Bernoulli

  • Bernoulli
  • Volume 25, Number 4B (2019), 3978-4006.

Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one

Adrien Saumard

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text

Abstract

We investigate links between the so-called Stein’s density approach in dimension one and some functional and concentration inequalities. We show that measures having a finite first moment and a density with connected support satisfy a weighted Poincaré inequality with the weight being the Stein kernel, that indeed exists and is unique in this case. Furthermore, we prove weighted log-Sobolev and asymmetric Brascamp–Lieb type inequalities related to Stein kernels. We also show that existence of a uniformly bounded Stein kernel is sufficient to ensure a positive Cheeger isoperimetric constant. Then we derive new concentration inequalities. In particular, we prove generalized Mills’ type inequalities when a Stein kernel is uniformly bounded and sub-gamma concentration for Lipschitz functions of a variable with a sub-linear Stein kernel. More generally, when some exponential moments are finite, the Laplace transform of the random variable of interest is shown to bounded from above by the Laplace transform of the Stein kernel. Along the way, we prove a general lemma for bounding the Laplace transform of a random variable, that may be of independent interest. We also provide density and tail formulas as well as tail bounds, generalizing previous results that where obtained in the context of Malliavin calculus.

Article information

Source
Bernoulli, Volume 25, Number 4B (2019), 3978-4006.

Dates
Received: June 2018
Revised: February 2019
First available in Project Euclid: 25 September 2019

Permanent link to this document
https://projecteuclid.org/euclid.bj/1569398791

Digital Object Identifier
doi:10.3150/19-BEJ1117

Mathematical Reviews number (MathSciNet)
MR4010979

Zentralblatt MATH identifier
07110162

Keywords
concentration inequality covariance identity isoperimetric constant Stein kernel tail bound weighted log-Sobolev inequality weighted Poincaré inequality

Citation

Saumard, Adrien. Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one. Bernoulli 25 (2019), no. 4B, 3978--4006. doi:10.3150/19-BEJ1117. https://projecteuclid.org/euclid.bj/1569398791


Export citation

References

  • [1] Ané, C., Blachère, S., Chafaï, D., Fougères, P., Gentil, I., Malrieu, F., Roberto, C. and Scheffer, G. (2000). Sur les Inégalités de Sobolev Logarithmiques. Panoramas et Synthèses [Panoramas and Syntheses] 10. Paris: Société Mathématique de France. With a preface by Dominique Bakry and Michel Ledoux.
  • [2] Bakry, D., Cattiaux, P. and Guillin, A. (2008). Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré. J. Funct. Anal. 254 727–759.
  • [3] Bakry, D., Gentil, I. and Ledoux, M. (2014). Analysis and Geometry of Markov Diffusion Operators. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences] 348. Cham: Springer.
  • [4] Barbour, A.D., Ross, N. and Wen, Y. (2018). Central moment inequalities using Stein’s method. Preprint. Available at arXiv:1802.10225.
  • [5] Barthe, F. and Roberto, C. (2003). Sobolev inequalities for probability measures on the real line. Studia Math. 159 481–497. Dedicated to Professor Aleksander Pełczyński on the occasion of his 70th birthday (Polish).
  • [6] Bobkov, S.G. and Götze, F. (1999). Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. J. Funct. Anal. 163 1–28.
  • [7] Bobkov, S.G., Götze, F. and Houdré, C. (2001). On Gaussian and Bernoulli covariance representations. Bernoulli 7 439–451.
  • [8] Bobkov, S.G. and Houdré, C. (1997). Isoperimetric constants for product probability measures. Ann. Probab. 25 184–205.
  • [9] Bobkov, S. and Ledoux, M. (1997). Poincaré’s inequalities and Talagrand’s concentration phenomenon for the exponential distribution. Probab. Theory Related Fields 107 383–400.
  • [10] Bobkov, S.G. and Ledoux, M. (2009). On weighted isoperimetric and Poincaré-type inequalities. In High Dimensional Probability V: The Luminy Volume. Inst. Math. Stat. (IMS) Collect. 5 1–29. Beachwood, OH: IMS.
  • [11] Bobkov, S.G. and Ledoux, M. (2009). Weighted Poincaré-type inequalities for Cauchy and other convex measures. Ann. Probab. 37 403–427.
  • [12] Bobkov, S. and Ledoux, M. (2014). One-dimensional empirical measures, order statistics, and Kantorovich transport distances. Mem. Amer. Math. Soc. To appear.
  • [13] Bonnefont, M. and Joulin, A. (2014). Intertwining relations for one-dimensional diffusions and application to functional inequalities. Potential Anal. 41 1005–1031.
  • [14] Bonnefont, M., Joulin, A. and Ma, Y. (2016). A note on spectral gap and weighted Poincaré inequalities for some one-dimensional diffusions. ESAIM Probab. Stat. 20 18–29.
  • [15] Bonnefont, M., Joulin, A. and Ma, Y. (2016). Spectral gap for spherically symmetric log-concave probability measures, and beyond. J. Funct. Anal. 270 2456–2482.
  • [16] Boucheron, S., Lugosi, G. and Massart, P. (2013). Concentration Inequalities. Oxford: Oxford Univ. Press. A nonasymptotic theory of independence, With a foreword by Michel Ledoux.
  • [17] Cattiaux, P., Guillin, A. and Wu, L.-M. (2011). Some remarks on weighted logarithmic Sobolev inequality. Indiana Univ. Math. J. 60 1885–1904.
  • [18] Cattiaux, P., Gozlan, N., Guillin, A. and Roberto, C. (2010). Functional inequalities for heavy tailed distributions and application to isoperimetry. Electron. J. Probab. 15 346–385.
  • [19] Chatterjee, S. (2007). Stein’s method for concentration inequalities. Probab. Theory Related Fields 138 305–321.
  • [20] Chatterjee, S. (2012). A new approach to strong embeddings. Probab. Theory Related Fields 152 231–264.
  • [21] Chatterjee, S. (2014). A short survey of Stein’s method. In Proceedings of the International Congress of Mathematicians – Seoul 2014. Vol. IV 1–24. Seoul: Kyung Moon Sa.
  • [22] Chatterjee, S. and Dey, P.S. (2010). Applications of Stein’s method for concentration inequalities. Ann. Probab. 38 2443–2485.
  • [23] Chen, L.H.Y., Goldstein, L. and Shao, Q.-M. (2011). Normal Approximation by Stein’s Method. Probability and Its Applications (New York). Heidelberg: Springer.
  • [24] Cook, N., Goldstein, L. and Johnson, T. (2018). Size biased couplings and the spectral gap for random regular graphs. Ann. Probab. 46 72–125.
  • [25] Cordero-Erausquin, D. and Gozlan, N. (2017). Transport proofs of weighted Poincaré inequalities for log-concave distributions. Bernoulli 23 134–158.
  • [26] Courtade, T.A., Fathi, M. and Pananjady, A. (2017). Existence of Stein Kernels under a Spectral Gap, and Discrepancy Bound. Preprint. Available at arXiv:1703.07707.
  • [27] Döbler, C. (2015). Stein’s method of exchangeable pairs for the beta distribution and generalizations. Electron. J. Probab. 20 109.
  • [28] Dümbgen, L. (2010). Bounding Standard Gaussian Tail Probabilities. Technical Report.
  • [29] Eden, R. and Viens, F. (2013). General upper and lower tail estimates using Malliavin calculus and Stein’s equations. In Seminar on Stochastic Analysis, Random Fields and Applications VII. Progress in Probability 67 55–84. Basel: Birkhäuser/Springer.
  • [30] Fathi, M. (2018). Stein kernels and moment maps. Ann. Probab. To appear. Available at arXiv:1804.04699.
  • [31] Fathi, M. and Nelson, B. (2017). Free Stein kernels and an improvement of the free logarithmic Sobolev inequality. Adv. Math. 317 193–223.
  • [32] Ghosh, S. and Goldstein, L. (2011). Applications of size biased couplings for concentration of measures. Electron. Commun. Probab. 16 70–83.
  • [33] Ghosh, S. and Goldstein, L. (2011). Concentration of measures via size-biased couplings. Probab. Theory Related Fields 149 271–278.
  • [34] Ghosh, S., Goldstein, L. and Raič, M. (2011). Concentration of measure for the number of isolated vertices in the Erdős–Rényi random graph by size bias couplings. Statist. Probab. Lett. 81 1565–1570.
  • [35] Goldstein, L. and Işlak, Ü. (2014). Concentration inequalities via zero bias couplings. Statist. Probab. Lett. 86 17–23.
  • [36] Gozlan, N. (2010). Poincaré inequalities and dimension free concentration of measure. Ann. Inst. Henri Poincaré Probab. Stat. 46 708–739.
  • [37] Latała, R. and Oleszkiewicz, K. (2000). Between Sobolev and Poincaré. In Geometric Aspects of Functional Analysis. Lecture Notes in Math. 1745 147–168. Berlin: Springer.
  • [38] Ledoux, M., Nourdin, I. and Peccati, G. (2015). Stein’s method, logarithmic Sobolev and transport inequalities. Geom. Funct. Anal. 25 256–306.
  • [39] Ledoux, M., Nourdin, I. and Peccati, G. (2017). A Stein deficit for the logarithmic Sobolev inequality. Sci. China Math. 60 1163–1180.
  • [40] Ley, C., Reinert, G. and Swan, Y. (2017). Stein’s method for comparison of univariate distributions. Probab. Surv. 14 1–52.
  • [41] Liu, Q., Lee, J. and Jordan, M. (2016). A kernelized Stein discrepancy for goodness-of-fit tests. In International Conference on Machine Learning 276–284.
  • [42] Mackey, L. and Gorham, J. (2016). Multivariate Stein factors for a class of strongly log-concave distributions. Electron. Commun. Probab. 21 56.
  • [43] Mackey, L., Jordan, M.I., Chen, R.Y., Farrell, B. and Tropp, J.A. (2014). Matrix concentration inequalities via the method of exchangeable pairs. Ann. Probab. 42 906–945.
  • [44] Menz, G. and Otto, F. (2013). Uniform logarithmic Sobolev inequalities for conservative spin systems with super-quadratic single-site potential. Ann. Probab. 41 2182–2224.
  • [45] Miclo, L. (2008). Quand est-ce que des bornes de Hardy permettent de calculer une constante de Poincaré exacte sur la droite? Ann. Fac. Sci. Toulouse Math. (6) 17 121–192.
  • [46] Muckenhoupt, B. (1972). Hardy’s inequality with weights. Studia Math. 44 31–38. Collection of articles honoring the completion by Antoni Zygmund of 50 years of scientific activity, I.
  • [47] Nourdin, I. and Viens, F.G. (2009). Density formula and concentration inequalities with Malliavin calculus. Electron. J. Probab. 14 2287–2309.
  • [48] Paulin, D., Mackey, L. and Tropp, J.A. (2016). Efron–Stein inequalities for random matrices. Ann. Probab. 44 3431–3473.
  • [49] Saumard, A. Supplement to “Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one.” DOI:10.3150/19-BEJ1117SUPP.
  • [50] Saumard, A. and Wellner, J.A. (2018). Efron’s monotonicity property for measures on $\mathbb{R}^{2}$. J. Multivariate Anal. 166 212–224.
  • [51] Saumard, A. and Wellner, J.A. (2018). On the isoperimetric constant, covariance inequalities and ${L}_{p}$-Poincaré inequalities in dimension one. Bernoulli, To appear. Available at arXiv:1711.00668.
  • [52] Stein, C. (1972). 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 (Univ. California, Berkeley, Calif., 1970/1971), Vol. II: Probability theory 583–602. Berkeley, CA: Univ. California Press.
  • [53] Stein, C. (1986). Approximate Computation of Expectations. Institute of Mathematical Statistics Lecture Notes – Monograph Series 7. Hayward, CA: IMS.
  • [54] Treilhard, J. and Mansouri, A.-R. (2015). Concentration inequalities via Malliavin calculus with applications. Electron. Commun. Probab. 20 36.
  • [55] Viens, F.G. (2009). Stein’s lemma, Malliavin calculus, and tail bounds, with application to polymer fluctuation exponent. Stochastic Process. Appl. 119 3671–3698.

Supplemental materials

  • Supplement to the article “Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one”. We provide additional results, comments and detail some proofs pertaining the work of this article.