On robustness properties of convex risk minimization methods for pattern recognition

Andreas Christmann and Ingo Steinwart

No 2003,15, Technical Reports from Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen

Abstract: The paper brings together methods from two disciplines: machine learning theory and robust statistics. Robustness properties of machine learning methods based on convex risk minimization are investigated for the problem of pattern recognition. Assumptions are given for the existence of the influence function of the classifiers and for bounds of the influence function. Kernel logistic regression, support vector machines, least squares and the AdaBoost loss function are treated as special cases. A sensitivity analysis of the support vector machine is given.

Keywords: AdaBoost loss function; influence function; kernel logistic regression; robustness; sensitivity curve; statistical learning; support vector machine; total variation (search for similar items in EconPapers)
Date: 2003
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/49356/1/369860896.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:sfb475:200315

Access Statistics for this paper

More papers in Technical Reports from Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().