Experimentally optimal ν in support vector regression for different noise models and parameter settings

Authors:
Athanassia Chalimourda;Bernhard Schölkopf;Alex J. Smola
Affiliations:
Ruhr-Universität Bochum, Institut für Neuroinformatik, D-44780 Bochum, Germany;Max-Planck-Institut for Biological Cybernetics, Spemannstraße 38, D-72076 Tübingen, Germany;Australian National University Canberra, ACT 0200, Australia
Venue:
Neural Networks
Year:
2004

Citing 6
Cited 20

The nature of statistical learning theory

The nature of statistical learning theory
Support vector machines for dynamic reconstruction of a chaotic system

Advances in kernel methods
Support vector regression with ANOVA decomposition kernels

Advances in kernel methods
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Selection of Meta-parameters for Support Vector Regression

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
New Support Vector Algorithms

Neural Computation

A tutorial on support vector regression

Statistics and Computing
Letter to the editor: Experimentally optimal ν in support vector regression for different noise models and parameter settings

Neural Networks
Identification of dynamic diagnostic models with the use of methodology of knowledge discovery in databases

Engineering Applications of Artificial Intelligence
Letters: Statistical criteria for early-stopping of support vector machines

Neurocomputing
Trade-off between accuracy and interpretability: Experience-oriented fuzzy modeling via reduced-set vectors

Computers & Mathematics with Applications
Image Denoising with Kernels Based on Natural Image Relations

The Journal of Machine Learning Research
Bootstrap based pattern selection for support vector regression

PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining
Car assembly line fault diagnosis based on modified support vector classifier machine

Expert Systems with Applications: An International Journal
Prostate cancer localization with multispectral MRI using cost-sensitive support vector machines and conditional random fields

IEEE Transactions on Image Processing
Fuzzy fault diagnosis based on fuzzy robust v-support vector classifier and modified genetic algorithm

Expert Systems with Applications: An International Journal
Car assembly line fault diagnosis based on triangular fuzzy support vector classifier machine and particle swarm optimization

Expert Systems with Applications: An International Journal
Fault diagnosis of car assembly line based on fuzzy wavelet kernel support vector classifier machine and modified genetic algorithm

Expert Systems with Applications: An International Journal
Smooth performance landscapes of the variational Bayesian approach

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
The complex fuzzy system forecasting model based on fuzzy SVM with triangular fuzzy number input and output

Expert Systems with Applications: An International Journal
ϵ-Tube based pattern selection for support vector machines

PAKDD'06 Proceedings of the 10th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
An LSSVR-based algorithm for online system condition prognostics

Expert Systems with Applications: An International Journal
Using genetic algorithms to improve prediction of execution times of ML tasks

HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
The complex fuzzy system forecasting model based on triangular fuzzy robust wavelet υ-support vector machine

Expert Systems with Applications: An International Journal
Car assembly line fault diagnosis model based on triangular fuzzy Gaussian wavelet kernel support vector classifier machine and genetic algorithm

Expert Systems with Applications: An International Journal
Multiple-ν support vector regression based on spectral risk measure minimization

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In Support Vector (SV) regression, a parameter v controls the number of Support Vectors and the number of points that come to lie outside of the so-called ε-insensitive tube. For various noise models and SV parameter settings, we experimentally determine the values of v that lead to the lowest generalization error. We find good agreement with the values that had previously been predicted by a theoretical argument based on a the asymptotic efficiency of a simplified model of SV regression. As a side effect of the experiments, valuable information about the generalization behavior of the remaining SVM parameters and their dependencies is gained. The experimental findings are valid even for complex 'real-world' data sets. Based on our results on the role of the v-SVM parameters, we discuss various model selection methods.