BriefGPT.xyz
Feb, 2018
通过选择训练子集提高学习效果的教师
Teacher Improves Learning by Selecting a Training Subset
HTML
PDF
Yuzhe Ma, Robert Nowak, Philippe Rigollet, Xuezhou Zhang, Xiaojin Zhu
TL;DR
本文提出了一个算法，通过寻找超级教学集来让学习者在少量的数据上表现得更好，该算法在回归和分类问题中表现良好，并在高斯分布的均值的最大似然估计和1D大边界分类器上提供超级教学保证。
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
→