An Equivalence between Critical Points for Rank Constraints Versus Low-Rank Factorizations
From MaRDI portal
Publication:5131960
DOI10.1137/18M1231675zbMath1453.90127arXiv1812.00404OpenAlexW3092363548WikidataQ114074270 ScholiaQ114074270MaRDI QIDQ5131960
Wooseok Ha, Rina Foygel Barber, Haoyang Liu
Publication date: 9 November 2020
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.00404
Related Items (4)
On the continuity of the tangent cone to the determinantal variety ⋮ Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy ⋮ An Apocalypse-Free First-Order Low-Rank Optimization Algorithm with at Most One Rank Reduction Attempt per Iteration ⋮ Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Fast global convergence of gradient methods for high-dimensional statistical recovery
- A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
- Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
- Exact matrix completion via convex optimization
- Low-Rank Matrix Completion by Riemannian Optimization
- Phase Retrieval via Wirtinger Flow: Theory and Algorithms
- Robust principal component analysis?
- Rank-Sparsity Incoherence for Matrix Decomposition
- Geometric Methods on Low-Rank Matrix and Tensor Manifolds
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Variational Analysis
- A Tight Bound of Hard Thresholding
- Global Optimality in Low-Rank Matrix Optimization
- Sharp Restricted Isometry Bounds for the Inexistence of Spurious Local Minima in Nonconvex Matrix Recovery
- Gradient descent with non-convex constraints: local concavity determines convergence
- Matrix Completion From a Few Entries
- Sharp Time–Data Tradeoffs for Linear Inverse Problems
- Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
- Low-Rank Optimization with Trace Norm Penalty
- Low-rank matrix completion using alternating minimization
- A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
This page was built for publication: An Equivalence between Critical Points for Rank Constraints Versus Low-Rank Factorizations
