Tight combinatorial generalization bounds for threshold conjunction rules

Authors:
Konstantin Vorontsov;Andrey Ivahnenko
Affiliations:
Dorodnycin Computing Center RAS, Moscow, Russia;Moscow Institute of Physics and Technology, Moscow, Russia
Venue:
PReMI'11 Proceedings of the 4th international conference on Pattern recognition and machine intelligence
Year:
2011

Citing 5
Cited 1

C4.5: programs for machine learning

C4.5: programs for machine learning
An Exact Probability Metric for Decision Tree Splitting and Stopping

Machine Learning
A simple, fast, and effective rule learner

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
ROC `n' Rule Learning—Towards a Better Understanding of Covering Algorithms

Machine Learning
Bagging, boosting, and C4.S

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

A combinatorial approach to hypothesis similarity in generalization bounds

Pattern Recognition and Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a combinatorial technique for obtaining tight data dependent generalization bounds based on a splitting and connectivity graph (SC-graph) of the set of classifiers. We apply this approach to a parametric set of conjunctive rules and propose an algorithm for effective SC-bound computation. Experiments on 6 data sets from the UCI ML Repository show that SC-bound helps to learn more reliable rule-based classifiers as compositions of less overfitted rules.