PAB-decisions for Boolean and real-valued features

Authors:
Svetlana Anoulova;Paul Fischer;Stefan Pölt;Hans Ulrich Simon
Affiliations:
Lehrstuhl Informatik II, Universität Dortmund, D-4600 Dortmund 50;Lehrstuhl Informatik II, Universität Dortmund, D-4600 Dortmund 50;Lehrstuhl Informatik II, Universität Dortmund, D-4600 Dortmund 50;Lehrstuhl Informatik II, Universität Dortmund, D-4600 Dortmund 50
Venue:
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Year:
1992

Citing 4
Cited 0

Learnability and the Vapnik-Chervonenkis dimension

Journal of the ACM (JACM)
A learning criterion for stochastic rules

COLT '90 Proceedings of the third annual workshop on Computational learning theory
Probably almost Bayes decisions

COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Polynomial learnability of probabilistic concepts with respect to the Kullback-Leibler divergence

COLT '91 Proceedings of the fourth annual workshop on Computational learning theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate the problem of classifying objects which are given by feature vectors with Boolean or real entries. Our aim is to “(efficiently) learn probably almost optimal classifications” from examples. A classical approach in pattern recognition uses empirical estimations of the Bayesian discriminant functions for this purpose. We analyze this approach for different classes of distribution functions: In the Boolean case we look at the k-th order Bahadur-Lazarsfeld expansions and k-th order Chow expansions and in the continuous case at the class of normal distributions. In all cases, we obtain polynomial upper bounds for the required sample size. The bounds for the Boolean case improve and extend results from [FPS91].