The No-Clash Teaching Dimension is Bounded by VC Dimension
Jiahua Liu, Benchong Li

TL;DR
This paper proves that for finite concept classes, the No-Clash Teaching Dimension is bounded by the VC dimension by constructing specific teaching sets that satisfy non-clashing conditions.
Contribution
It demonstrates that the No-Clash Teaching Dimension is upper-bounded by VC dimension for finite concept classes through explicit construction.
Findings
Constructed fragments of size equal to VC dimension that identify concepts.
These fragments serve as non-clashing teaching sets.
Resolved the open question for finite concept classes.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
