TY - GEN
T1 - Towards black-box iterative machine teaching
AU - Liu, Weiyang
AU - Dai, Bo
AU - Li, Xingguo
AU - Liu, Zhen
AU - Rehg, James M.
AU - Song, Le
N1 - Publisher Copyright:
© Copyright 2018 by the author(s).
PY - 2018
Y1 - 2018
N2 - In this paper, we make an important step towards the black-box machine teaching by con-sidering the cross-space machine teaching, 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 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 provably guide the learner to achieve faster convergence. The sample complexities for both teaching and query are provided. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.
AB - In this paper, we make an important step towards the black-box machine teaching by con-sidering the cross-space machine teaching, 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 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 provably guide the learner to achieve faster convergence. The sample complexities for both teaching and query are provided. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.
UR - http://www.scopus.com/inward/record.url?scp=85057240048&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85057240048&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85057240048
T3 - 35th International Conference on Machine Learning, ICML 2018
SP - 4911
EP - 4928
BT - 35th International Conference on Machine Learning, ICML 2018
A2 - Dy, Jennifer
A2 - Krause, Andreas
PB - International Machine Learning Society (IMLS)
T2 - 35th International Conference on Machine Learning, ICML 2018
Y2 - 10 July 2018 through 15 July 2018
ER -