

Error bounds for simultaneous Wasserstein contractive adaptive increasingly rare MCMC

统计理论 2026-06-29 v1 概率论 统计计算

摘要

We investigate adaptive increasingly rare Markov chain Monte Carlo algorithms and the associated time-average estimator for approximating expectations. Under a simultaneous Wasserstein contraction assumption on the underlying family of Markov kernels we derive explicit bounds for the mean squared error. We illustrate the applicability of our estimate through adaptive stereographic algorithms and Metropolis-Hastings schemes that employ normalizing flows for adaptation. We also consider a generic adaptive algorithm for doubly intractable problems and provide a corresponding cost analysis to achieve a desired precision.

引用

@article{arxiv.2606.30018,
  title  = {Error bounds for simultaneous Wasserstein contractive adaptive increasingly rare MCMC},
  author = {Julian Hofstadler and Daniel Rudolf},
  journal= {arXiv preprint arXiv:2606.30018},
  year   = {2026}
}

备注

33 pages