Modeling decision tree performance with the power law

Lewis J. Frey, Douglas H. Fisher
Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics, PMLR R2, 1999.

Abstract

This paper discusses the use of a power law to predict decision tree performance. Power laws are fit to learning curves of decision trees trained on data sets from the UCI repository. The learning curves are generated by training C4.5 on different size training sets. The power law predicts diminishing returns in terms of error rate as training set size increase. By characterizing the learning curve with a power law, the error rate for a given size training set can be projected. This projection can be used in estimating the amount of data needed to achieve an acceptable error rate, and the cost effectiveness of further data collection.

Cite this Paper


BibTeX
@InProceedings{pmlr-vR2-frey99a, title = {Modeling decision tree performance with the power law}, author = {Frey, Lewis J. and Fisher, Douglas H.}, booktitle = {Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics}, year = {1999}, editor = {Heckerman, David and Whittaker, Joe}, volume = {R2}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r2/frey99a/frey99a.pdf}, url = {https://proceedings.mlr.press/r2/frey99a.html}, abstract = {This paper discusses the use of a power law to predict decision tree performance. Power laws are fit to learning curves of decision trees trained on data sets from the UCI repository. The learning curves are generated by training C4.5 on different size training sets. The power law predicts diminishing returns in terms of error rate as training set size increase. By characterizing the learning curve with a power law, the error rate for a given size training set can be projected. This projection can be used in estimating the amount of data needed to achieve an acceptable error rate, and the cost effectiveness of further data collection.}, note = {Reissued by PMLR on 20 August 2020.} }
Endnote
%0 Conference Paper %T Modeling decision tree performance with the power law %A Lewis J. Frey %A Douglas H. Fisher %B Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 1999 %E David Heckerman %E Joe Whittaker %F pmlr-vR2-frey99a %I PMLR %U https://proceedings.mlr.press/r2/frey99a.html %V R2 %X This paper discusses the use of a power law to predict decision tree performance. Power laws are fit to learning curves of decision trees trained on data sets from the UCI repository. The learning curves are generated by training C4.5 on different size training sets. The power law predicts diminishing returns in terms of error rate as training set size increase. By characterizing the learning curve with a power law, the error rate for a given size training set can be projected. This projection can be used in estimating the amount of data needed to achieve an acceptable error rate, and the cost effectiveness of further data collection. %Z Reissued by PMLR on 20 August 2020.
APA
Frey, L.J. & Fisher, D.H.. (1999). Modeling decision tree performance with the power law. Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R2 Available from https://proceedings.mlr.press/r2/frey99a.html. Reissued by PMLR on 20 August 2020.

Related Material