Electronic Communications in Probability

Multivariate Stein factors for a class of strongly log-concave distributions

Lester Mackey and Jackson Gorham

Full-text: Open access


We establish uniform bounds on the low-order derivatives of Stein equation solutions for a broad class of multivariate, strongly log-concave target distributions. These “Stein factor” bounds deliver control over Wasserstein and related smooth function distances and are well-suited to analyzing the computable Stein discrepancy measures of Gorham and Mackey. Our arguments of proof are probabilistic and feature the synchronous coupling of multiple overdamped Langevin diffusions.

Article information

Electron. Commun. Probab., Volume 21 (2016), paper no. 56, 14 pp.

Received: 4 April 2016
Accepted: 8 August 2016
First available in Project Euclid: 2 September 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 60J60: Diffusion processes [See also 58J65] 62E17: Approximations to distributions (nonasymptotic) 60E15: Inequalities; stochastic orderings

Stein’s method Stein factors multivariate log-concave distribution overdamped Langevin diffusion generator method synchronous coupling Stein discrepancy

Creative Commons Attribution 4.0 International License.


Mackey, Lester; Gorham, Jackson. Multivariate Stein factors for a class of strongly log-concave distributions. Electron. Commun. Probab. 21 (2016), paper no. 56, 14 pp. doi:10.1214/16-ECP15. https://projecteuclid.org/euclid.ecp/1472830238

Export citation


  • [1] A. D. Barbour, Stein’s method and Poisson process convergence, J. Appl. Probab. (1988), no. Special Vol. 25A, 175–184, A celebration of applied probability.
  • [2] A. D. Barbour, Stein’s method for diffusion approximations, Probab. Theory Related Fields 84 (1990), no. 3, 297–322.
  • [3] V. Bentkus, On the dependence of the Berry-Esseen bound on dimension, J. Statist. Plann. Inference 113 (2003), no. 2, 385–402.
  • [4] P. Cattiaux and A. Guillin, Semi log-concave Markov diffusions, Séminaire de Probabilités XLVI, Lecture Notes in Math., vol. 2123, Springer, Cham, 2014, pp. 231–292.
  • [5] S. Chatterjee and E. Meckes, Multivariate normal approximation using exchangeable pairs, ALEA Lat. Am. J. Probab. Math. Stat. 4 (2008), 257–283.
  • [6] S. Chatterjee and Q.-M. Shao, Nonnormal approximation by Stein’s method of exchangeable pairs with application to the Curie-Weiss model, Ann. Appl. Probab. 21 (2011), no. 2, 464–483.
  • [7] L. H. Y. Chen, L. Goldstein, and Q.-M. Shao, Normal approximation by Stein’s method, Probability and its Applications (New York), Springer, Heidelberg, 2011.
  • [8] M. Cule and R. Samworth, Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density, Electron. J. Stat. 4 (2010), 254–270.
  • [9] S. N. Ethier and T. G. Kurtz, Markov processes, Wiley Series in Probability and Mathematical Statistics: Probability and Mathematical Statistics, John Wiley & Sons, Inc., New York, 1986, Characterization and convergence.
  • [10] A. Gelman, J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari, and D. B. Rubin, Bayesian data analysis, third ed., Texts in Statistical Science Series, CRC Press, Boca Raton, FL, 2014.
  • [11] J. Gorham and L. Mackey, Measuring sample quality with Stein’s method, Advances in Neural Information Processing Systems 28 (C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, eds.), Curran Associates, Inc., 2015, pp. 226–234.
  • [12] F. Götze, On the rate of convergence in the multivariate CLT, Ann. Probab. 19 (1991), no. 2, 724–739.
  • [13] R. Khasminskii, Stochastic stability of differential equations, second ed., Stochastic Modelling and Applied Probability, vol. 66, Springer, Heidelberg, 2012, With contributions by G. N. Milstein and M. B. Nevelson.
  • [14] M. Ledoux, I. Nourdin, and G. Peccati, Stein’s method, logarithmic Sobolev and transport inequalities, Geom. Funct. Anal. 25 (2015), no. 1, 256–306.
  • [15] E. Meckes, On Stein’s method for multivariate normal approximation, High dimensional probability V: the Luminy volume, Inst. Math. Stat. Collect., vol. 5, Inst. Math. Statist., Beachwood, OH, 2009, pp. 153–178.
  • [16] I. Nourdin, G. Peccati, and A. Réveillac, Multivariate normal approximation using Stein’s method and Malliavin calculus, Ann. Inst. Henri Poincaré Probab. Stat. 46 (2010), no. 1, 45–58.
  • [17] G. A. Pavliotis, Stochastic processes and applications, Texts in Applied Mathematics, vol. 60, Springer, New York, 2014, Diffusion processes, the Fokker-Planck and Langevin equations.
  • [18] G. Reinert and A. Röllin, Multivariate normal approximation with Stein’s method of exchangeable pairs under a general linearity condition, Ann. Probab. 37 (2009), no. 6, 2150–2173.
  • [19] G. O. Roberts and R. L. Tweedie, Exponential convergence of Langevin distributions and their discrete approximations, Bernoulli 2 (1996), no. 4, 341–363.
  • [20] C. Stein, A bound for the error in the normal approximation to the distribution of a sum of dependent random variables, Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability (Univ. California, Berkeley, Calif., 1970/1971), Vol. II: Probability theory, Univ. California Press, Berkeley, Calif., 1972, pp. 583–602.
  • [21] J. Wishart, The generalised product moment distribution in samples from a normal multivariate population, Biometrika 20A (1928), no. 1/2, 32–52.