Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
From MaRDI portal
Publication:5210519
DOI10.1137/18M122457XzbMath1434.90195arXiv1811.00980OpenAlexW2999695911WikidataQ126385160 ScholiaQ126385160MaRDI QIDQ5210519
No author found.
Publication date: 21 January 2020
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1811.00980
Stiefel manifoldnonsmoothiteration complexitysemismooth Newton methodproximal gradient methodsparse PCAmanifold optimizationcompressed modes
Related Items
Riemannian Conjugate Gradient Methods: General Framework and Specific Algorithms with Convergence Analyses ⋮ Riemannian proximal gradient methods ⋮ DC semidefinite programming and cone constrained DC optimization. I: Theory ⋮ Tracking and Regret Bounds for Online Zeroth-Order Euclidean and Riemannian Optimization ⋮ Stochastic consensus dynamics for nonconvex optimization on the Stiefel manifold: Mean-field limit and convergence ⋮ 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 semismooth Newton based augmented Lagrangian method for nonsmooth optimization on matrix manifolds ⋮ Adaptive trust-region method on Riemannian manifold ⋮ A Dynamic Smoothing Technique for a Class of Nonsmooth Optimization Problems on Manifolds ⋮ A penalty-free infeasible approach for a class of nonsmooth optimization problems over the Stiefel manifold ⋮ Proximal gradient algorithm with trust region scheme on Riemannian manifold ⋮ A communication-efficient and privacy-aware distributed algorithm for sparse PCA ⋮ An image inpainting algorithm using exemplar matching and low-rank sparse prior ⋮ Dynamic Principal Component Analysis in High Dimensions ⋮ Riemannian thresholding methods for row-sparse and low-rank matrix recovery ⋮ Proximal quasi-Newton method for composite optimization over the Stiefel manifold ⋮ Slow and finite-time relaxations to \(m\)-bipartite consensus on the Stiefel manifold ⋮ A Riemannian Proximal Newton Method ⋮ Linear Programming on the Stiefel Manifold ⋮ Retraction-based first-order feasible methods for difference-of-convex programs with smooth inequality and simple geometric constraints ⋮ An inexact Riemannian proximal gradient method ⋮ A brief introduction to manifold optimization ⋮ Unnamed Item ⋮ Emergent behaviors of high-dimensional Kuramoto models on Stiefel manifolds ⋮ Proximal gradient method for nonconvex and nonsmooth optimization on Hadamard manifolds ⋮ Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods ⋮ An Inexact Semismooth Newton Method on Riemannian Manifolds with Application to Duality-Based Total Variation Denoising ⋮ A stochastic Nesterov's smoothing accelerated method for general nonsmooth constrained stochastic composite convex optimization ⋮ Exact Penalty Function for $\ell_{2,1}$ Norm Minimization over the Stiefel Manifold ⋮ An active-set proximal quasi-Newton algorithm for ℓ1-regularized minimization over a sphere constraint ⋮ Riemannian optimization with a preconditioning scheme on the generalized Stiefel manifold
Uses Software
Cites Work
- A feasible method for optimization with orthogonality constraints
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Nearly unbiased variable selection under minimax concave penalty
- \(\varepsilon\)-subgradient algorithms for locally Lipschitz functions on Riemannian manifolds
- A new approach to the proximal point method: convergence on general Riemannian manifolds
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Alternating direction method of multipliers for sparse principal component analysis
- A splitting method for orthogonality constrained problems
- Low-rank retractions: a survey and new results
- SDPNAL+: a majorized semismooth Newton-CG augmented Lagrangian method for semidefinite programming with nonnegative constraints
- Generalized gradients and characterization of epi-Lipschitz sets in Riemannian manifolds
- A framework of constraint preserving update schemes for optimization on Stiefel manifold
- Generalized Hessian matrix and second-order optimality conditions for problems with \(C^{1,1}\) data
- Sparse principal component analysis via regularized low rank matrix approximation
- Conjugate gradient algorithm for optimization under unitary matrix constraint
- A dual algorithm for the solution of nonlinear variational problems via finite element approximation
- Subgradient algorithm on Riemannian manifolds
- A regularized semi-smooth Newton method with projection steps for composite convex programs
- Global convergence of ADMM in nonconvex nonsmooth optimization
- Superlinear convergence of a Newton-type algorithm for monotone equations
- A geometric analysis of phase retrieval
- Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis
- A Riemannian subgradient algorithm for economic dispatch with valve-point effect
- 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
- Iteration-complexity of gradient, subgradient and proximal point methods on Riemannian manifolds
- A nonsmooth version of Newton's method
- Nonconvex and nonsmooth optimization with generalized orthogonality constraints: an approximate augmented Lagrangian method
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- A Second Order Nonsmooth Variational Model for Restoring Manifold-Valued Images
- Weakly Correlated Sparse Components with Nearly Orthonormal Loadings
- Nonconvex Phase Synchronization
- A Proximal Point Algorithm for Log-Determinant Optimization with Group Lasso Regularization
- Low-Rank Matrix Completion by Riemannian Optimization
- Generalized power method for sparse principal component analysis
- Manopt, a Matlab toolbox for optimization on manifolds
- A Riemannian Gradient Sampling Algorithm for Nonsmooth Optimization on Manifolds
- Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
- An augmented Lagrangian dual approach for the H-weighted nearest correlation matrix problem
- A Newton-CG Augmented Lagrangian Method for Semidefinite Programming
- Solving Log-Determinant Optimization Problems by a Newton-CG Primal Proximal Point Algorithm
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- The Split Bregman Method for L1-Regularized Problems
- A Fast Algorithm for Edge-Preserving Variational Multichannel Image Restoration
- An Augmented Lagrangian Method for $\ell_{1}$-Regularized Optimization Problems with Orthogonality Constraints
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- Semismooth and Semiconvex Functions in Constrained Optimization
- The Geometry of Algorithms with Orthogonality Constraints
- Variational Analysis
- Proximal Point Algorithm On Riemannian Manifolds
- Non-Convex Phase Retrieval From STFT Measurements
- Steepest Descent Algorithms for Optimization Under Unitary Matrix Constraint
- On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase Synchronization
- A Highly Efficient Semismooth Newton Augmented Lagrangian Method for Solving Lasso Problems
- Line Search Algorithms for Locally Lipschitz Functions on Riemannian Manifolds
- Nonsmooth trust region algorithms for locally Lipschitz functions on Riemannian manifolds
- Finite-Dimensional Variational Inequalities and Complementarity Problems
- Global rates of convergence for nonconvex optimization on manifolds
- Compressed modes for variational problems in mathematics and physics
- Quasi-Newton Methods on Grassmannians and Multilinear Approximations of Tensors
- Blind Deconvolution by a Steepest Descent Algorithm on a Quotient Manifold
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- Nonsmooth Riemannian Optimization with Applications to Sphere Packing and Grasping
- Manifolds of Negative Curvature
- A Direct Formulation for Sparse PCA Using Semidefinite Programming
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
