1. Unlabeled Compression Schemes Exceeding the VC-dimension
- Author
-
P��lv��lgyi, D��m��t��r and Tardos, G��bor
- Subjects
Computer Science::Machine Learning ,FOS: Computer and information sciences ,Statistics::Machine Learning ,Discrete Mathematics (cs.DM) ,FOS: Mathematics ,Combinatorics (math.CO) ,Machine Learning (cs.LG) - Abstract
In this note we disprove a conjecture of Kuzmin and Warmuth claiming that every family whose VC-dimension is at most d admits an unlabeled compression scheme to a sample of size at most d. We also study the unlabeled compression schemes of the joins of some families and conjecture that these give a larger gap between the VC-dimension and the size of the smallest unlabeled compression scheme for them.
- Published
- 2018
- Full Text
- View/download PDF