On the Convergence of Projected-Gradient Methods with Low-Rank Projections for Smooth Convex Minimization over Trace-Norm Balls and Related Problems
DOI10.1137/18M1233170zbMath1461.65151arXiv1902.01644OpenAlexW3135857341MaRDI QIDQ5853570
Publication date: 10 March 2021
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1902.01644
matrix completionsemidefinite optimizationfirst-order methodsnuclear norm optimizationlarge scale matrix optimizationlow-rank matrix optimizationtrace norm optimization
Numerical mathematical programming methods (65K05) Semidefinite programming (90C22) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Nonlinear programming (90C30)
Related Items (1)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- User-friendly tail bounds for sums of random matrices
- Improved complexities of conditional gradient-type methods with applications to robust matrix recovery problems
- Exact matrix completion via convex optimization
- Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
- Robust principal component analysis?
- A Singular Value Thresholding Algorithm for Matrix Completion
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Practical Sketching Algorithms for Low-Rank Matrix Approximation
- First-Order Methods in Optimization
- Finding Low-Rank Solutions via Nonconvex Matrix Factorization, Efficiently and Provably
- A Simpler Approach to Matrix Completion
- Low-Rank Optimization with Trace Norm Penalty
- Sparse Approximate Solutions to Semidefinite Programs
This page was built for publication: On the Convergence of Projected-Gradient Methods with Low-Rank Projections for Smooth Convex Minimization over Trace-Norm Balls and Related Problems
