
TL;DR
This paper establishes a connection between the model-theoretic concept of dp-rank and the combinatorial properties of VC classes, showing that a theory's dp-rank corresponds to interpreting certain maximum VC classes.
Contribution
It provides a new characterization of dp-rank via the interpretation of maximum VC classes, linking model theory and combinatorial geometry.
Findings
Dp-rank corresponds to interpreting maximum VC classes.
A theory has an ICT pattern of depth k iff it interprets a k-maximum VC class.
Bridges model theory with combinatorial properties of VC classes.
Abstract
A theory is shown to have an ICT pattern of depth in variables iff it interprets some -maximum VC class in parameters.
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.
