Authors: Christmann, Andreas
Steinwart, Ingo
Title: On Robustness Properties of Convex Risk Minimization Methods for Pattern Recognition
Language (ISO): en
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.
Subject Headings: AdaBoost loss function
influence function
kernel logistic regression
robustness
sensitivity curve
statistical learning
support vector machine
total variation
URI: http://hdl.handle.net/2003/4977
http://dx.doi.org/10.17877/DE290R-15035
Issue Date: 2003
Publisher: Universitätsbibliothek Dortmund
Appears in Collections:Sonderforschungsbereich (SFB) 475

Files in This Item:
File Description SizeFormat 
15_03.pdfDNB693.83 kBAdobe PDFView/Open
tr15-03.ps1.13 MBPostscriptView/Open


This item is protected by original copyright



All resources in the repository are protected by copyright.