Iterative Weak Learnability and Multiclass AdaBoost

摘要

We propose an efficient boosting algorithm for multiclass classification, called AdaBoost.Iter, that extends SAMME and AdaBoost. The algorithm iteratively applies the weak learnability condition of SAMME to eliminate classes to find the correct classificiation. The iterative weak learnability is a sufficient and necessary condition for boostability, but it is also easier to validate than the EOR criterion of AdaBoost.MM \citeMukherjeeSchapire2013. We show that the training error of AdaBoost.Iter vanishes at the exponential rate, while the generalization error converges to zero at the same rate as AdaBoost. AdaBoost.Iter numerically outperforms SAMME and achieves performance comparable to AdaBoost.MM on benchmark datasets.