An Improved Predictive Accuracy Bound for Averaging Classifiers

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.

• Type: Conference
• Year: 2001
• Where: ICML
• Authors: John Langford, Matthias Seeger, Nimrod Megiddo
• Keywords: ICML 2001, Improved Bound, Machine Learning, Maximum Entropy Discrimination, Popular Averaging Techniques