تقرير
Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations
| العنوان: | Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations |
|---|---|
| المؤلفون: | Medina-Aguayo, Felipe, Rudolf, Daniel, Schweizer, Nikolaus |
| سنة النشر: | 2018 |
| المجموعة: | Computer Science Mathematics Statistics |
| مصطلحات موضوعية: | Statistics - Computation, Mathematics - Numerical Analysis, Mathematics - Probability |
| الوصف: | The Monte Carlo within Metropolis (MCwM) algorithm, interpreted as a perturbed Metropolis-Hastings (MH) algorithm, provides an approach for approximate sampling when the target distribution is intractable. Assuming the unperturbed Markov chain is geometrically ergodic, we show explicit estimates of the difference between the n-th step distributions of the perturbed MCwM and the unperturbed MH chains. These bounds are based on novel perturbation results for Markov chains which are of interest beyond the MCwM setting. To apply the bounds, we need to control the difference between the transition probabilities of the two chains and to verify stability of the perturbed chain. |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1016/j.spa.2019.06.015 |
| URL الوصول: | http://arxiv.org/abs/1809.09547 |
| رقم الأكسشن: | edsarx.1809.09547 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1016/j.spa.2019.06.015 |
|---|