Skip to main content

Tightness of the maximum likelihood semidefinite relaxation for angular synchronization

Author(s): Bandeira, Afonso S.; Boumal, Nicolas; Singer, Amit

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr15m23
Abstract: Maximum likelihood estimation problems are, in general, intractable optimization problems. As a result, it is common to approximate the maximum likelihood estimator (MLE) using convex relaxations. In some cases, the relaxation is tight: it recovers the true MLE. Most tightness proofs only apply to situations where the MLE exactly recovers a planted solution (known to the analyst). It is then sufficient to establish that the optimality conditions hold at the planted signal. In this paper, we study an estimation problem (angular synchronization) for which the MLE is not a simple function of the planted solution, yet for which the convex relaxation is tight. To establish tightness in this context, the proof is less direct because the point at which to verify optimality conditions is not known explicitly. Angular synchronization consists in estimating a collection of n phases, given noisy measurements of the pairwise relative phases. The MLE for angular synchronization is the solution of a (hard) nonbipartite Grothendieck problem over the complex numbers. We consider a stochastic model for the data: a planted signal (that is, a ground truth set of phases) is corrupted with non-adversarial random noise. Even though the MLE does not coincide with the planted signal, we show that the classical semidefinite relaxation for it is tight, with high probability. This holds even for high levels of noise.
Publication Date: May-2017
Electronic Publication Date: 8-Aug-2016
Citation: Bandeira, Afonso S., Boumal, Nicolas, Singer, Amit. (2017). Tightness of the maximum likelihood semidefinite relaxation for angular synchronization. Mathematical Programming, 163 (1-2), 145 - 167. doi:10.1007/s10107-016-1059-6
DOI: doi:10.1007/s10107-016-1059-6
ISSN: 0025-5610
EISSN: 1436-4646
Pages: 145 - 167
Type of Material: Journal Article
Journal/Proceeding Title: Mathematical Programming
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.