IDEAS home Printed from https://ideas.repec.org/a/eee/stapro/v161y2020ics0167715220300444.html
   My bibliography  Save this article

High-probability bounds for the reconstruction error of PCA

Author

Listed:
  • Milbradt, Cassandra
  • Wahl, Martin

Abstract

We derive high-probability bounds for the reconstruction error of PCA in infinite dimensions. We apply our bounds in the case that the eigenvalues of the covariance operator satisfy polynomial or exponential upper bounds.

Suggested Citation

  • Milbradt, Cassandra & Wahl, Martin, 2020. "High-probability bounds for the reconstruction error of PCA," Statistics & Probability Letters, Elsevier, vol. 161(C).
    • Handle: RePEc:eee:stapro:v:161:y:2020:i:c:s0167715220300444
    DOI: 10.1016/j.spl.2020.108741
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0167715220300444
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.spl.2020.108741?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Y. Yu & T. Wang & R. J. Samworth, 2015. "A useful variant of the Davis–Kahan theorem for statisticians," Biometrika, Biometrika Trust, vol. 102(2), pages 315-323.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Steland, Ansgar, 2020. "Testing and estimating change-points in the covariance matrix of a high-dimensional time series," Journal of Multivariate Analysis, Elsevier, vol. 177(C).
    2. Matteo Barigozzi, 2023. "Asymptotic equivalence of Principal Components and Quasi Maximum Likelihood estimators in Large Approximate Factor Models," Papers 2307.09864, arXiv.org, revised Jun 2024.
    3. Chao, Shih-Kang & Härdle, Wolfgang Karl & Yuan, Ming, 2016. "Factorisable multi-task quantile regression," SFB 649 Discussion Papers 2016-057, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    4. Wang, Wuyi & Su, Liangjun, 2021. "Identifying latent group structures in nonlinear panels," Journal of Econometrics, Elsevier, vol. 220(2), pages 272-295.
    5. Denis Chetverikov & Elena Manresa, 2022. "Spectral and post-spectral estimators for grouped panel data models," Papers 2212.13324, arXiv.org, revised Dec 2022.
    6. Avanti Athreya & Joshua Cape & Minh Tang, 2022. "Eigenvalues of Stochastic Blockmodel Graphs and Random Graphs with Low-Rank Edge Probability Matrices," Sankhya A: The Indian Journal of Statistics, Springer;Indian Statistical Institute, vol. 84(1), pages 36-63, June.
    7. repec:hum:wpaper:sfb649dp2016-057 is not listed on IDEAS
    8. Chao, Shih-Kang & Härdle, Wolfgang K. & Yuan, Ming, 2021. "Factorisable Multitask Quantile Regression," Econometric Theory, Cambridge University Press, vol. 37(4), pages 794-816, August.
    9. Barigozzi, Matteo & Cho, Haeran & Fryzlewicz, Piotr, 2018. "Simultaneous multiple change-point and factor analysis for high-dimensional time series," Journal of Econometrics, Elsevier, vol. 206(1), pages 187-225.
    10. Timothy I. Cannings & Richard J. Samworth, 2017. "Random-projection ensemble classification," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 79(4), pages 959-1035, September.
    11. Banerjee, Sayantan & Akbani, Rehan & Baladandayuthapani, Veerabhadran, 2019. "Spectral clustering via sparse graph structure learning with application to proteomic signaling networks in cancer," Computational Statistics & Data Analysis, Elsevier, vol. 132(C), pages 46-69.
    12. Fogel, Fajwel & d'Aspremont, Alexandre & Vojnovic, Milan, 2016. "Spectral ranking using seriation," LSE Research Online Documents on Economics 68987, London School of Economics and Political Science, LSE Library.
    13. Long Zhao & Deepayan Chakrabarti & Kumar Muthuraman, 2019. "Portfolio Construction by Mitigating Error Amplification: The Bounded-Noise Portfolio," Operations Research, INFORMS, vol. 67(4), pages 965-983, July.
    14. Yu, Long & He, Yong & Kong, Xinbing & Zhang, Xinsheng, 2022. "Projected estimation for large-dimensional matrix factor models," Journal of Econometrics, Elsevier, vol. 229(1), pages 201-217.
    15. Matteo Barigozzi, 2022. "On Estimation and Inference of Large Approximate Dynamic Factor Models via the Principal Component Analysis," Papers 2211.01921, arXiv.org, revised Jul 2023.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:stapro:v:161:y:2020:i:c:s0167715220300444. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/622892/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.