AdaBoost is Consistent

December, 2006
Report Number: 
Peter L. Bartlett and Mikhail Traskin

The risk, or probability of error, of the classifier produced by the AdaBoost algorithm is investigated. In particular, we consider the stopping strategy to be used in AdaBoost to achieve universal consistency. We show that provided AdaBoost is stopped after $n^{1-\varepsilon}$ iterations---for sample size $n$ and $\varepsilon \in (0,1)$---the sequence of risks of the classifiers it produces approaches the Bayes risk.

PDF File: