Advertisement

Probability Theory and Related Fields

, Volume 175, Issue 3–4, pp 957–973 | Cite as

Near-optimal mean estimators with respect to general norms

  • Gábor LugosiEmail author
  • Shahar Mendelson
Article

Abstract

We study the problem of estimating the mean of a random vector in \(\mathbb {R}^d\) based on an i.i.d. sample, when the accuracy of the estimator is measured by a general norm on \(\mathbb {R}^d\). We construct an estimator (that depends on the norm) that achieves an essentially optimal accuracy/confidence tradeoff under the only assumption that the random vector has a well-defined covariance matrix. At the heart of the argument is the construction of a uniform median-of-means estimator in a class of real valued functions.

Mathematics Subject Classification

62H12 62G05 

Notes

References

  1. 1.
    Alon, N., Matias, Y., Szegedy, M.: The space complexity of approximating the frequency moments. J. Comput. Syst. Sci. 58, 137–147 (2002)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Artstein, S., Milman, V., Szarek, S.J.: Duality of metric entropy. Ann. Math. 159, 1313–1328 (2004)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Boucheron, S., Lugosi, G., Massart, P.: Concentration Inequalities: A Nonasymptotic Theory of Independence. Oxford University Press, Oxford (2013)CrossRefGoogle Scholar
  4. 4.
    Catoni, O.: Challenging the empirical mean and empirical variance: a deviation study. Ann. Inst. Henri Poincaré Probab. Stat. 48(4), 1148–1185 (2012)MathSciNetCrossRefGoogle Scholar
  5. 5.
    O. Catoni.: PAC-Bayesian bounds for the Gram matrix and least squares regression with a random design. arXiv:1603.05229 (2016)
  6. 6.
    O. Catoni and I. Giulini.: Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression. arXiv:1712.02747 (2017)
  7. 7.
    Devroye, L., Lerasle, M., Lugosi, G., Oliveira, R.I.: Sub-Gausssian mean estimators. Ann. Stat. 44, 2695–2725 (2016)CrossRefGoogle Scholar
  8. 8.
    S.B. Hopkins.: Sub-Gaussian mean estimation in polynomial time. arXiv:1809.07425 (2018)
  9. 9.
    Hsu, D., Sabato, S.: Loss minimization and parameter estimation with heavy tails. J. Mach. Learn. Res. 17, 1–40 (2016)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Jerrum, M., Valiant, L., Vazirani, V.: Random generation of combinatorial structures from a uniform distribution. Theor. Comput. Sci. 43, 186–188 (1986)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Joly, E., Lugosi, G., Oliveira, R.I.: On the estimation of the mean of a random vector. Electron. J. Stat. 11, 440–451 (2017)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Krahmer, F., Mendelson, S., Rauhut, H.: Suprema of chaos processes and the restricted isometry property. Commun. Pure Appl. Math. 26(3), 473–494 (2014)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Ledoux, M., Talagrand, M.: Probability in Banach Space. Springer, New York (1991)CrossRefGoogle Scholar
  14. 14.
    M. Lerasle and R. I. Oliveira.: Robust empirical mean estimators. arXiv:1112.3914 (2012)
  15. 15.
    G. Lugosi and S. Mendelson.: Sub-Gaussian estimators of the mean of a random vector. Ann. Stat. 47(2), 783–794 (2019)MathSciNetCrossRefGoogle Scholar
  16. 16.
    S. Mendelson.: “Local” vs. “global” parameters—breaking the Gaussian complexity barrier. Ann. Stat. 45(5):1835–1862 (2017)Google Scholar
  17. 17.
    Geometric median and robust estimation in Banach spaces: S. Minsker. Bernoulli 21, 2308–2335 (2015)MathSciNetCrossRefGoogle Scholar
  18. 18.
    S. Minsker.: Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries. arXiv:1605.07129 (2016)
  19. 19.
    Nemirovsky, A.S., Yudin, D.B.: Problem complexity and method efficiency in optimization. Wiley, Hoboken (1983)Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Economics and BusinessPompeu Fabra UniversityBarcelonaSpain
  2. 2.ICREABarcelonaSpain
  3. 3.Barcelona Graduate School of EconomicsBarcelonaSpain
  4. 4.LPSMSorbonne UniversitéParisFrance
  5. 5.Mathematical Sciences InstituteThe Australian National UniversityCanberraAustralia

Personalised recommendations