使用成员查询和对比示例学习洗牌理想

中文摘要 AI 辅助

本文研究了使用成员查询以及对比查询（一种成员查询形式，不仅揭示所选单词 $w$ 是否属于目标语言，而且在 $w$ 不属于目标语言时，还提供一个属于目标语言的最相似单词 $w'$）来学习洗牌理想的问题。对于这两种设置，研究表明即使是一些非常简单的洗牌理想类别也无法被高效学习。相比之下，我们获得了满足某些结构条件的洗牌理想类别的正面可学习性结果。在成员查询的情况下，这些结构条件与先前研究的普遍单词概念相关，并提出了单词组合学中的新问题。在对比查询的情况下，结构条件与按短字典序排列的单词集合的分区有关。

英文摘要

This paper studies learning of shuffle ideals with membership queries as well as with contrastive queries---a form of membership query that reveals not only whether a selected word $w$ is in the target language or not, but also provides a most similar word $w'$ that belongs to the target language if %and only if $w$ does not. For both settings, it is shown that even some very simple classes of shuffle ideals cannot be learned efficiently. By contrast, we obtain positive learnability results for classes of shuffle ideals that meet certain structural conditions. In the case of membership queries, these structural conditions are related to the previously studied notion of universal words, and raise new questions in word combinatorics. In the case of contrastive queries, the structural conditions relate to partitioning sets of words that are listed in shortlex order.

发表机构

• University of Regina（里贾纳大学）
• Politecnico di Milano（米兰理工大学）
• CNR-IEIIT（意大利国家研究委员会-信息工程与信息技术研究所）
• Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）

机构由 AI 辅助整理，请以论文原文为准。