Stability of Unstable Learning Algorithms

Authors:
Don Hush;Clint Scovel;Ingo Steinwart
Affiliations:
CCS-3, Los Alamos National Laboratory, Los Alamos, USA;CCS-3, Los Alamos National Laboratory, Los Alamos, USA;CCS-3, Los Alamos National Laboratory, Los Alamos, USA
Venue:
Machine Learning
Year:
2007

Citing 5
Cited 1

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
Stability and generalization

The Journal of Machine Learning Research
Sparseness of support vector machines

The Journal of Machine Learning Research
Almost-everywhere algorithmic stability and generalization error

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence

A boosting approach for supervised Mahalanobis distance metric learning

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce graphical learning algorithms and use them to produce bounds on error deviance for unstable learning algorithms which possess a partial form of stability. As an application we obtain error deviance bounds for support vector machines (SVMs) with variable offset parameter.