SDP Achieves Exact Minimax Optimality in Phase Synchronization

by   Chao Gao, et al.

We study the phase synchronization problem with noisy measurements Y=z^*z^*H+σ W∈ℂ^n× n, where z^* is an n-dimensional complex unit-modulus vector and W is a complex-valued Gaussian random matrix. It is assumed that each entry Y_jk is observed with probability p. We prove that an SDP relaxation of the MLE achieves the error bound (1+o(1))σ^2/2np under a normalized squared ℓ_2 loss. This result matches the minimax lower bound of the problem, and even the leading constant is sharp. The analysis of the SDP is based on an equivalent non-convex programming whose solution can be characterized as a fixed point of the generalized power iteration lifted to a higher dimensional space. This viewpoint unifies the proofs of the statistical optimality of three different methods: MLE, SDP, and generalized power method. The technique is also applied to the analysis of the SDP for ℤ_2 synchronization, and we achieve the minimax optimal error (-(1-o(1))np/2σ^2) with a sharp constant in the exponent.



page 1

page 2

page 3

page 4


Exact Minimax Estimation for Phase Synchronization

We study the phase synchronization problem with measurements Y=z^*z^*H+σ...

Optimal Orthogonal Group Synchronization and Rotation Group Synchronization

We study the statistical estimation problem of orthogonal group synchron...

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation

We study stochastic approximation procedures for approximately solving a...

Sharp optimal recovery in the Two Component Gaussian Mixture Model

In this paper, we study the problem of clustering in the Two component G...

Orthogonal Group Synchronization with Incomplete Measurements: Error Bounds and Linear Convergence of the Generalized Power Method

Group synchronization refers to estimating a collection of group element...

Minimax bounds for estimating multivariate Gaussian location mixtures

We prove minimax bounds for estimating Gaussian location mixtures on ℝ^d...

Minimax Estimation of Partially-Observed Vector AutoRegressions

To understand the behavior of large dynamical systems like transportatio...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.