Limit Cycles of AdaBoost. (arXiv:2209.06928v1 [cs.LG])

The iterative weight update for the AdaBoost machine learning algorithm may
be realized as a dynamical map on a probability simplex. When learning a
low-dimensional data set this algorithm has a tendency towards cycling
behavior, which is the topic of this paper. AdaBoost's cycling behavior lends
itself to direct computational methods that are ineffective in the general,
non-cycling case of the algorithm. From these computational properties we give
a concrete correspondence between AdaBoost's cycling behavior and continued
fractions dynamics. Then …

adaboost arxiv