Gradient-Based Adaptation of General Gaussian Kernels

Authors:
Tobias Glasmachers;Christian Igel
Affiliations:
Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany;Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany
Venue:
Neural Computation
Year:
2005

Citing 7
Cited 20

The nature of statistical learning theory

The nature of statistical learning theory
Choosing Multiple Parameters for Support Vector Machines

Machine Learning
Optimization of the kernel functions in a probabilistic neural network analyzing the local pattern distribution

Neural Computation
Using the Fisher Kernel Method to Detect Remote Protein Homologies

Proceedings of the Seventh International Conference on Intelligent Systems for Molecular Biology
Radius margin bounds for support vector machines with the RBF kernel

Neural Computation
Evolutionary tuning of multiple SVM parameters

Neurocomputing
Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms

IEEE Transactions on Neural Networks

Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Effects of SVM parameter optimization on discrimination and calibration for post-procedural PCI mortality

Journal of Biomedical Informatics
Second-order smo improves svm online and active learning

Neural Computation
Shark

The Journal of Machine Learning Research
A novel LS-SVMs hyper-parameter selection based on particle swarm optimization

Neurocomputing
Uncertainty Handling in Model Selection for Support Vector Machines

Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Gaussian kernel optimization for pattern classification

Pattern Recognition
Kernel Trees for Support Vector Machines

IEICE - Transactions on Information and Systems
A majorization-minimization algorithm for (multiple) hyperparameter learning

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Learning by local kernel polarization

Neurocomputing
Experiments on kernel tree support vector machines for text categorization

PAKDD'07 Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data mining
Feature selection for SVM via optimization of kernel polarization with Gaussian ARD kernels

Expert Systems with Applications: An International Journal
Exponential natural evolution strategies

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Learning Translation Invariant Kernels for Classification

The Journal of Machine Learning Research
Learning general Gaussian kernel hyperparameters of SVMs using optimization on symmetric positive-definite matrices manifold

Pattern Recognition Letters
Evolutionary optimization of sequence kernels for detection of bacterial gene starts

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Learning bounds for support vector machines with learned kernels

COLT'06 Proceedings of the 19th annual conference on Learning Theory
An experimental study of the combination of meta-learning with particle swarm algorithms for SVM parameter selection

ICCSA'12 Proceedings of the 12th international conference on Computational Science and Its Applications - Volume Part III
Optimizing the Gaussian kernel function with the formulated kernel target alignment criterion for two-class pattern classification

Pattern Recognition
Prediction of dissolved oxygen content in river crab culture based on least squares support vector regression optimized by improved particle swarm optimization

Computers and Electronics in Agriculture

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gradient-based optimizing of gaussian kernel functions is considered. The gradient for the adaptation of scaling and rotation of the input space is computed to achieve invariance against linear transformations. This is done by using the exponential map as a parameterization of the kernel parameter manifold. By restricting the optimization to a constant trace subspace, the kernel size can be controlled. This is, for example, useful to prevent overfitting when minimizing radius-margin generalization performance measures. The concepts are demonstrated by training hard margin support vector machines on toy data.