Exact Minimax Estimation for Phase Synchronization
Statistics Theory
2021-01-08 v2 Optimization and Control
Statistics Theory
Abstract
We study the phase synchronization problem with measurements , where is an -dimensional complex unit-modulus vector and is a complex-valued Gaussian random matrix. It is assumed that each entry is observed with probability . We prove that the minimax lower bound of estimating under the squared loss is . We also show that both generalized power method and maximum likelihood estimator achieve the error bound . Thus, 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.
Cite
@article{arxiv.2010.04345,
title = {Exact Minimax Estimation for Phase Synchronization},
author = {Chao Gao and Anderson Y. Zhang},
journal= {arXiv preprint arXiv:2010.04345},
year = {2021}
}