Skip to main content
SpringerLink
Log in

Confidence Sets for Spectral Projectors of Covariance Matrices

  • Mathematics
  • Published:
Doklady Mathematics Aims and scope Submit manuscript

Abstract

A sample X1,...,Xn consisting of independent identically distributed vectors in ℝp with zero mean and a covariance matrix Σ is considered. The recovery of spectral projectors of high-dimensional covariance matrices from a sample of observations is a key problem in statistics arising in numerous applications. In their 2015 work, V. Koltchinskii and K. Lounici obtained nonasymptotic bounds for the Frobenius norm \(\parallel {P_r} - {\hat P_r}{\parallel _2}\) of the distance between sample and true projectors and studied asymptotic behavior for large samples. More specifically, asymptotic confidence sets for the true projector Pr were constructed assuming that the moment characteristics of the observations are known. This paper describes a bootstrap procedure for constructing confidence sets for the spectral projector Pr of the covariance matrix Σ from given data. This approach does not use the asymptotical distribution of \(\parallel {P_r} - {\hat P_r}{\parallel _2}\) and does not require the computation of its moment characteristics. The performance of the bootstrap approximation procedure is analyzed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. J. Tropp, Found. Comput. Math. 12 (4), 389–434 (2012).

    Article  MathSciNet  Google Scholar 

  2. R. Vershynin, “Introduction to the non-asymptotic analysis of random matrices,” in Compressed Sensing: Theory and Applications (Cambridge Univ. Press, Cambridge, 2012), pp. 210–268.

    Chapter  Google Scholar 

  3. R. van Handel, Trans. Am. Math. Soc. 369 (11), 8161–8178 (2017).

    Article  Google Scholar 

  4. V. Koltchinskii and K. Lounici, “Concentration inequalities and moment bounds for sample covariance operators” (2015). ArXiv:1405.2468.

    MATH  Google Scholar 

  5. V. Koltchinskii and K. Lounici, Ann. Stat. 45 (1), 121–157 (2017).

    Article  Google Scholar 

  6. V. Spokoiny, and M. Zhilova, Ann. Stat. 43 (6), 2653–2675 (2015).

    Article  Google Scholar 

  7. V. Chernozhukov, D. Chetverikov, and K. Kato, Ann. Stat. 41 (6), 2786–2819 (2013).

    Article  Google Scholar 

  8. V. Chernozhukov, D. Chetverikov, and K. Kato, Ann. Probab. 45 (4), 2309–2352 (2017).

    Article  MathSciNet  Google Scholar 

  9. A. Naumov, V. Spokoiny, and V. Ulyanov, “Bootstrap confidence sets for spectral projectors of sample covariance” (2017). arXiv:1703.00871.

    Google Scholar 

  10. F. Götze, A. Naumov, V. Spokoiny, and V. Ulyanov, “Large ball probabilities, Gaussian comparison and anti-concentration,” Bernoulli 25 (2019). arXiv:1708.08663v2.

  11. A. Naumov, V. Spokoiny, Yu. Tavyrikov and V. Ulyanov, “Nonasymptotic estimates for the closeness of Gaussian measures on balls”, Dokl. Math. 98 (2018).

Download references

Author information

Authors and Affiliations

  1. National Research University Higher School of Economics, Moscow, Russia

    A. A. Naumov & V. V. Ulyanov

  2. Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia

    A. A. Naumov & V. G. Spokoiny

  3. Skolkovo Institute of Science and Technology, Skolkovo, Moscow, Russia

    V. G. Spokoiny

  4. Weierstrass Institute for Applied Analysis and Stochastics, Berlin, Germany

    V. G. Spokoiny

  5. Humboldt University of Berlin, Berlin, Germany

    V. G. Spokoiny

  6. Faculty of Computational Mathematics and Cybernetics, Moscow State University, Moscow, Russia

    V. V. Ulyanov

Authors
  1. A. A. Naumov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. G. Spokoiny
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. V. V. Ulyanov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. A. Naumov.

Additional information

Original Russian Text © A.A. Naumov, V.G. Spokoiny, V.V. Ulyanov, 2018, published in Doklady Akademii Nauk, 2018, Vol. 482, No. 6.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Naumov, A.A., Spokoiny, V.G. & Ulyanov, V.V. Confidence Sets for Spectral Projectors of Covariance Matrices. Dokl. Math. 98, 511–514 (2018). https://doi.org/10.1134/S1064562418060285

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1064562418060285

Search

Navigation