Minimum Tournaments with the Strong $S_k$-Property and Implications for Teaching
Hans Ulrich Simon

TL;DR
This paper introduces a stronger version of the $S_k$-property in tournaments, explores its theoretical properties, and demonstrates its application in teaching models, showing a significant separation between No-Clash and recursive teaching.
Contribution
It defines the strong $S_k$-property, extends existing results to this new notion, and applies it to construct concept classes that separate teaching models by a logarithmic factor.
Findings
Several results on the $S_k$-property extend to the strong $S_k$-property.
An infinite family of concept classes can be taught with one example in the No-Clash model.
A logarithmic separation between No-Clash and recursive teaching models is established.
Abstract
A tournament is said to have the -property if, for any set of players, there is another player who beats them all. Minimum tournaments having this property have been explored very well in the 1960's and the early 1970's. In this paper, we define a strengthening of the -property that we name "strong -property". We show, first, that several basic results on the weaker notion remain valid for the stronger notion (and the corresponding modification of the proofs requires only little extra-effort). Second, it is demonstrated that the stronger notion has applications in the area of Teaching. Specifically, we present an infinite family of concept classes all of which can be taught with a single example in the No-Clash model of teaching while, in order to teach a class of this family in the recursive model of teaching, order of many examples are required.…
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.
Taxonomy
TopicsAuction Theory and Applications · Machine Learning and Algorithms · Complexity and Algorithms in Graphs
