Dynamic angular synchronization under smoothness constraints

TL;DR

This paper introduces a dynamic angular synchronization framework that accounts for evolving angles and measurement graphs over time, providing algorithms with theoretical guarantees for accurate joint estimation under smoothness assumptions.

Contribution

It proposes three algorithms for dynamic angular synchronization with non-asymptotic recovery guarantees, extending static methods to time-evolving scenarios with sparse and noisy data.

Findings

MSE converges to zero as T increases under mild conditions.

Algorithms perform well even with sparse, disconnected graphs.

Theoretical guarantees hold under large, increasing noise levels.

Abstract

Given an undirected measurement graph $\mathcal{H} = ([n], \mathcal{E})$, the classical angular synchronization problem consists of recovering unknown angles $\theta_1^*,\dots,\theta_n^*$ from a collection of noisy pairwise measurements of the form $(\theta_i^* - \theta_j^*) \mod 2\pi$, for all $\{i,j\} \in \mathcal{E}$. This problem arises in a variety of applications, including computer vision, time synchronization of distributed networks, and ranking from pairwise comparisons. In this paper, we consider a dynamic version of this problem where the angles, and also the measurement graphs evolve over $T$ time points. Assuming a smoothness condition on the evolution of the latent angles, we derive three algorithms for joint estimation of the angles over all time points. Moreover, for one of the algorithms, we establish non-asymptotic recovery guarantees for the mean-squared error (MSE) under different statistical models. In particular, we show that the MSE converges to zero as $T$ increases under milder conditions than in the static setting. This includes the setting where the measurement graphs are highly sparse and disconnected, and also when the measurement noise is large and can potentially increase with $T$. We complement our theoretical results with experiments on synthetic data.