Teaching a blackbox learner
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:15471555, 2019.
Abstract
One widelystudied model of teaching calls for a teacher to provide the minimal set of labeled examples that uniquely specifies a target concept. The assumption is that the teacher knows the learner’s hypothesis class, which is often not true of reallife teaching scenarios. We consider the problem of teaching a learner whose representation and hypothesis class are unknown—that is, the learner is a black box. We show that a teacher who does not interact with the learner can do no better than providing random examples. We then prove, however, that with interaction, a teacher can efficiently find a set of teaching examples that is a provably good approximation to the optimal set. As an illustration, we show how this scheme can be used to shrink training sets for any family of classifiers: that is, to find an approximatelyminimal subset of training instances that yields the same classifier as the entire set.
Related Material


