Call for NIPS 2008 Kernel Learning Workshop Submissions
Document Actions
W. N Street and O. L Mangasarian (1998)
Improved Generalization via Tolerant Training
Journal of Optimization Theory and Applications, 96:259-279.
Theoretical and computational justification is given for improved generalization when the training set is learned with less accuracy. The model used for this investigation is a simple linear one. It is shown that learning a training set with a tolerance $\tau$ improves generalization, over zero-tolerance training, for any testing set satisfying a certain closeness condition to the training set.