Rates in the Central Limit Theorem and diffusion approximation via Stein's Method
Abstract
We present a way to use Stein's method in order to bound the Wasserstein distance of order between two measures and supported on such that is the reversible measure of a diffusion process. In order to apply our result, we only require to have access to a stochastic process such that is drawn from for any . We then show that, whenever is the Gaussian measure , one can use a slightly different approach to bound the Wasserstein distances of order between and under an additional exchangeability assumption on the stochastic process . Using our results, we are able to obtain convergence rates for the multi-dimensional Central Limit Theorem in terms of Wasserstein distances of order . Our results can also provide bounds for steady-state diffusion approximation, allowing us to tackle two problems appearing in the field of data analysis by giving a quantitative convergence result for invariant measures of random walks on random geometric graphs and by providing quantitative guarantees for a Monte Carlo sampling algorithm.
Cite
@article{arxiv.1506.06966,
title = {Rates in the Central Limit Theorem and diffusion approximation via Stein's Method},
author = {Thomas Bonis},
journal= {arXiv preprint arXiv:1506.06966},
year = {2018}
}