arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.02047cs.LG
收藏

偏好教学

Preference-based Teaching

University of Regina(里贾纳大学);Ruhr-Universität Bochum(波鸿鲁尔大学)

Ziyuan Gao, Christoph Ries, Hans Ulrich Simon, Sandra Zilles

摘要:

我们引入了一种新的教学模式命名为“基于偏好的教学”和相应的复杂性参数-基于偏好的教学维度(PBTD)-代表的最坏情况下的例子的数量需要教任何概念在一个给定的概念类。虽然PBTD符合众所周知的递归教学维(RTD)有限类,它是从根本上不同的无限类:RTD已经成为无限平凡的无限类(如半区间),而PBTD评估合理的小值为广泛的集合无限类,包括类组成的所谓的封闭集w.r.t.一个给定的闭包算子,包括与$\mathbb{N}_0$上的线性集有关的各种类(其RTD最近已经被研究),并包括欧氏半空间类。在提出这些具体的结果之上,我们为读者提供了一个理论框架(组合风味),这有助于推导出PBTD的界限。

英文摘要:

We introduce a new model of teaching named "preference-based teaching" and a corresponding complexity parameter---the preference-based teaching dimension (PBTD)---representing the worst-case number of examples needed to teach any concept in a given concept class. Although the PBTD coincides with the well-known recursive teaching dimension (RTD) on finite classes, it is radically different on infinite ones: the RTD becomes infinite already for trivial infinite classes (such as half-intervals) whereas the PBTD evaluates to reasonably small values for a wide collection of infinite classes including classes consisting of so-called closed sets w.r.t. a given closure operator, including various classes related to linear sets over $\mathbb{N}_0$ (whose RTD had been studied quite recently) and including the class of Euclidean half-spaces. On top of presenting these concrete results, we provide the reader with a theoretical framework (of a combinatorial flavor) which helps to derive bounds on the PBTD.

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。

↑