Labeled sample compression schemes for complexes of oriented matroids
Not on the map. Why?
Abstract (arXiv)
We show that the topes of a complex of oriented matroids (abbreviated COM) of VC-dimension d admit a proper labeled sample compression scheme of size d. This considerably extends results of Moran and Warmuth on ample classes, of Ben-David and Litman on affine arrangements of hyperplanes, and of the authors on complexes of uniform oriented matroids, and is a step towards the sample compression conjecture -- one of the oldest open problems in computational learning theory. On the one hand, our approach exploits the rich combinatorial cell structure of COMs via oriented matroid theory. On the other hand, viewing tope graphs of COMs as partial cubes creates a fruitful link to metric graph theory.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 12 of its 81 references that are in the map. First posted on arXiv 28 Oct 2021.
Builds on
12 of 81 references.
References · 12
- 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
- 2017Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networkscited by 311
- 2019Complexity of Linear Regions in Deep Networkscited by 167
- 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 161
- 2015Sample compression schemes for VC classescited by 47
- 2020On transversality of bent hyperplane arrangements and the topological expressiveness of ReLU neural networkscited by 35
- 2018Unlabeled sample compression schemes and corner peelings for ample and maximum classescited by 16
- 2015Labeled compression schemes for extremal classescited by 11
- 2018Unlabeled Compression Schemes Exceeding the VC-dimensioncited by 6
- 2014Bounding Embeddings of VC Classes into Maximum Classescited by 5
- 2018Hyperplane Neural Codes and the Polar Complexcited by 2
- 2021Sweeps, polytopes, oriented matroids, and allowable graphs of permutationscited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 2; 2026: 1.
7 papers.
- 2022Sample compression schemes for balls in graphscited by 9
- 2023Non-Clashing Teaching Maps for Balls in Graphscited by 6
- 2024Dual VC Dimension Obstructs Sample Compression by Embeddingscited by 5
- 2025Spherical dimensioncited by 4
- 2026An Optimal Sauer Lemma Over k-ary Alphabetscited by 4
- 2024Efficient Algorithms for Learning Monophonic Halfspaces in Graphscited by 3
- 2025Efficient Algorithms for Learning and Compressing Monophonic Halfspaces in Graphscited by 1
- 2026An Optimal Sauer Lemma Over k-ary Alphabets14 Apr 2026
- 2025Efficient Algorithms for Learning and Compressing Monophonic Halfspaces in Graphs29 Jun 2025
- 2025Spherical dimension13 Mar 2025
- 2024Dual VC Dimension Obstructs Sample Compression by Embeddings27 May 2024
- 2024Efficient Algorithms for Learning Monophonic Halfspaces in Graphs1 May 2024
- 2023Non-Clashing Teaching Maps for Balls in Graphs6 Sep 2023
- 2022Sample compression schemes for balls in graphs27 Jun 2022