Teacher Improves Learning by Selecting a Training Subset

被引：0

作者：

Ma, Yuzhe ^{[1
]}

Nowak, Robert ^{[1
]}

Rigollet, Philippe ^{[2
]}

Zhang, Xuezhou ^{[1
]}

Zhu, Xiaojin ^{[1
]}

机构：

[1] Univ Wisconsin, Madison, WI 53706 USA

[2] MIT, Cambridge, MA 02139 USA

来源：

INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84 | 2018年 / 84卷

关键词：

VC-DIMENSION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页数：10