Exact Minimax Estimation for Phase Synchronization
Authors:
- 14 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 67 (12) , 8236-8247
Abstract
We study the phase synchronization problem with measurements Y = z*z*H + σW ∈ Cn×n, where z* is an n-dimensional complex unit-modulus vector and W is a complexvalued Gaussian random matrix. It is assumed that each entry Yjk is observed with probability p. We prove that the minimax lower bound of estimating z* under the squared ℓ2 loss is (1-o(1)) σ2/2p. We also show that both generalized power method and maximum likelihood estimator achieve the error bound (1 + o(1)) σ2/2p. Thus, σ2/2p 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.Keywords
All Related Versions
Funding Information
- NSF CAREER (DMS-1847590)
- NSF (CCF-1934931)
- NSF (DMS-2112988)
This publication has 17 references indexed in Scilit:
- On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase SynchronizationSIAM Journal on Optimization, 2017
- Tightness of the maximum likelihood semidefinite relaxation for angular synchronizationMathematical Programming, 2016
- Sharp nonasymptotic bounds on the norm of random matrices with independent entriesThe Annals of Probability, 2016
- Phase transitions in semidefinite relaxationsProceedings of the National Academy of Sciences, 2016
- Nonconvex Phase SynchronizationSIAM Journal on Optimization, 2016
- Consistency of spectral clustering in stochastic block modelsThe Annals of Statistics, 2015
- Concentration of the Kirchhoff index for Erdős–Rényi graphsSystems & Control Letters, 2014
- Cramer-Rao bounds for synchronization of rotationsInformation and Inference: A Journal of the IMA, 2013
- On Intrinsic Cramér-Rao Bounds for Riemannian Submanifolds and Quotient ManifoldsIEEE Transactions on Signal Processing, 2013
- Angular synchronization by eigenvectors and semidefinite programmingApplied and Computational Harmonic Analysis, 2011