Analysis of Asymptotic Escape of Strict Saddle Sets in Manifold Optimization

DOI10.1137/19M129437XzbMath1486.90155arXiv1911.12518OpenAlexW3088502654MaRDI QIDQ5037575

Zhen-zhen Li, Thomas Yizhao Hou, Zi-Yun Zhang

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.12518

zbMATH Keywords

phase retrievalstable manifold theoremmanifold optimizationprojected gradient descentstrict saddles

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Iterative numerical methods for linear systems (65F10) Invariant manifold theory for dynamical systems (37D10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Low-rank tensor completion by Riemannian optimization
• Feature selection and multi-kernel learning for sparse representation on a manifold
• Efficient rank reduction of correlation matrices
• Solving polynomial systems
• Riemannian structure on manifolds of quantum states
• Critical points of matrix least squares distance functions
• Natural gradient via optimal transport
• A geometric analysis of phase retrieval
• Data-driven tight frame construction and image denoising
• Optimization on the hierarchical Tucker manifold - applications to tensor completion
• On manifolds of tensors of fixed TT-rank
• Bose-Einstein Condensation and Superfluidity
• Welcome to Riemannian Computing in Computer Vision
• Guarantees of Riemannian Optimization for Low Rank Matrix Recovery
• Low-Rank Matrix Completion by Riemannian Optimization
• Convergence Results for Projected Line-Search Methods on Varieties of Low-Rank Matrices Via Łojasiewicz Inequality
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Information-Theoretic Differential Geometry of Quantum Phase Transitions
• Morse-Bott homology
• On the Number of Solutions to Polynomial Systems of Equations
• The Geometry of Algorithms with Orthogonality Constraints
• Optimization Techniques on Riemannian Manifolds
• Empirical Arithmetic Averaging Over the Compact Stiefel Manifold
• A Fast Hierarchically Preconditioned Eigensolver Based on Multiresolution Matrix Decomposition
• Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
• Low Dimensional Manifold Model for Image Processing
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model
• Sobolev Gradient Flow for the Gross--Pitaevskii Eigenvalue Problem: Global Convergence and Computational Efficiency
• Toward the Optimal Construction of a Loss Function Without Spurious Local Minima for Solving Quadratic Equations
• Compressed modes for variational problems in mathematics and physics
• Blind Deconvolution by a Steepest Descent Algorithm on a Quotient Manifold
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Time Integration of Tensor Trains
• An Extrinsic Look at the Riemannian Hessian
• Dynamical Low‐Rank Approximation

This page was built for publication: Analysis of Asymptotic Escape of Strict Saddle Sets in Manifold Optimization