Tightness of the maximum likelihood semidefinite relaxation for angular synchronization

Afonso S. Bandeira (1) , Nicolas Boumal (2, 3) , Amit Singer (4)

1 MIT - Massachusetts Institute of Technology
2 SIERRA - Statistical Machine Learning and Parsimony
3 LIENS - Laboratoire d'informatique de l'école normale supérieure
4 Princeton University

Many 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. Semidefinite relaxations are among the most popular. Sometimes, the relaxations turn out to be tight. In this paper, we study such a phenomenon. The angular synchronization problem consists in estimating a collection of n phases, given noisy measurements of some of the pairwise relative phases. The MLE for the angular synchronization problem is the solution of a (hard) non-bipartite Grothendieck problem over the complex numbers. It is known that its semidefinite relaxation enjoys worst-case approximation guarantees. In this paper, we consider a stochastic model on the input of that semidefinite relaxation. We assume there is a planted signal (corresponding to a ground truth set of phases) and the measurements are corrupted with random noise. Even though the MLE does not coincide with the planted signal, we show that the relaxation is, with high probability, tight. This holds even for high levels of noise. This analysis explains, for the interesting case of angular synchronization, a phenomenon which has been observed without explanation in many other settings. Namely, the fact that even when exact recovery of the ground truth is impossible, semidefinite relaxations for the MLE tend to be tight (in favorable noise regimes).

Mots clés: Angular Synchronization; Semidefinite programming; Tightness of convex relaxation; Maximum likelihood estimation

Domaines: Complexité [cs.CC]; Statistiques [math.ST]; Optimisation et contrôle [math.OC]; Géométrie différentielle [math.DG]; Imagerie médicale; Théorie de l'information [cs.IT]; Analyse numérique [cs.NA]

Afonso S. Bandeira, Nicolas Boumal, Amit Singer. Tightness of the maximum likelihood semidefinite relaxation for angular synchronization. 2015. ⟨hal-01240565⟩