Open Access
2021 On the estimation of latent distances using graph distances
Ery Arias-Castro, Antoine Channarond, Bruno Pelletier, Nicolas Verzelen
Electron. J. Statist. 15(1): 722-747 (2021). DOI: 10.1214/21-EJS1801

Abstract

We are given the adjacency matrix of a geometric graph and the task of recovering the latent positions. We study one of the most popular approaches which consists in using the graph distances and derive error bounds under various assumptions on the link function. In the simplest case where the link function is proportional to an indicator function, the bound matches an information lower bound that we derive.

Citation

Download Citation

Ery Arias-Castro. Antoine Channarond. Bruno Pelletier. Nicolas Verzelen. "On the estimation of latent distances using graph distances." Electron. J. Statist. 15 (1) 722 - 747, 2021. https://doi.org/10.1214/21-EJS1801

Information

Received: 1 August 2020; Published: 2021
First available in Project Euclid: 21 January 2021

Digital Object Identifier: 10.1214/21-EJS1801

Keywords: graph distances , graph embedding , Latent positions , multidimensional scaling , Random geometric graphs

Vol.15 • No. 1 • 2021
Back to Top