Abstract
We use Stein’s method to bound the Wasserstein distance of order 2 between a measure \(\nu \) and the Gaussian measure using a stochastic process \((X_t)_{t \ge 0}\) such that \(X_t\) is drawn from \(\nu \) for any \(t > 0\). If the stochastic process \((X_t)_{t \ge 0}\) satisfies an additional exchangeability assumption, we show it can also be used to obtain bounds on Wasserstein distances of any order \(p \ge 1\). Using our results, we provide convergence rates for the multi-dimensional central limit theorem in terms of Wasserstein distances of any order \(p \ge 2\) under simple moment assumptions.
Similar content being viewed by others
References
Bakry, D., Gentil, I., Ledoux, M.: Analysis and Geometry of Markov Diffusion Operators. Grundlehren der mathematischen Wissenschaften, vol. 348. Springer, Berlin (2014)
Bobkov, S.G.: Entropic approach to E. Rio’s central limit theorem for W2 transport distance. Stat. Probab. Lett. 83(7), 1644–1648 (2013)
Courtade, T.A., Fathi, M., Pananjady, A.: Existence of Stein Kernels under a Spectral Gap, and Discrepancy Bound. ArXiv e-prints (2017)
Eldan, R., Mikulincer, D., Zhai, A.: The CLT in high dimensions: quantitative bounds via martingale embedding. ArXiv e-prints (2018)
Fathi, M.: Stein kernels and moment maps. ArXiv e-prints (2018)
Goldstein, L., Reinert, G.: Stein’s method and the zero bias transformation with application to simple random sampling. Ann. Appl. Probab. 7(4), 935–952 (1997)
Goldstein, L., Rinott, Y.: Multivariate normal approximations by Stein’s method and size bias couplings. J. Appl. Probab. 33, 1–17 (1996)
Ledoux, M., Nourdin, I., Peccati, G.: Stein’s method, logarithmic sobolev and transport inequalities. Geometric Funct. Anal. 25(1), 256–306 (2015)
Otto, F., Villani, C.: Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality. J. Funct. Anal. 173(2), 361–400 (2000)
Pinelis, I.: Optimum bounds for the distributions of martingales in banach spaces. Ann. Probab. 22(4), 1679–1706 (1994)
Reinert, G., Röllin, A.: Multivariate normal approximation with Stein’s method of exchangeable pairs under a general linearity condition. Ann. Probab. 37(6), 2150–2173 (2009)
Rio, E.: Upper bounds for minimal distances in the central limit theorem. Ann. Inst. H. Poincaré Probab. Statist. 45(3), 802–817 (2009)
Röllin, A.: A note on the exchangeability condition in Stein’s method. Stat. Probab. Lett. 78(13), 1800–1806 (2008)
Stein, C.: A bound for the error in the normal approximation to the distribution of a sum of dependent random variables. In: Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability, Volume 2: Probability Theory, pp. 583–602. University of California Press, Berkeley (1972)
Villani, C.: Optimal Transport: Old and New. Grundlehren der mathematischen Wissenschaften. Springer, Berlin (2009)
Wang, F.Y.: Probability distance inequalities on riemannian manifolds and path spaces. J. Funct. Anal. 206(1), 167–190 (2004)
Zhai, A.: A high-dimensional CLT in W2 distance with near optimal convergence rate. Probab. Theory Related Fields 170, 1–25 (2018)
Acknowledgements
The author would like to thank Michel Ledoux for his many comments and advice regarding the redaction of this paper as well as Jérôme Dedecker, Yvik Swan, Frédéric Chazal and anonymous reviewers for their multiple remarks.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The author was supported by the French Délégation Générale de l’Armement (DGA) and by ANR project TopData ANR-13-BS01-0008.
Rights and permissions
About this article
Cite this article
Bonis, T. Stein’s method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem. Probab. Theory Relat. Fields 178, 827–860 (2020). https://doi.org/10.1007/s00440-020-00989-4
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00440-020-00989-4