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

DOI10.1137/16M110109XzbMath1387.90199arXiv1603.00211OpenAlexW2962970675MaRDI QIDQ4602339

Anthony Man-Cho So, Huikang Liu, Man-Chung Yue

Publication date: 10 January 2018

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1603.00211

zbMATH Keywords

maximum likelihood estimationerror boundsphase synchronizationconvergence rate analysisgeneralized power method

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Optimality conditions and duality in mathematical programming (90C46)

Related Items (19)

Orientation estimation of cryo-EM images using projected gradient descent method ⋮ Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods ⋮ Improved Performance Guarantees for Orthogonal Group Synchronization via Generalized Power Method ⋮ On recovery guarantees for angular synchronization ⋮ Solving orthogonal group synchronization via convex and low-rank optimization: tightness and landscape analysis ⋮ Adaptive trust-region method on Riemannian manifold ⋮ A unified approach to synchronization problems over subgroups of the orthogonal group ⋮ Linear Convergence of a Proximal Alternating Minimization Method with Extrapolation for \(\boldsymbol{\ell_1}\) -Norm Principal Component Analysis ⋮ The noise-sensitivity phase transition in spectral group synchronization over compact groups ⋮ Near-optimal bounds for generalized orthogonal Procrustes problem via generalized power method ⋮ Tightness of a New and Enhanced Semidefinite Relaxation for MIMO Detection ⋮ The global optimization geometry of shallow linear neural networks ⋮ Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold ⋮ New analysis of linear convergence of gradient-type methods via unifying error bound conditions ⋮ Error analysis for denoising smooth modulo signals on a graph ⋮ Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods ⋮ Non-convex exact community recovery in stochastic block model ⋮ On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint ⋮ Orthogonal Trace-Sum Maximization: Tightness of the Semidefinite Relaxation and Guarantee of Locally Optimal Solutions

Cites Work

• Unnamed Item
• Unnamed Item
• Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
• Angular synchronization by eigenvectors and semidefinite programming
• Alternating direction augmented Lagrangian methods for semidefinite programming
• On approximating complex quadratic optimization problems via semidefinite programming relaxations
• A unified approach to error bounds for structured convex optimization problems
• Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
• Block Coordinate Descent Methods for Semidefinite Programming
• Nonconvex Phase Synchronization
• Phase Retrieval with Polarization
• Generalized power method for sparse principal component analysis
• On the complexity of purely complex μ computation and related problems in multidimensional systems
• On Intrinsic Cramér-Rao Bounds for Riemannian Submanifolds and Quotient Manifolds
• Non-asymptotic convergence analysis of inexact gradient methods for machine learning without strong convexity
• Near-Optimal Bounds for Phase Synchronization
• Conditional Gradient Algorithmsfor Rank-One Matrix Approximations with a Sparsity Constraint

This page was built for publication: On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase Synchronization