arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.04907math.COcs.LG
收藏

关于机器教学中出现的一个组合问题

On a Combinatorial Problem Arising in Machine Teaching

University Of Bergen(卑尔根大学);Charles University(查理大学)

Brigt Håvardstun, Jan Kratochvíl, Joakim Sunde, Jan Arne Telle

AI总结:

本文证明了一个关于机器教学中教学维度最坏情况的猜想,该猜想涉及一致性矩阵包含二进制表示时的情形,结果推广了超立方体边缘等周定理。

摘要:

我们研究了一种机器教学模型,其中教师映射由概念和示例上的大小函数构建。机器教学中的主要问题是任何概念所需的最小示例数,即所谓的教学维度。最近的一篇论文[7]推测,对于该模型,最坏情况(作为概念类大小的函数)发生在一致性矩阵包含从零开始递增的数字的二进制表示时。在本文中,我们证明了他们的猜想。该结果可视为解决超立方体边缘等周问题[12]的定理的推广,我们的证明基于[10]的一个引理。

英文摘要:

We study a model of machine teaching where the teacher mapping is constructed from a size function on both concepts and examples. The main question in machine teaching is the minimum number of examples needed for any concept, the so-called teaching dimension. A recent paper [7] conjectured that the worst case for this model, as a function of the size of the concept class, occurs when the consistency matrix contains the binary representations of numbers from zero and up. In this paper we prove their conjecture. The result can be seen as a generalization of a theorem resolving the edge isoperimetry problem for hypercubes [12], and our proof is based on a lemma of [10].

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑