Near-optimal bounds for generalized orthogonal Procrustes problem via generalized power method

DOI10.1016/j.acha.2023.04.008arXiv2112.13725MaRDI QIDQ6172167

Shuyang Ling

Publication date: 19 July 2023

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.13725

zbMATH Keywords

semidefinite programmingnonconvex optimizationrandom matrixorthogonal Procrustes problemleave-one-out technique

Mathematics Subject Classification ID

Statistics (62-XX) Numerical analysis (65-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• A feasible method for optimization with orthogonality constraints
• Solving semidefinite-quadratic-linear programs using SDPT3
• Approximating the little Grothendieck problem over the orthogonal and unitary groups
• SDPNAL+: a majorized semismooth Newton-CG augmented Lagrangian method for semidefinite programming with nonnegative constraints
• Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Angular synchronization by eigenvectors and semidefinite programming
• Moment inequalities for sums of random matrices and their applications in optimization
• Generalized Procrustes analysis
• A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
• Random perturbation of low rank matrices: improving classical bounds
• A geometric analysis of phase retrieval
• Optimality and sub-optimality of PCA. I: Spiked random matrix models
• Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• Entrywise eigenvector analysis of random matrices with low expected rank
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Local minima and convergence in low-rank semidefinite programming
• Exact matrix completion via convex optimization
• Nonconvex Phase Synchronization
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• Blind Deconvolution Using Convex Programming
• Three-Dimensional Structure Determination from Common Lines in Cryo-EM by Eigenvectors and Semidefinite Programming
• The generalized orthogonal Procrustes problem in the high noise regime
• New Perturbation Bounds for the Unitary Polar Factor
• Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming
• Procrustes Problems
• Community Detection and Stochastic Block Models
• The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences
• On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase Synchronization
• Non-Iterative Rigid 2D/3D Point-Set Registration Using Semidefinite Programming
• High-Dimensional Statistics
• Near-Optimal Bounds for Phase Synchronization
• High-Dimensional Probability
• SDPNAL+: A Matlab software for semidefinite programming with bound constraints (version 1.0)
• Scalable Semidefinite Programming
• Reducibility among Combinatorial Problems
• Deterministic Guarantees for Burer‐Monteiro Factorizations of Smooth Semidefinite Programs
• MATHEMATICS FOR CRYO-ELECTRON MICROSCOPY
• Phase Retrieval by Alternating Minimization With Random Initialization
• Exact and stable recovery of rotations for robust synchronization
• Global Registration of Multiple Point Clouds Using Semidefinite Programming
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• Matrix Completion From a Few Entries
• Efficient rounding for the noncommutative grothendieck inequality
• The Rotation of Eigenvectors by a Perturbation. III
• Perturbation bounds in connection with singular value decomposition
• Orthogonal Trace-Sum Maximization: Tightness of the Semidefinite Relaxation and Guarantee of Locally Optimal Solutions
• Phase Retrieval via Matrix Completion
• Solving orthogonal group synchronization via convex and low-rank optimization: tightness and landscape analysis

This page was built for publication: Near-optimal bounds for generalized orthogonal Procrustes problem via generalized power method