S. Ben-David,
P. M. Long
and Y. Mansour. Agnostic boosting.
Proceedings of the 2001
Conference on Computational Learning Theory.
(Available in Postscript and PDF formats.)
Abstract
We extend the boosting paradigm to the realistic setting of
agnostic learning, that is, to a setting where the training sample is
generated by an arbitrary (unknown) probability distribution over examples
and labels.