English

Learning Sparse Graphons and the Generalized Kesten-Stigum Threshold

Statistics Theory 2020-06-16 v1 Machine Learning Probability Statistics Theory

Abstract

The problem of learning graphons has attracted considerable attention across several scientific communities, with significant progress over the recent years in sparser regimes. Yet, the current techniques still require diverging degrees in order to succeed with efficient algorithms in the challenging cases where the local structure of the graph is homogeneous. This paper provides an efficient algorithm to learn graphons in the constant expected degree regime. The algorithm is shown to succeed in estimating the rank-kk projection of a graphon in the L2L_2 metric if the top kk eigenvalues of the graphon satisfy a generalized Kesten-Stigum condition.

Keywords

Cite

@article{arxiv.2006.07695,
  title  = {Learning Sparse Graphons and the Generalized Kesten-Stigum Threshold},
  author = {Emmanuel Abbe and Shuangping Li and Allan Sly},
  journal= {arXiv preprint arXiv:2006.07695},
  year   = {2020}
}

Comments

32 pages

R2 v1 2026-06-23T16:18:06.805Z