Advanced Search
MyIDEAS: Login to save this paper or follow this series

Consistency and robustness of kernel based regression

Contents:

Author Info

  • Christmann, Andreas
  • Steinwart, Ingo
Registered author(s):

    Abstract

    We investigate properties of kernel based regression (KBR) methods which are inspired by the convex risk minimization method of support vector machines. We first describe the relation between the used loss function of the KBR method and the tail of the response variable Y . We then establish a consistency result for KBR and give assumptions for the existence of the influence function. In particular, our results allow to choose the loss function and the kernel to obtain computational tractable and consistent KBR methods having bounded influence functions. Furthermore, bounds for the sensitivity curve which is a finite sample version of the influence function are developed, and some numerical experiments are discussed. --

    Download Info

    If you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
    File URL: http://econstor.eu/bitstream/10419/22592/1/tr01-05.pdf
    Download Restriction: no

    Bibliographic Info

    Paper provided by Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen in its series Technical Reports with number 2005,01.

    as in new window
    Length:
    Date of creation: 2005
    Date of revision:
    Handle: RePEc:zbw:sfb475:200501

    Contact details of provider:
    Postal: Vogelpothsweg 78, D-44221 Dortmund
    Phone: (0231) 755-3125
    Fax: (0231) 755-5284
    Web page: http://www.statistik.tu-dortmund.de/sfb475.html
    More information through EDIRC

    Related research

    Keywords:

    References

    References listed on IDEAS
    Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
    as in new window
    1. Struyf, Anja J. & Rousseeuw, Peter J., 1999. "Halfspace Depth and Regression Depth Characterize the Empirical Distribution," Journal of Multivariate Analysis, Elsevier, vol. 69(1), pages 135-153, April.
    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 in new window

    Cited by:
    1. Marin-Galiano, Marcos & Luebke, Karsten & Christmann, Andreas & Rüping, Stefan, 2005. "Determination of hyper-parameters for kernel based classification and regression," Technical Reports 2005,38, Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen.
    2. Christmann, Andreas & Steinwart, Ingo & Hubert, Mia, 2007. "Robust learning from bites for data mining," Computational Statistics & Data Analysis, Elsevier, vol. 52(1), pages 347-361, September.
    3. Christmann, Andreas & Steinwart, Ingo & Hubert, Mia, 2006. "Robust Learning from Bites for Data Mining," Technical Reports 2006,03, Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen.

    Lists

    This item is not listed on Wikipedia, on a reading list or among the top items on IDEAS.

    Statistics

    Access and download statistics

    Corrections

    When requesting a correction, please mention this item's handle: RePEc:zbw:sfb475:200501. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (ZBW - German National Library of Economics).

    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 references are entirely missing, you can add them using this form.

    If the full references list an item that is present in RePEc, but the system did not link 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 profile, as there may be some citations waiting for confirmation.

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