On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase Synchronization

TL;DR

This paper analyzes the generalized power method for phase synchronization, showing it achieves near-optimal estimation error and linear convergence under minimal noise assumptions, offering a computationally efficient alternative to semidefinite programming.

Contribution

It provides the first error bounds for all GPM iterates matching the Cramér-Rao bound and proves linear convergence to the MLE under broad noise conditions.

Findings

GPM iterates achieve estimation error on the same order as the Cramér-Rao bound.

GPM converges linearly to the MLE with high probability.

The analysis introduces a new error bound for non-convex quadratic optimization.

Abstract

An estimation problem of fundamental interest is that of phase synchronization, in which the goal is to recover a collection of phases using noisy measurements of relative phases. It is known that in the Gaussian noise setting, the maximum likelihood estimator (MLE) has an expected squared $\ell_2$-estimation error that is on the same order as the Cram\'er-Rao lower bound. Moreover, even though the MLE is an optimal solution to a non-convex quadratic optimization problem, it can be found with high probability using semidefinite programming (SDP), provided that the noise power is not too large. In this paper, we study the estimation and convergence performance of a recently-proposed low-complexity alternative to the SDP-based approach, namely, the generalized power method (GPM). Our contribution is twofold. First, we bound the rate at which the estimation error decreases in each iteration of the GPM and use this bound to show that all iterates---not just the MLE---achieve an estimation error that is on the same order as the Cram\'er-Rao bound. Our result holds under the least restrictive assumption on the noise power and gives the best provable bound on the estimation error known to date. It also implies that one can terminate the GPM at any iteration and still obtain an estimator that has a theoretical guarantee on its estimation error. Second, we show that under the same assumption on the noise power as that for the SDP-based method, the GPM will converge to the MLE at a linear rate with high probability. This answers a question raised in [3] and shows that the GPM is competitive in terms of both theoretical guarantees and numerical efficiency with the SDP-based method. At the heart of our convergence rate analysis is a new error bound for the non-convex quadratic optimization formulation of the phase synchronization problem, which could be of independent interest.