English

Reconstructing the Geometry of Random Geometric Graphs

Machine Learning 2026-04-10 v3 Probability

Abstract

Random geometric graphs are random graph models defined on metric spaces. Such a model is defined by first sampling points from a metric space and then connecting each pair of sampled points with probability that depends on their distance, independently among pairs. In this work, we show how to efficiently reconstruct the geometry of the underlying space from the sampled graph under the manifold assumption, i.e., assuming that the underlying space is a low dimensional manifold and that the connection probability is a strictly decreasing function of the Euclidean distance between the points in a given embedding of the manifold in RN\mathbb{R}^N. Our work complements a large body of work on manifold learning, where the goal is to recover a manifold from sampled points sampled in the manifold along with their (approximate) distances.

Keywords

Cite

@article{arxiv.2402.09591,
  title  = {Reconstructing the Geometry of Random Geometric Graphs},
  author = {Han Huang and Pakawut Jiradilok and Elchanan Mossel},
  journal= {arXiv preprint arXiv:2402.09591},
  year   = {2026}
}

Comments

Polish the introduction section; include an example for non-identifiability in the setting with step function (hard-disc random geometric graph model)

R2 v1 2026-06-28T14:49:03.514Z