The Annals of Probability

A Gaussian small deviation inequality for convex functions

Grigoris Paouris and Petros Valettas

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

Let $Z$ be an $n$-dimensional Gaussian vector and let $f:\mathbb{R}^{n}\to \mathbb{R}$ be a convex function. We prove that

\[\mathbb{P}(f(Z)\leq \mathbb{E}f(Z)-t\sqrt{\operatorname{Var}f(Z)})\leq\exp (-ct^{2}),\] for all $t>1$ where $c>0$ is an absolute constant. As an application we derive variance-sensitive small ball probabilities for Gaussian processes.

Article information

Source
Ann. Probab., Volume 46, Number 3 (2018), 1441-1454.

Dates
Received: November 2016
Revised: May 2017
First available in Project Euclid: 12 April 2018

Permanent link to this document
https://projecteuclid.org/euclid.aop/1523520021

Digital Object Identifier
doi:10.1214/17-AOP1206

Mathematical Reviews number (MathSciNet)
MR3785592

Zentralblatt MATH identifier
06894778

Subjects
Primary: 60D05: Geometric probability and stochastic geometry [See also 52A22, 53C65]
Secondary: 52A21: Finite-dimensional Banach spaces (including special norms, zonoids, etc.) [See also 46Bxx] 52A23: Asymptotic theory of convex bodies [See also 46B06]

Keywords
Ehrhard’s inequality concentration for convex functions small ball probability Johnson–Lindenstrauss lemma

Citation

Paouris, Grigoris; Valettas, Petros. A Gaussian small deviation inequality for convex functions. Ann. Probab. 46 (2018), no. 3, 1441--1454. doi:10.1214/17-AOP1206. https://projecteuclid.org/euclid.aop/1523520021


Export citation

References

  • [1] Bogachev, V. I. (1998). Gaussian Measures. Mathematical Surveys and Monographs 62. Amer. Math. Soc., Providence, RI.
  • [2] Borell, C. (1975). The Brunn–Minkowski inequality in Gauss space. Invent. Math. 30 207–216.
  • [3] Borell, C. (2003). The Ehrhard inequality. C. R. Math. Acad. Sci. Paris 337 663–666.
  • [4] Boucheron, S., Lugosi, G. and Massart, P. (2013). Concentration Inequalities: A Non-asymptotic Theory of Independence. Oxford Univ. Press, Oxford.
  • [5] Chatterjee, S. (2014). Superconcentration and Related Topics. Springer, Cham.
  • [6] Chen, L. H. Y. (1982). An inequality for the multivariate normal distribution. J. Multivariate Anal. 12 306–315.
  • [7] Cordero-Erausquin, D., Fradelizi, M. and Maurey, B. (2004). The (B) conjecture for the Gaussian measure of dilates of symmetric convex sets and related problems. J. Funct. Anal. 214 410–427.
  • [8] Ehrhard, A. (1983). Symétrisation dans l’espace de Gauss. Math. Scand. 53 281–301.
  • [9] Eskenazis, A., Nayar, P. and Tkocz, T. (2016). Gaussian mixtures: Entropy and geometric inequalities. Preprint. Available at https://arxiv.org/abs/1611.04921.
  • [10] Grafakos, L. (2004). Classical and Modern Fourier Analysis. Pearson Education, Upper Saddle River, NJ.
  • [11] Indyk, P. (2001). Algorithmic applications of low-distortion geometric embeddings. In 42nd IEEE Symposium on Foundations of Computer Science (Las Vegas, NV, 2001) 10–33. IEEE Computer Soc., Los Alamitos, CA.
  • [12] Ivanisvili, P. and Volberg, A. (2015). Bellman partial differential equation and the hill property for classical isoperimetric problems. Preprint. Available at https://arxiv.org/abs/1506.03409.
  • [13] Johnson, W. B. and Lindenstrauss, J. (1984). Extensions of Lipschitz mappings into a Hilbert space. In Conference in Modern Analysis and Probability (New Haven, Conn., 1982). 189–206. Amer. Math. Soc., Providence, RI.
  • [14] Johnson, W. B. and Naor, A. (2010). The Johnson–Lindenstrauss lemma almost characterizes Hilbert space, but not quite. Discrete Comput. Geom. 43 542–553.
  • [15] Klartag, B. and Vershynin, R. (2007). Small ball probability and Dvoretzky’s theorem. Israel J. Math. 157 193–207.
  • [16] Kushilevitz, E., Ostrovsky, R. and Rabani, Y. (2000). Efficient search for approximate nearest neighbor in high dimensional spaces. SIAM J. Comput. 30 457–474.
  • [17] Kwapień, S. (1994). A remark on the median and the expectation of convex functions of Gaussian vectors. In Probability in Banach Spaces, 9 (Sandjberg, 1993). Progress in Probability 35 271–272. Birkhäuser, Boston, MA.
  • [18] Latała, R. (1996). A note on the Ehrhard inequality. Studia Math. 118 169–174.
  • [19] Latała, R. and Oleszkiewicz, K. (2005). Small ball probability estimates in terms of widths. Studia Math. 169 305–314.
  • [20] Ledoux, M. (2001). The Concentration of Measure Phenomenon. Mathematical Surveys and Monographs 89. Amer. Math. Soc., Providence, RI.
  • [21] Ledoux, M. and Talagrand, M. (1991). Probability in Banach Spaces. Isoperimetry and Processes. Springer, Berlin.
  • [22] Litvak, A. E., Milman, V. D. and Schechtman, G. (1998). Averages of norms and quasi-norms. Math. Ann. 312 95–124.
  • [23] Milman, V. D. (1971). New proof of the theorem of A. Dvoretzky on sections of convex bodies (in Russian). Funkcional. Anal. i Prilozen. 5 28–37.
  • [24] Milman, V. D. and Schechtman, G. (1986). Asymptotic Theory of Finite-Dimensional Normed Spaces. Lecture Notes in Math. 1200. Springer, Berlin.
  • [25] Nayar, P. and Tkocz, T. (2013). A note on a Brunn-Minkowski inequality for the Gaussian measure. Proc. Amer. Math. Soc. 141 4027–4030.
  • [26] Neeman, J. and Paouris, G. (2016). An interpolation proof of Ehrhard’s inequality. Preprint. Available at https://arxiv.org/abs/1605.07233.
  • [27] Paouris, G., Pivovarov, P. and Valettas, P. (2017). On a quantitative reversal of Alexandrov’s inequality. Trans. Amer. Math. Soc. To appear. Available at https://arxiv.org/abs/1702.05762.
  • [28] Paouris, G. and Valettas, P. (2015). On Dvoretzky’s theorem for subspaces of $L_{p}$. Preprint. Available at http://arxiv.org/abs/1510.07289.
  • [29] Paouris, G. and Valettas, P. (2017). Variance estimates and almost Euclidean structure. Preprint. Available at https://arxiv.org/abs/1703.10244.
  • [30] Paouris, G., Valettas, P. and Zinn, J. (2017). Random version of Dvoretzky’s theorem in $\ell_{p}^{n}$. Stochastic Process. Appl. 127 3187–3227.
  • [31] Schechtman, G. (2006). Two observations regarding embedding subsets of Euclidean spaces in normed spaces. Adv. Math. 200 125–135.
  • [32] Schechtman, G. (2007). The random version of Dvoretzky’s theorem in $\ell^{n}_{\infty}$. In Geometric Aspects of Functional Analysis. Lecture Notes in Math. 1910 265–270. Springer, Berlin.
  • [33] Sudakov, V. N. and Tsirel’son, B. S. (1974). Extremal properties of half-spaces for spherically invariant measures (in Russian). Zap. Naučn. Sem. Leningrad. Otdel. Mat. Inst. Steklov. (LOMI) 41 14–24.
  • [34] van Handel, R. (2017). The Borell-Ehrhard game. Probab. Theory Related Fields To appear. Available at DOI:10.1007/s00440-017-0762-4.
  • [35] Vempala, S. S. (2004). The Random Projection Method. DIMACS Series in Discrete Mathematics and Theoretical Computer Science 65. Amer. Math. Soc., Providence, RI.