PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On Generalization Error Bounds Using Unlabeled Data
Matti Kääriäinen
(2005) Technical Report. University of Helsinki, Helsinki, Finland.


We present two new methods for obtaining generalization error bounds in a semi-supervised setting. Both methods are based on approximating the disagreement probability of pairs of classifiers using unlabeled data. The first method works in the realizable case. It suggests how the ERM principle can be refined using unlabeled data and has provable optimality guarantees when the number of unlabeled examples is large. Furthermore, the technique extends easily to cover active learning. A downside is that the method is of little use in practice due to its limitation to the realizable case. The idea in our second method is to use unlabeled data to transform bounds for randomized classifiers into bounds for simpler deterministic classifiers. As a concrete example of how the general method works in practice, we apply it to a bound based on cross-validation. The result is a semi-supervised bound for classifiers learned based on all the labeled data. The bound is easy to implement and apply and should be tight whenever cross-validation makes sense. Applying the bound to SVMs on the MNIST benchmark data set gives results that suggest that the bound may be tight enough to be useful in practice.

Postscript - Requires a viewer, such as GhostView
EPrint Type:Monograph (Technical Report)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:956
Deposited By:Matti Kääriäinen
Deposited On:07 March 2005