Some Open Problems in Optimal AdaBoost and Decision Stumps

TL;DR

This paper discusses open problems related to the theoretical understanding of Optimal AdaBoost, especially with decision stumps, aiming to improve convergence analysis, understand hypothesis classes, and explain AdaBoost's practical stability.

Contribution

It identifies key open problems in the theory of Optimal AdaBoost, focusing on decision stumps, and discusses their potential impact on understanding convergence, hypothesis complexity, and AdaBoost's behavior.

Findings

Empirical observations suggest the effective decision stump class is smaller than the total hypothesis class.

Open problems could lead to better convergence rate analysis for finite datasets.

Understanding these problems may clarify AdaBoost's self-control and stability in practice.

Abstract

The significance of the study of the theoretical and practical properties of AdaBoost is unquestionable, given its simplicity, wide practical use, and effectiveness on real-world datasets. Here we present a few open problems regarding the behavior of "Optimal AdaBoost," a term coined by Rudin, Daubechies, and Schapire in 2004 to label the simple version of the standard AdaBoost algorithm in which the weak learner that AdaBoost uses always outputs the weak classifier with lowest weighted error among the respective hypothesis class of weak classifiers implicit in the weak learner. We concentrate on the standard, "vanilla" version of Optimal AdaBoost for binary classification that results from using an exponential-loss upper bound on the misclassification training error. We present two types of open problems. One deals with general weak hypotheses. The other deals with the particular case of decision stumps, as often and commonly used in practice. Answers to the open problems can have immediate significant impact to (1) cementing previously established results on asymptotic convergence properties of Optimal AdaBoost, for finite datasets, which in turn can be the start to any convergence-rate analysis; (2) understanding the weak-hypotheses class of effective decision stumps generated from data, which we have empirically observed to be significantly smaller than the typically obtained class, as well as the effect on the weak learner's running time and previously established improved bounds on the generalization performance of Optimal AdaBoost classifiers; and (3) shedding some light on the "self control" that AdaBoost tends to exhibit in practice.