Teacher Improves Learning by Selecting a Training Subset
Machine Learning
2018-02-27 v1 Artificial Intelligence
Machine Learning
Abstract
We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a mixed-integer nonlinear programming-based algorithm to find a super teaching set. Empirical experiments show that our algorithm is able to find good super-teaching sets for both regression and classification problems.
Cite
@article{arxiv.1802.08946,
title = {Teacher Improves Learning by Selecting a Training Subset},
author = {Yuzhe Ma and Robert Nowak and Philippe Rigollet and Xuezhou Zhang and Xiaojin Zhu},
journal= {arXiv preprint arXiv:1802.08946},
year = {2018}
}
Comments
AISTATS 2018