Robustness Versus Consistency in Ill-Posed Classification and Regression Problems

Title data

Hable, Robert ; Christmann, Andreas:
Robustness Versus Consistency in Ill-Posed Classification and Regression Problems.
In: Giusti, Antonio ; Ritter, Gunter ; Vichi, Maurizio (ed.): Classification and Data Mining. - Berlin : Springer , 2013 . - pp. 27-35
ISBN 978-3-642-28894-4
DOI: https://doi.org/10.1007/978-3-642-28894-4_4

Official URL:

Abstract in another language

It is well-known from parametric statistics that there can be a goal conflict between efficiency and robustness. However, in so-called ill-posed problems, there is even a goal conflict between consistency and robustness. This particularly applies to certain nonparametric statistical problems such as nonparametric classification and regression problems which are often ill-posed. As an example in statistical machine learning, support vector machines are considered.

Further data

Item Type:	Article in a book
Refereed:	Yes
Keywords:	qualitative robustness; consistency; ill-posed; classification; pattern recognition; regression; universal consistency; kernel methods
Institutions of the University:	Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics > Chair Mathematics VII - Stochastics Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics > Chair Mathematics VII - Stochastics > Chair Mathematics VII - Stochastics - Univ.-Prof. Dr. Andreas Christmann Faculties Faculties > Faculty of Mathematics, Physics und Computer Science Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Mathematics
Result of work at the UBT:	Yes
DDC Subjects:	300 Social sciences > 310 Statistics 500 Science > 510 Mathematics
Date Deposited:	19 Oct 2015 06:24
Last Modified:	19 Oct 2015 07:00
URI:	https://eref.uni-bayreuth.de/id/eprint/20516