The Annals of Statistics

Sub-Gaussian mean estimators

Luc Devroye, Matthieu Lerasle, Gabor Lugosi, and Roberto I. Oliveira

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


We discuss the possibilities and limitations of estimating the mean of a real-valued random variable from independent and identically distributed observations from a nonasymptotic point of view. In particular, we define estimators with a sub-Gaussian behavior even for certain heavy-tailed distributions. We also prove various impossibility results for mean estimators.

Article information

Ann. Statist., Volume 44, Number 6 (2016), 2695-2725.

Received: September 2015
Revised: January 2016
First available in Project Euclid: 23 November 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62G05: Estimation
Secondary: 60F99: None of the above, but in this section

Sub-Gaussian estimators minimax bounds


Devroye, Luc; Lerasle, Matthieu; Lugosi, Gabor; Oliveira, Roberto I. Sub-Gaussian mean estimators. Ann. Statist. 44 (2016), no. 6, 2695--2725. doi:10.1214/16-AOS1440.

Export citation


  • [1] Alon, N., Matias, Y. and Szegedy, M. (1996). The space complexity of approximating the frequency moments. In Proceedings of the Twenty-Eighth Annual ACM Symposium on the Theory of Computing (Philadelphia, PA, 1996) 20–29. ACM, New York.
  • [2] Audibert, J.-Y. and Catoni, O. (2011). Robust linear least squares regression. Ann. Statist. 39 2766–2794.
  • [3] Brownlees, C., Joly, E. and Lugosi, G. (2015). Empirical risk minimization for heavy-tailed losses. Ann. Statist. 43 2507–2536.
  • [4] Bubeck, S., Cesa-Bianchi, N. and Lugosi, G. (2013). Bandits with heavy tail. IEEE Trans. Inform. Theory 59 7711–7717.
  • [5] Catoni, O. (2012). Challenging the empirical mean and empirical variance: A deviation study. Ann. Inst. Henri Poincaré Probab. Stat. 48 1148–1185.
  • [6] Chen, L. H. Y., Goldstein, L. and Shao, Q. (2011). Normal Approximation by Stein’s Method. Springer, Berlin.
  • [7] Hsu, D. (2010). Robust statistics. Available at
  • [8] Hsu, D., Kakade, S. M. and Zhang, T. (2012). A tail inequality for quadratic forms of sub-Gaussian random vectors. Electron. Commun. Probab. 17 1–6.
  • [9] Hsu, D. and Sabato, S. (2014). Heavy-tailed regression with a generalized median-of-means. In Proceedings of the 31st International Conference on Machine Learning (ICML-14) (T. Jebara and E. P. Xing, eds.) 37–45. JMLR Workshop and Conference Proceedings.
  • [10] Jerrum, M. R., Valiant, L. G. and Vazirani, V. V. (1986). Random generation of combinatorial structures from a uniform distribution. Theoret. Comput. Sci. 43 169–188.
  • [11] Joly, E. (2015). Estimation robuste de distributions à queue lourde. Ph.D. thesis, Mathematics at Univ. Paris-Saclay.
  • [12] Lepskiĭ, O. V. (1990). A problem of adaptive estimation in Gaussian white noise. Theory Probab. Appl. 35 454–466.
  • [13] Lepskiĭ, O. V. (1991). Asymptotically minimax adaptive estimation. I. Upper bounds. Optimally adaptive estimates. Theory Probab. Appl. 36 682–697.
  • [14] Lerasle, M. and Oliveira, R. I. (2012). Robust empirical mean estimators. Available at arXiv:1112.3914.
  • [15] Levin, L. A. (2005). Notes for miscellaneous lectures. CoRR. Available at arXiv:cs/0503039.
  • [16] Minsker, S. (2015). Geometric median and robust estimation in Banach spaces. Bernoulli 21 2308–2335.
  • [17] Nemirovsky, A. S. and Yudin, D. B. (1983). Problem Complexity and Method Efficiency in Optimization. Wiley, New York.
  • [18] Petrov, V. V. (1975). Sums of Independent Random Variables. Springer, Berlin.