Labeled sample compression schemes for complexes of oriented matroids

10/28/2021
by   Victor Chepoi, et al.
0

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 and the authors and is a step towards the sample compression conjecture – one of the oldest open 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

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2020

Ample completions of OMs and CUOMs

This paper considers completions of COMs (complexes oriented matroids) t...
research
06/27/2022

Sample compression schemes for balls in graphs

One of the open problems in machine learning is whether any set-family o...
research
06/11/2019

Two-dimensional partial cubes

We investigate the structure of two-dimensional partial cubes, i.e., of ...
research
11/29/2018

Unlabeled Compression Schemes Exceeding the VC-dimension

In this note we disprove a conjecture of Kuzmin and Warmuth claiming tha...
research
03/02/2022

First-order logic axiomatization of metric graph theory

The main goal of this note is to provide a First-Order Logic with Betwee...
research
07/18/2018

An Information-theoretic Framework for the Lossy Compression of Link Streams

Graph compression is a data analysis technique that consists in the repl...
research
01/29/2014

Bounding Embeddings of VC Classes into Maximum Classes

One of the earliest conjectures in computational learning theory-the Sam...

Please sign up or login with your details

Forgot password? Click here to reset