Exact Minimax Estimation for Phase Synchronization

10/09/2020
by   Chao Gao, et al.
0

We study the phase synchronization problem with 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 the minimax lower bound of estimating z^* under the squared ℓ_2 loss is (1-o(1))σ^2/2p. We also show that both generalized power method and maximum likelihood estimator achieve the error bound (1+o(1))σ^2/2p. Thus, σ^2/2p is the exact asymptotic minimax error of the problem. Our upper bound analysis involves a precise characterization of the statistical property of the power iteration. The lower bound is derived through an application of van Trees' inequality.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

01/07/2021

SDP Achieves Exact Minimax Optimality in Phase Synchronization

We study the phase synchronization problem with noisy measurements Y=z^*...
09/28/2021

Optimal Orthogonal Group Synchronization and Rotation Group Synchronization

We study the statistical estimation problem of orthogonal group synchron...
06/17/2021

Minimax Estimation of Partially-Observed Vector AutoRegressions

To understand the behavior of large dynamical systems like transportatio...
12/01/2020

Minimax bounds for estimating multivariate Gaussian location mixtures

We prove minimax bounds for estimating Gaussian location mixtures on ℝ^d...
05/24/2022

Minimax Optimal Clustering of Bipartite Graphs with a Generalized Power Method

Clustering bipartite graphs is a fundamental task in network analysis. I...
10/19/2020

Use of Uncertain Additional Information in Newsvendor Models

The newsvendor problem is a popular inventory management problem in supp...
06/19/2022

Deterministic Finite-Memory Bias Estimation

In this paper we consider the problem of estimating a Bernoulli paramete...
This week in AI

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