Stopping conditions for exact computation of leave-one-out error in support vector machines

Authors:
Vojtěch Franc;Pavel Laskov;Klaus-Robert Müller
Affiliations:
Fraunhofer Institute FIRST, Berlin, Germany;Fraunhofer Institute FIRST, Berlin, Germany and University of Tuebingen, Tuebingen, Germany;Fraunhofer Institute FIRST, Berlin, Germany and Technical University of Berlin, Berlin, Germany
Venue:
Proceedings of the 25th international conference on Machine learning
Year:
2008

Citing 11
Cited 1

The nature of statistical learning theory

The nature of statistical learning theory
Making large-scale support vector machine learning practical

Advances in kernel methods
Fast training of support vector machines using sequential minimal optimization

Advances in kernel methods
Alpha seeding for support vector machines

Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
Soft Margins for AdaBoost

Machine Learning
Estimating the Generalization Performance of an SVM Efficiently

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Convex Optimization

Convex Optimization
Improvements to Platt's SMO Algorithm for SVM Classifier Design

Neural Computation
Incremental Support Vector Learning: Analysis, Implementation and Applications

The Journal of Machine Learning Research
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
An efficient method for computing leave-one-out error in support vector machines with Gaussian kernels

IEEE Transactions on Neural Networks

Optimized Cutting Plane Algorithm for Large-Scale Risk Minimization

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new stopping condition for a Support Vector Machine (SVM) solver which precisely reflects the objective of the Leave-One-Out error computation. The stopping condition guarantees that the output on an intermediate SVM solution is identical to the output of the optimal SVM solution with one data point excluded from the training set. A simple augmentation of a general SVM training algorithm allows one to use a stopping criterion equivalent to the proposed sufficient condition. A comprehensive experimental evaluation of our method shows consistent speedup of the exact LOO computation by our method, up to the factor of 13 for the linear kernel. The new algorithm can be seen as an example of constructive guidance of an optimization algorithm towards achieving the best attainable expected risk at optimal computational cost.