Diameter-Based Active Learning

[edit]

Christopher Tosh, Sanjoy Dasgupta ;
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3444-3452, 2017.

Abstract

To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.

Related Material