Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods

DOI10.1137/20M1321000zbMath1505.65216arXiv1911.05047OpenAlexW3176493728WikidataQ115246903 ScholiaQ115246903MaRDI QIDQ5003207

Xiao Li, Zengde Deng, Qing Qu, Shixiang Chen, Zhihui Zhu, Anthony Man-Cho So

Publication date: 20 July 2021

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

Full work available at URL: https://arxiv.org/abs/1911.05047

zbMATH Keywords

nonconvex optimizationlinear convergenceiteration complexitydictionary learningorthogonality constraintmanifold optimizationrobust subspace recovery

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Large-scale problems in mathematical programming (90C06) Abstract computational complexity for mathematical programming problems (90C60) Nonconvex programming, global optimization (90C26)

Related Items (5)

Tracking and Regret Bounds for Online Zeroth-Order Euclidean and Riemannian Optimization ⋮ Riemannian smoothing gradient type algorithms for nonsmooth optimization problem on compact Riemannian submanifold embedded in Euclidean space ⋮ Riemannian stochastic variance-reduced cubic regularized Newton method for submanifold optimization ⋮ A Dynamic Smoothing Technique for a Class of Nonsmooth Optimization Problems on Manifolds ⋮ A Riemannian Proximal Newton Method

Uses Software

• GradSamp
• FMS
• MADMM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A feasible method for optimization with orthogonality constraints
• A new approach to the proximal point method: convergence on general Riemannian manifolds
• A splitting method for orthogonality constrained problems
• Subgradient algorithm on Riemannian manifolds
• Introductory lectures on convex optimization. A basic course.
• Subgradient methods for sharp weakly convex functions
• Riemannian proximal gradient methods
• A brief introduction to manifold optimization
• Nonconvex weak sharp minima on Riemannian manifolds
• A collection of nonsmooth Riemannian optimization problems
• Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods
• Efficiency of minimizing compositions of convex functions and smooth maps
• Robust computation of linear models by convex relaxation
• Generalized principal component analysis
• Iteration-complexity of gradient, subgradient and proximal point methods on Riemannian manifolds
• A generalized solution of the orthogonal Procrustes problem
• Non-existence of continuous convex functions on certain Riemannian manifolds
• Sparse Modeling for Image and Vision Processing
• A Vector-Contraction Inequality for Rademacher Complexities
• Generalized power method for sparse principal component analysis
• A Novel M-Estimator for Robust PCA
• A Riemannian Gradient Sampling Algorithm for Nonsmooth Optimization on Manifolds
• Finding a Sparse Vector in a Subspace: Linear Sparsity Using Alternating Directions
• Outlier-Robust PCA: The High-Dimensional Case
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
• Strong and Weak Convexity of Sets and Functions
• Weak Sharp Minima in Mathematical Programming
• Weak Sharp Minima on Riemannian Manifolds
• Robust Stochastic Approximation Approach to Stochastic Programming
• On convergence rates of subgradient optimization methods
• The Geometry of Algorithms with Orthogonality Constraints
• Variational Analysis
• Proximal Point Algorithm On Riemannian Manifolds
• Robust subspace recovery by Tyler's M-estimator
• Line Search Algorithms for Locally Lipschitz Functions on Riemannian Manifolds
• Stochastic Model-Based Minimization of Weakly Convex Functions
• Iteration-complexity of the subgradient method on Riemannian manifolds with lower bounded curvature
• A Well-Tempered Landscape for Non-convex Robust Subspace Recovery
• Global rates of convergence for nonconvex optimization on manifolds
• Exact and stable recovery of rotations for robust synchronization
• Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
• Nonconvex Robust Low-Rank Matrix Recovery
• Fast, robust and non-convex subspace recovery
• A Robust Gradient Sampling Algorithm for Nonsmooth, Nonconvex Optimization
• Majorization for Changes in Angles Between Subspaces, Ritz Values, and Graph Laplacian Spectra
• Manifolds of Negative Curvature

This page was built for publication: Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods