Towards Black-box Iterative Machine Teaching

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space teaching setting, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner’s model. In such scenario, we study how the teacher is still able to teach the learner to achieve a faster convergence rate than the traditional passive learning. We propose an active teacher model that can actively query the learner (i.e., make the learner take exams) for estimating the learner’s status, and provide the sample complexity for both teaching and query, respectively. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.