English

A Geometric Approach to Sample Compression

Machine Learning 2014-02-04 v1 Combinatorics Geometric Topology Machine Learning

Abstract

The Sample Compression Conjecture of Littlestone & Warmuth has remained unsolved for over two decades. This paper presents a systematic geometric investigation of the compression of finite maximum concept classes. Simple arrangements of hyperplanes in Hyperbolic space, and Piecewise-Linear hyperplane arrangements, are shown to represent maximum classes, generalizing the corresponding Euclidean result. A main result is that PL arrangements can be swept by a moving hyperplane to unlabeled d-compress any finite maximum class, forming a peeling scheme as conjectured by Kuzmin & Warmuth. A corollary is that some d-maximal classes cannot be embedded into any maximum class of VC dimension d+k, for any constant k. The construction of the PL sweeping involves Pachner moves on the one-inclusion graph, corresponding to moves of a hyperplane across the intersection of d other hyperplanes. This extends the well known Pachner moves for triangulations to cubical complexes.

Keywords

Cite

@article{arxiv.0911.3633,
  title  = {A Geometric Approach to Sample Compression},
  author = {Benjamin I. P. Rubinstein and J. Hyam Rubinstein},
  journal= {arXiv preprint arXiv:0911.3633},
  year   = {2014}
}

Comments

37 pages, 18 figures, submitted to the Journal of Machine Learning Research

R2 v1 2026-06-21T14:13:23.591Z