A Framework for Average Case Analysis of Conjunctive Learning Algorithms

Authors:
Michael J. Pazzani;Wendy Sarrett
Affiliations:
Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92717 USA. PAZZANI@ICS.UCI.EDU;Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92717 USA. SARRETT@ICS.UCI.EDU
Venue:
Machine Learning
Year:
1992

Citing 0
Cited 6

On the Optimality of the Simple Bayesian Classifier under Zero-One Loss

Machine Learning - Special issue on learning with probabilistic representations
Effects of domain characteristics on instance-based learning algorithms

Theoretical Computer Science - Selected papers in honour of Setsuo Arikawa
Average-case analysis of a nearest neighbor algorthim

IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 2
An average-case analysis of the k-nearest neighbor classifier for noisy domains

IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
A complete and tight average-case analysis of learning monomials

STACS'99 Proceedings of the 16th annual conference on Theoretical aspects of computer science
Towards the discovery of reliable biomarkers from gene-expression profiles: an iterative constraint satisfaction learning approach

SETN'10 Proceedings of the 6th Hellenic conference on Artificial Intelligence: theories, models and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an approach to modeling the average case behavior of learning algorithms. Our motivation is to predict the expected accuracy of learning algorithms as a function of the number of training examples. We apply this framework to a purely empirical learning algorithm, (the one-sided algorithm for pure conjunctive concepts), and to an algorithm that combines empirical and explanation-based learning. The model is used to gain insight into the behavior of these algorithms on a series of problems. Finally, we evaluate how well the average case model performs when the training examples violate the assumptions of the model.