An Improved Predictive Accuracy Bound for Averaging Classifiers

John Langford, Matthias W. Seeger, Nimrod MegiddoICML 2001 · OpenReview

Abstract

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.
BibTeX
@inproceedings{langford2001improved,
  author = {John Langford and Matthias W. Seeger and Nimrod Megiddo},
  title = {{An Improved Predictive Accuracy Bound for Averaging Classifiers}},
  booktitle = {International Conference on Machine Learning},
  year = {2001},
  url = {https://openreview.net/forum?id=Sy4AZiWdZB},
}

Loading related content...

Figure