Minimax support vector machines

Mark A. Davenport, Richard G. Baraniuk, Clayton D. Scott

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations


We study the problem of designing support vector machine (SVM) classifiers that minimize the maximum of the false alarm and miss rates. This is a natural classification setting in the absence of prior information regarding the relative costs of the two types of errors or true frequency of the two classes in nature. Examining two approaches - one based on shifting the offset of a conventionally trained SVM, the other based on the introduction of class-specific weights - we find that when proper care is taken in selecting the weights, the latter approach significantly outperforms the strategy of shifting the offset. We also find that the magnitude of this improvement depends chiefly on the accuracy of the error estimation step of the training procedure. Furthermore, comparison with the minimax probability machine (MPM) illustrates that our SVM approach can outperform the MPM even when the MPM parameters are set by an oracle.

Original languageEnglish (US)
Title of host publication2007 IEEE/SP 14th Workshop on Statistical Signal Processing, SSP 2007, Proceedings
Number of pages5
StatePublished - 2007
Event2007 IEEE/SP 14th WorkShoP on Statistical Signal Processing, SSP 2007 - Madison, WI, United States
Duration: Aug 26 2007Aug 29 2007

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings


Other2007 IEEE/SP 14th WorkShoP on Statistical Signal Processing, SSP 2007
Country/TerritoryUnited States
CityMadison, WI

ASJC Scopus subject areas

  • Signal Processing


Dive into the research topics of 'Minimax support vector machines'. Together they form a unique fingerprint.

Cite this