Teaching a black-box learner
Teaching a black-box learner
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
S. Dasgupta;Daniel J. Hsu;Stefanos Poulis;Xiaojin Zhu
中科院分区：
文献类型：
--
作者：
S. Dasgupta;Daniel J. Hsu;Stefanos Poulis;Xiaojin Zhu
一个广泛的教学模型（Goldman＆Kearns，1995; Shinohara＆Miyano，1991; Anthony et al。，1992）呼吁教师提供一组最小的标签示例，这些示例独特地指定了一个目标概念。老师知道学习者的假设课程，这对于现实生活中的方案通常不正确。 ：也就是说，学习者是一个黑匣子。在教学示例中，这是最佳集合的典型近似，我们表明该方案如何用于缩小任何分类者的训练集：也就是说发现训练实例的大约最小子集与整个集合相同的分类器。
One widely-studied model of teaching (Goldman & Kearns, 1995; Shinohara & Miyano, 1991; Anthony et al., 1992) calls for a teacher to provide the minimal set of labeled examples that uniquely specifies a target concept. The assumption is that the teacher knows the learner’s hypothesis class, which is often not true of real-life teaching scenarios. We consider the problem of teaching a learner whose representation and hypothesis class are unknown : that is, the learner is a black box. We find that a teacher who does not interact with the learner can do no better than providing random examples. However, by interacting with the black-box learner, a teacher can efficiently find a set of teaching examples that is a provably good approximation to the optimal set. As an illustration, we show how this scheme can be used to shrink training sets for any family of classifiers: that is, to find an approximately-minimal subset of training instances that yields the same classifier as the entire set.