arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.23561cs.ITcs.LGmath.IT
收藏

无冲突教学维度被VC维度所限制

The No-Clash Teaching Dimension is Bounded by VC Dimension

School of Mathematics and Statistics, Xidian University(西安电子科技大学数学与统计学院)

Jiahua Liu, Benchong Li

AI总结:

本文证明有限概念类的无冲突教学维度不超过VC维度,通过构造压缩方案解决开放性问题。

摘要:

在机器学习理论中,为防止教师与学习者之间的不自然编码方案,引入了无冲突教学维度作为碰撞自由教学的最优复杂性度量。然而,无冲突教学维度是否被VC维所限制仍不清楚。本文针对任何有限概念类,构造大小等于其VC维的片段,通过有序压缩方案识别概念。这些片段自然被用作教学集,可以轻易看出它们满足非冲突条件,即该开放性问题在有限概念类中得到解决。

英文摘要:

In the realm of machine learning theory, to prevent unnatural coding schemes between teacher and learner, No-Clash Teaching Dimension was introduced as provably optimal complexity measure for collusion-free teaching. However, whether No-Clash Teaching Dimension is upper-bounded by Vapnik-Chervonenkis dimension remains unknown. In this paper, for any finite concept class, we construct fragments of size equals to its Vapnik-Chervonenkis dimension which identify concepts through an ordered compression scheme. Naturally, these fragments are used as teaching sets, one can easily see that they satisfy the non-clashing condition, i.e., this open question is resolved for finite concept classes.

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。

↑