On the optimal parameter choice for ν-support vector machines

Authors:
I. Steinwart
Affiliations:
Modeling, Algorithms, & Informatics Group, Los Alamos Nat. Lab., NM, USA
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2003

Citing 0
Cited 7

Sparseness of support vector machines

The Journal of Machine Learning Research
Support vector classifiers via gradient systems with discontinuous righthand sides

Neural Networks
Variant of Gaussian kernel and parameter setting method for nonlinear SVM

Neurocomputing
Tuning SVM parameters by using a hybrid CLPSO-BFGS algorithm

Neurocomputing
On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation

The Journal of Machine Learning Research
Prostate cancer localization with multispectral MRI using cost-sensitive support vector machines and conditional random fields

IEEE Transactions on Image Processing
Conjugate relation between loss functions and uncertainty sets in classification problems

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.14

Visualization

Abstract

We determine the asymptotically optimal choice of the parameter ν for classifiers of ν-support vector machine (ν-SVM) type which has been introduced by Scholkopf et al. (2000). It turns out that ν should be a close upper estimate of twice the optimal Bayes risk provided that the classifier uses a so-called universal kernel such as the Gaussian RBF kernel. Moreover, several experiments show that this result can be used to implement some modified cross validation procedures which improve standard cross validation for ν-SVMs.