Electronic Communications in Probability

Hanson-Wright inequality and sub-gaussian concentration

Mark Rudelson and Roman Vershynin

Full-text: Open access

Abstract

In this expository note, we give a modern proof of Hanson-Wright inequality for quadratic forms in sub-gaussian random variables.We deduce a useful concentration inequality for sub-gaussian random vectors.Two examples are given to illustrate these results: a concentration of distances between random vectors and subspaces, and a bound on the norms of products of random and deterministic matrices.

Article information

Source
Electron. Commun. Probab., Volume 18 (2013), paper no. 82, 9 pp.

Dates
Accepted: 23 October 2013
First available in Project Euclid: 7 June 2016

Permanent link to this document
https://projecteuclid.org/euclid.ecp/1465315621

Digital Object Identifier
doi:10.1214/ECP.v18-2865

Mathematical Reviews number (MathSciNet)
MR3125258

Zentralblatt MATH identifier
1329.60056

Keywords
subgaussian random variables measure concentration

Rights
This work is licensed under a Creative Commons Attribution 3.0 License.

Citation

Rudelson, Mark; Vershynin, Roman. Hanson-Wright inequality and sub-gaussian concentration. Electron. Commun. Probab. 18 (2013), paper no. 82, 9 pp. doi:10.1214/ECP.v18-2865. https://projecteuclid.org/euclid.ecp/1465315621


Export citation

References

  • R. Adamczak, P. Wolff, Concentration inequalities for non-Lipschitz functions with bounded derivatives of higher order, arXiv:1304.1826
  • Bourgain, Jean. Random points in isotropic convex sets. Convex geometric analysis (Berkeley, CA, 1996), 53–58, Math. Sci. Res. Inst. Publ., 34, Cambridge Univ. Press, Cambridge, 1999.
  • Barthe, Franck; Milman, Emanuel. Transference Principles for Log-Sobolev and Spectral-Gap with Applications to Conservative Spin Systems. Comm. Math. Phys. 323 (2013), no. 2, 575–625. arXiv:1202.5318
  • de la Peña, Víctor H.; Giné, Evarist. Decoupling. From dependence to independence. Randomly stopped processes. $U$-statistics and processes. Martingales and beyond. Probability and its Applications (New York). Springer-Verlag, New York, 1999. xvi+392 pp. ISBN: 0-387-98616-2
  • de la Peña, Victor H.; Montgomery-Smith, S. J. Decoupling inequalities for the tail probabilities of multivariate $U$-statistics. Ann. Probab. 23 (1995), no. 2, 806–816.
  • Diakonikolas, Ilias; Kane, Daniel M.; Nelson, Jelani. Bounded independence fools degree-2 threshold functions. 2010 IEEE 51st Annual Symposium on Foundations of Computer Science FOCS 2010, 11–20, IEEE Computer Soc., Los Alamitos, CA, 2010.
  • ErdÅ‘s, László; Yau, Horng-Tzer; Yin, Jun. Bulk universality for generalized Wigner matrices. Probab. Theory Related Fields 154 (2012), no. 1-2, 341–407.
  • A. Foucart, H. Rauhut, A Mathematical Introduction to Compressive Sensing. Applied and Numerical Harmonic Analysis. Birkhäuser, 2013.
  • Hanson, D. L.; Wright, F. T. A bound on tail probabilities for quadratic forms in independent random variables. Ann. Math. Statist. 42 1971 1079–1083.
  • Hsu, Daniel; Kakade, Sham M.; Zhang, Tong. A tail inequality for quadratic forms of subgaussian random vectors. Electron. Commun. Probab. 17 (2012), no. 52, 6 pp.
  • Latała, Rafał. Estimates of moments and tails of Gaussian chaoses. Ann. Probab. 34 (2006), no. 6, 2315–2331.
  • Latala, Rafal; Mankiewicz, Piotr; Oleszkiewicz, Krzysztof; Tomczak-Jaegermann, Nicole. Banach-Mazur distances and projections on random subgaussian polytopes. Discrete Comput. Geom. 38 (2007), no. 1, 29–50.
  • Ledoux, Michel. The concentration of measure phenomenon. Mathematical Surveys and Monographs, 89. American Mathematical Society, Providence, RI, 2001. x+181 pp. ISBN: 0-8218-2864-9
  • J. Nelson, Johnson–Lindenstrauss notes, http://web.mit.edu/minilek/www/jl_notes.pdf.
  • Talagrand, Michel. Concentration of measure and isoperimetric inequalities in product spaces. Inst. Hautes Études Sci. Publ. Math. No. 81 (1995), 73–205.
  • Tao, Terence. Topics in random matrix theory. Graduate Studies in Mathematics, 132. American Mathematical Society, Providence, RI, 2012. x+282 pp. ISBN: 978-0-8218-7430-1
  • Vershynin, Roman. Spectral norm of products of random and deterministic matrices. Probab. Theory Related Fields 150 (2011), no. 3-4, 471–509.
  • Vershynin, Roman. Introduction to the non-asymptotic analysis of random matrices. Compressed sensing, 210–268, Cambridge Univ. Press, Cambridge, 2012.
  • Wright, F. T. A bound on tail probabilities for quadratic forms in independent random variables whose distributions are not necessarily symmetric. Ann. Probability 1 (1973), no. 6, 1068–1070.