We investigate the sub-Gaussian property for almost surely bounded random variables. If sub-Gaussianity per se is de facto ensured by the bounded support of said random variables, then exciting research avenues remain open. Among these questions is how to characterize the optimal sub-Gaussian proxy variance? Another question is how to characterize strict sub-Gaussianity, defined by a proxy variance equal to the (standard) variance? We address the questions in proposing conditions based on the study of functions variations. A particular focus is given to the relationship between strict sub-Gaussianity and symmetry of the distribution. In particular, we demonstrate that symmetry is neither sufficient nor necessary for strict sub-Gaussianity. In contrast, simple necessary conditions on the one hand, and simple sufficient conditions on the other hand, for strict sub-Gaussianity are provided. These results are illustrated via various applications to a number of bounded random variables, including Bernoulli, beta, binomial, Kumaraswamy, triangular, and uniform distributions.
Accepté le :
Première publication :
Publié le :
DOI : 10.1051/ps/2019018
Mots-clés : Sub-Gaussian, beta distribution, Kumaraswamy distribution, triangular distribution
@article{PS_2020__24_1_39_0,
author = {Arbel, Julyan and Marchal, Olivier and Nguyen, Hien D.},
title = {On strict {sub-Gaussianity,} optimal proxy variance and symmetry for bounded random variables},
journal = {ESAIM: Probability and Statistics},
pages = {39--55},
publisher = {EDP-Sciences},
volume = {24},
year = {2020},
doi = {10.1051/ps/2019018},
mrnumber = {4053001},
zbl = {1445.60016},
language = {en},
url = {http://archive.numdam.org/articles/10.1051/ps/2019018/}
}
TY - JOUR AU - Arbel, Julyan AU - Marchal, Olivier AU - Nguyen, Hien D. TI - On strict sub-Gaussianity, optimal proxy variance and symmetry for bounded random variables JO - ESAIM: Probability and Statistics PY - 2020 SP - 39 EP - 55 VL - 24 PB - EDP-Sciences UR - http://archive.numdam.org/articles/10.1051/ps/2019018/ DO - 10.1051/ps/2019018 LA - en ID - PS_2020__24_1_39_0 ER -
%0 Journal Article %A Arbel, Julyan %A Marchal, Olivier %A Nguyen, Hien D. %T On strict sub-Gaussianity, optimal proxy variance and symmetry for bounded random variables %J ESAIM: Probability and Statistics %D 2020 %P 39-55 %V 24 %I EDP-Sciences %U http://archive.numdam.org/articles/10.1051/ps/2019018/ %R 10.1051/ps/2019018 %G en %F PS_2020__24_1_39_0
Arbel, Julyan; Marchal, Olivier; Nguyen, Hien D. On strict sub-Gaussianity, optimal proxy variance and symmetry for bounded random variables. ESAIM: Probability and Statistics, Tome 24 (2020), pp. 39-55. doi : 10.1051/ps/2019018. http://archive.numdam.org/articles/10.1051/ps/2019018/
[1] , and , Concentration inequalities in the infinite urn scheme for occupancy counts and the missing mass, with applications. Bernoulli 23 (2017) 249–287. | DOI | MR | Zbl
[2] and , On the concentration of the missing mass. Electr. Commun. Prob. 18 (2013) 1–7. | MR | Zbl
[3] and , Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. J. Funct. Anal. 163 (1999) 1–28. | DOI | MR | Zbl
[4] , and , Concentration inequalities: a nonasymptotic theory of independence. Oxford University Press, Oxford (2013). | DOI | MR | Zbl
[5] and , Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5 (2012) 1–122. | DOI | Zbl
[6] and , volume 188 of Metric characterization of random variables and random processes. American Mathematical Society, Providence, Rhode Island (2000). | DOI | MR | Zbl
[7] , PAC-Bayesian supervised classification: the thermodynamics of statistical learning. Vol. 56 of Monograph Series. Institute of Mathematical Statistics Lecture Notes (2007). | MR | Zbl
[8] , Kumaraswamy’s distribution: A beta-type distribution with some tractability advantages. Stat. Methodol. 6 (2009) 70–81. | DOI | MR | Zbl
[9] and , Large deviation methods for approximate probabilistic inference. In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence UAI1 (1998).
[10] and , Beyond Beta: Other Continuous Families of Distributions with Bounded Support and Applications. World Scientific, Singapore (2004). | DOI | MR | Zbl
[11] , A generalized probability density function for double-bounded random processes. J. Hydrol. 46 (1980) 79–88. | DOI
[12] and , On the sub-Gaussianity of the beta and Dirichlet distributions. Electr. Commun. Probab. 22 (2017). | MR | Zbl
[13] and , Concentration inequalities for the missing mass and for histogram rule error. J. Mach. Learn. Res. 4 (2003) 895–911. | MR | Zbl
[14] and , Progress on a conjecture regarding the triangular distribution. Commun. Stat. Theory Methods 46 (2017) 11261–11271. | DOI | MR | Zbl
[15] and , Concentration of measure inequalities in information theory, communications, and coding. Found. Trends Commun. Inf. Theory 10 (2013) 1–246. | DOI | Zbl
[16] and , Non-asymptotic theory of random matrices: extreme singular values. In Proceedings of the International Congress of Mathematicians 2010 (ICM 2010) (In 4 Volumes) Vol. I: Plenary Lectures and Ceremonies Vols. II–IV: Invited Lectures. World Scientific, Singapore (2010) 1576–1602. | MR | Zbl
[17] , The Kearns-Saul inequality for Bernoulli and Poisson-binomial distributions. J. Theoret. Probab. 29 (2016) 48–62. | DOI | MR | Zbl
[18] , Probability in high dimension. Technical report, Princeton University, 2014. | DOI
Cité par Sources :
