Empirical margin distributions and bounding the generalization error of combined classifiers

Details Empirical margin distributions and bounding the generalization error of combined classifiers Empirical margin distributions and bounding the generalization error of combined classifiers

2004-05-18

arxiv.org/abs/math/0405343v1

2002 Ann. Statist. Vol. 30 No. 1

Mathematics

Probability

35 pages, 1 figure

Scientific paper

We prove new probabilistic upper bounds on generalization error of complex classifiers that are combinations of simple classifiers. Such combinations could be implemented by neural networks or by voting methods of combining the classifiers, such as boosting and bagging. The bounds are in terms of the empirical distribution of the margin of the combined classifier. They are based on the methods of the theory of Gaussian and empirical processes (comparison inequalities, symmetrization method, concentration inequalities) and they improve previous results of Bartlett (1998) on bounding the generalization error of neural networks in terms of l_1-norms of the weights of neurons and of Schapire, Freund, Bartlett and Lee (1998) on bounding the generalization error of boosting. We also obtain rates of convergence in Levy distance of empirical margin distribution to the true margin distribution uniformly over the classes of classifiers and prove the optimality of these rates.

Affiliated with

Also associated with

No associations

Rating

Empirical margin distributions and bounding the generalization error of combined classifiers does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Empirical margin distributions and bounding the generalization error of combined classifiers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Empirical margin distributions and bounding the generalization error of combined classifiers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-366490