The EMS Publishing House is now EMS Press and has its new home at

Please find all EMS Press journals and articles on the new platform.

Mathematical Statistics and Learning

Full-Text PDF (379 KB) | Metadata | Table of Contents | MSL summary
Volume 1, Issue 3/4, 2018, pp. 227–256
DOI: 10.4171/MSL/6

Published online: 2018-09-28

Group synchronization on grids

Emmanuel Abbe[1], Laurent MassouliƩ[2], Andrea Montanari[3], Allan Sly[4] and Nikhil Srivastava[5]

(1) Princeton University, USA
(2) MSR-Inria Joint Centre, Palaiseau, France
(3) Stanford University, USA
(4) Princeton University, USA
(5) University of California, Berkeley, USA

Group synchronization requires to estimate unknown elements $(\boldsymbol{\theta}_v)_{v\in V}$ of a compact group $\mathfrak G$ associated to the vertices of a graph $G=(V,E)$, using noisy observations of the group differences associated to the edges. This model is relevant to a variety of applications ranging from structure from motion in computer vision to graph localization and positioning, to certain families of community detection problems.

We focus on the case in which the graph $G$ is the $d$-dimensional grid. Since the unknowns $\boldsymbol{\theta}_v$ are only determined up to a global action of the group, we consider the following weak recovery question. Can we determine the group difference $\boldsymbol{\theta}_u^{-1}\boldsymbol{\theta}_v$ between far apart vertices $u, v$ better than by random guessing? We prove that weak recovery is possible (provided the noise is small enough) for $d\ge 3$ and, for certain finite groups, for $d\ge 2$. Vice-versa, for some continuous groups, we prove that weak recovery is impossible for $d=2$. Finally, for strong enough noise, weak recovery is always impossible.

Keywords: Graphs, group synchronization, weak recovery, community detection

Abbe Emmanuel, MassouliƩ Laurent, Montanari Andrea, Sly Allan, Srivastava Nikhil: Group synchronization on grids. Math. Stat. Learn. 1 (2018), 227-256. doi: 10.4171/MSL/6