On probabilistic convergence rates of stochastic Bernstein polynomials

Sun, Xingping; Wu, Zongmin; Zhou, Xuan

doi:10.1090/mcom/3589

On probabilistic convergence rates of stochastic Bernstein polynomials
HTML articles powered by AMS MathViewer

by Xingping Sun, Zongmin Wu and Xuan Zhou;

Math. Comp. 90 (2021), 813-830

DOI: https://doi.org/10.1090/mcom/3589

Published electronically: November 3, 2020

HTML | PDF | Request permission

Abstract:

In this article, we introduce the notion “$L_p$-probabilistic convergence" ($1 \le p \le \infty$) of stochastic Bernstein polynomials built upon order statistics of identically, independently, and uniformly distributed random variables on $[0,1]$. We establish power and exponential convergence rates in terms of the modulus of continuity of a target function $f \in C[0,1]$. For $p$ in the range $1 \le p \le 2,$ we obtain Gaussian tail bounds for the corresponding probabilistic convergence. Our result for the case $p=\infty$ confirms a conjecture raised by the second and third authors. Monte Carlo simulations (presented at the end of the article) show that the stochastic Bernstein approximation scheme studied herein achieves comparable computational goals to the classical Bernstein approximation, and indicate strongly that the Gaussian tail bounds proved for $1 \le p \le 2$ also hold true for the cases $2< p \le \infty$.

References

Robert A. Adams and John J. F. Fournier, Sobolev spaces, 2nd ed., Pure and Applied Mathematics (Amsterdam), vol. 140, Elsevier/Academic Press, Amsterdam, 2003. MR 2424078
José A. Adell and Daniel Cárdenas-Morales, Quantitative generalized Voronovskaja’s formulae for Bernstein polynomials, J. Approx. Theory 231 (2018), 41–52. MR 3800100, DOI 10.1016/j.jat.2018.04.007
Sergey Bobkov and Michel Ledoux, One-dimensional empirical measures, order statistics, and Kantorovich transport distances, Mem. Amer. Math. Soc. 261 (2019), no. 1259, v+126. MR 4028181, DOI 10.1090/memo/1259
Stéphane Boucheron, Gábor Lugosi, and Pascal Massart, Concentration inequalities, Oxford University Press, Oxford, 2013. A nonasymptotic theory of independence; With a foreword by Michel Ledoux. MR 3185193, DOI 10.1093/acprof:oso/9780199535255.001.0001
V. V. Buldygin and Yu. V. Kozachenko, Metric characterization of random variables and random processes, Translations of Mathematical Monographs, vol. 188, American Mathematical Society, Providence, RI, 2000. Translated from the 1998 Russian original by V. Zaiats. MR 1743716, DOI 10.1090/mmono/188
G. Casella and R. Berger, Statistical Reference, (2nd ed), Duxbury Advanced Series, 2002.
E. W. Cheney, Introduction to approximation theory, AMS Chelsea Publishing, Providence, RI, 1998. Reprint of the second (1982) edition. MR 1656150
Kai Lai Chung, Elementary probability theory with stochastic processes, 3rd ed., Undergraduate Texts in Mathematics, Springer-Verlag, New York-Heidelberg, 1979. MR 560506
Felipe Cucker and Steve Smale, On the mathematical foundations of learning, Bull. Amer. Math. Soc. (N.S.) 39 (2002), no. 1, 1–49. MR 1864085, DOI 10.1090/S0273-0979-01-00923-5
Felipe Cucker and Ding-Xuan Zhou, Learning theory: an approximation theory viewpoint, Cambridge Monographs on Applied and Computational Mathematics, vol. 24, Cambridge University Press, Cambridge, 2007. With a foreword by Stephen Smale. MR 2354721, DOI 10.1017/CBO9780511618796
H. A. David and H. N. Nagaraja, Order statistics, 3rd ed., Wiley Series in Probability and Statistics, Wiley-Interscience [John Wiley & Sons], Hoboken, NJ, 2003. MR 1994955, DOI 10.1002/0471722162
Z. Ditzian and K. G. Ivanov, Strong converse inequalities, J. Anal. Math. 61 (1993), 61–111. MR 1253439, DOI 10.1007/BF02788839
Z. Ditzian and V. Totik, Moduli of smoothness, Springer Series in Computational Mathematics, vol. 9, Springer-Verlag, New York, 1987. MR 914149, DOI 10.1007/978-1-4612-4778-4
S. Elder, Bayesian adaptive data analysis guarantees from subgaussianity, arXiv preprint arXiv:1611.00065 (2016).
Wenwu Gao, Xingping Sun, Zongmin Wu, and Xuan Zhou, Multivariate Monte Carlo approximation based on scattered data, SIAM J. Sci. Comput. 42 (2020), no. 4, A2262–A2280. MR 4127103, DOI 10.1137/19M1249138
Ioan Gavrea and Mircea Ivan, The Bernstein Voronovskaja-type theorem for positive linear approximation operators, J. Approx. Theory 192 (2015), 291–296. MR 3313485, DOI 10.1016/j.jat.2014.12.008
Dianne Hansford, Bézier techniques, Handbook of computer aided geometric design, North-Holland, Amsterdam, 2002, pp. 75–109. MR 1928537, DOI 10.1016/B978-044451104-1/50005-8
Asma Jmaei, Yousri Slaoui, and Wassima Dellagi, Recursive distribution estimator defined by stochastic approximation method using Bernstein polynomials, J. Nonparametr. Stat. 29 (2017), no. 4, 792–805. MR 3740720, DOI 10.1080/10485252.2017.1369538
G. G. Lorentz, Bernstein polynomials, Mathematical Expositions, No. 8, University of Toronto Press, Toronto, ON, 1953. MR 57370
Olivier Marchal and Julyan Arbel, On the sub-Gaussianity of the beta and Dirichlet distributions, Electron. Commun. Probab. 22 (2017), Paper No. 54, 14. MR 3718704, DOI 10.1214/17-ECP92
P. C. Sikkema, Der Wert einiger Konstanten in der Theorie der Approximation mit Bernstein-Polynomen, Numer. Math. 3 (1961), 107–116 (German). MR 123128, DOI 10.1007/BF01386008
P. C. Sikkema, Über den Grad der Approximation mit Bernstein-Polynomen, Numer. Math. 1 (1959), 221–239 (German). MR 110178, DOI 10.1007/BF01386387
Y. Slaoui, The stochastic approximation method for estimation of a distribution function, Math. Methods Statist. 23 (2014), no. 4, 306–325. MR 3295061, DOI 10.3103/S1066530714040048
Xingping Sun and Zongmin Wu, Chebyshev type inequality for stochastic Bernstein polynomials, Proc. Amer. Math. Soc. 147 (2019), no. 2, 671–679. MR 3894906, DOI 10.1090/proc/14161
Richard A. Vitale, Bernstein polynomial approach to density function estimation, Statistical inference and related topics (Proc. Summer Res. Inst. Statist. Inference for Stochastic Processes, Indiana Univ., Bloomington, Ind., 1974, Vol. 2; dedicated to Z. W. Birnbaum), Academic Press, New York-London, 1975, pp. 87–99. MR 397977
Zongmin Wu, Xingping Sun, and Limin Ma, Sampling scattered data with Bernstein polynomials: stochastic and deterministic error estimates, Adv. Comput. Math. 38 (2013), no. 1, 187–205. MR 3011338, DOI 10.1007/s10444-011-9233-0
Zongmin Wu and Xuan Zhou, Polynomial convergence order of stochastic Bernstein approximation, Adv. Comput. Math. 46 (2020), no. 1, Paper No. 8, 14. MR 4062488, DOI 10.1007/s10444-020-09742-w