IDEAS home Printed from https://ideas.repec.org/a/eee/jmvana/v132y2014icp197-208.html
   My bibliography  Save this article

Optimal global rates of convergence for noiseless regression estimation problems with adaptively chosen design

Author

Listed:
  • Kohler, Michael

Abstract

Given the values of a measurable function m:Rd→R at n arbitrarily chosen points in Rd the problem of estimating m on whole Rd is considered. Here the estimate has to be defined such that the L1 error of the estimate (with integration with respect to a fixed but unknown probability measure) is small. Under the assumption that m is (p,C)-smooth (i.e., roughly speaking, m is p-times continuously differentiable) it is shown that the optimal minimax rate of convergence of the L1 error is n−p/d, where the upper bound is valid even if the support of the design measure is unbounded but the design measure satisfies some moment condition. Furthermore it is shown that this rate of convergence cannot be improved even if the function is not allowed to change with the size of the data.

Suggested Citation

  • Kohler, Michael, 2014. "Optimal global rates of convergence for noiseless regression estimation problems with adaptively chosen design," Journal of Multivariate Analysis, Elsevier, vol. 132(C), pages 197-208.
    • Handle: RePEc:eee:jmvana:v:132:y:2014:i:c:p:197-208
    DOI: 10.1016/j.jmva.2014.08.008
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0047259X14001900
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.jmva.2014.08.008?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. Kohler, Michael & Krzyżak, Adam, 2013. "Optimal global rates of convergence for interpolation problems with random design," Statistics & Probability Letters, Elsevier, vol. 83(8), pages 1871-1879.
    2. Kohler, Michael & Krzyzak, Adam & Walk, Harro, 2006. "Rates of convergence for partitioning and nearest neighbor regression estimates with unbounded data," Journal of Multivariate Analysis, Elsevier, vol. 97(2), pages 311-323, February.
    3. Tina Felber & Michael Kohler & Adam Krzyżak, 2015. "Adaptive density estimation based on real and artificial data," Journal of Nonparametric Statistics, Taylor & Francis Journals, vol. 27(1), pages 1-18, March.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Langer, Sophie, 2021. "Approximating smooth functions by deep neural networks with sigmoid activation function," Journal of Multivariate Analysis, Elsevier, vol. 182(C).
    2. Bauer, Benedikt & Devroye, Luc & Kohler, Michael & Krzyżak, Adam & Walk, Harro, 2017. "Nonparametric estimation of a function from noiseless observations at random points," Journal of Multivariate Analysis, Elsevier, vol. 160(C), pages 93-104.
    3. Michael Kohler & Adam Krzyżak & Reinhard Tent & Harro Walk, 2018. "Nonparametric quantile estimation using importance sampling," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 70(2), pages 439-465, April.
    4. Benedikt Bauer & Felix Heimrich & Michael Kohler & Adam Krzyżak, 2019. "On estimation of surrogate models for multivariate computer experiments," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 71(1), pages 107-136, February.

    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. Leluc, Rémi & Portier, François & Zhuman, Aigerim & Segers, Johan, 2023. "Speeding up Monte Carlo Integration: Control Neighbors for Optimal Convergence," LIDAM Discussion Papers ISBA 2023019, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    2. Charlier, Isabelle & Paindaveine, Davy & Saracco, Jérôme, 2015. "Conditional quantile estimation based on optimal quantization: From theory to practice," Computational Statistics & Data Analysis, Elsevier, vol. 91(C), pages 20-39.
    3. Christian Bender & Nikolaus Schweizer, 2019. "`Regression Anytime' with Brute-Force SVD Truncation," Papers 1908.08264, arXiv.org, revised Oct 2020.
    4. Cattaneo, Matias D. & Farrell, Max H., 2013. "Optimal convergence rates, Bahadur representation, and asymptotic normality of partitioning estimators," Journal of Econometrics, Elsevier, vol. 174(2), pages 127-143.
    5. Benedict Götz & Sebastian Kersting & Michael Kohler, 2021. "Estimation of an improved surrogate model in uncertainty quantification by neural networks," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 73(2), pages 249-281, April.
    6. Paola Gloria Ferrario, 2018. "Partitioning estimation of local variance based on nearest neighbors under censoring," Statistical Papers, Springer, vol. 59(2), pages 423-447, June.
    7. Ann-Kathrin Bott & Tina Felber & Michael Kohler, 2015. "Estimation of a density in a simulation model," Journal of Nonparametric Statistics, Taylor & Francis Journals, vol. 27(3), pages 271-285, September.
    8. P. G. Ferrario & H. Walk, 2012. "Nonparametric partitioning estimation of residual and local variance based on first and second nearest neighbours," Journal of Nonparametric Statistics, Taylor & Francis Journals, vol. 24(4), pages 1019-1039, December.
    9. Michael Kohler & Adam Krzyżak, 2020. "Estimating quantiles in imperfect simulation models using conditional density estimation," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 72(1), pages 123-155, February.
    10. Kohler, Michael & Krzyżak, Adam & Walk, Harro, 2014. "Nonparametric recursive quantile estimation," Statistics & Probability Letters, Elsevier, vol. 93(C), pages 102-107.
    11. Liitiäinen, Elia & Corona, Francesco & Lendasse, Amaury, 2010. "Residual variance estimation using a nearest neighbor statistic," Journal of Multivariate Analysis, Elsevier, vol. 101(4), pages 811-823, April.
    12. Sancetta, A., 2007. "Online Forecast Combination for Dependent Heterogeneous Data," Cambridge Working Papers in Economics 0718, Faculty of Economics, University of Cambridge.
    13. Kohler, Michael & Krzyżak, Adam, 2013. "Optimal global rates of convergence for interpolation problems with random design," Statistics & Probability Letters, Elsevier, vol. 83(8), pages 1871-1879.
    14. Benedikt Bauer & Felix Heimrich & Michael Kohler & Adam Krzyżak, 2019. "On estimation of surrogate models for multivariate computer experiments," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 71(1), pages 107-136, February.
    15. Bauer, Benedikt & Devroye, Luc & Kohler, Michael & Krzyżak, Adam & Walk, Harro, 2017. "Nonparametric estimation of a function from noiseless observations at random points," Journal of Multivariate Analysis, Elsevier, vol. 160(C), pages 93-104.

    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:jmvana:v:132:y:2014:i:c:p:197-208. 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.