Tuning Support Vector Machines for Minimax and Neyman-Pearson Classification
Lists
Only you see this
Abstract
This paper studies the training of support vector machine (SVM) classifiers with respect to the minimax and Neyman-Pearson criteria. In principle, these criteria can be optimized in a straightforward way using a cost-sensitive SVM. In practice, however, because these criteria require especially accurate error estimation, standard techniques for tuning SVM parameters, such as cross-validation, can lead to poor classifier performance. To address this issue, we first prove that the usual cost-sensitive SVM, here called the 2C-SVM, is equivalent to another formulation called the 2\nu-SVM. We then exploit a characterization of the 2\nu-SVM parameter space to develop a simple yet powerful approach to error estimation based on smoothing. In an extensive experimental study, we demonstrate that smoothing significantly improves the accuracy of cross-validation error estimates, leading to dramatic performance gains. Furthermore, we propose coordinate descent strategies that offer significant gains in computational efficiency, with little to no loss in performance.
BibTeX
@article{davenport2010tuning,
author = {Mark A. Davenport and Richard G. Baraniuk and Clayton D. Scott},
title = {{Tuning Support Vector Machines for Minimax and Neyman-Pearson Classification}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2010},
doi = {10.1109/tpami.2010.29},
}Loading related content...