Loading...
conference paper
An Improved Predictive Accuracy Bound for Averaging Classifiers
2001
Proceedings of the 18th International Conference on Machine Learning
We present an improved bound on the difference between training and test errors for voting classifiers. This improved averaging bound provides a theoretical justification for popular averaging techniques such as Bayesian classification, Maximum Entropy discrimination, Winnow and Bayes point machines and has implications for learning algorithm design.
Loading...
Name
averaging_icml.pdf
Access type
openaccess
Size
197.22 KB
Format
Adobe PDF
Checksum (MD5)
4f8bf5c30a31d5d6c6e663b398253e7f