Improved complexities of conditional gradient-type methods with applications to robust matrix recovery problems

DOI10.1007/s10107-019-01452-6zbMath1459.90146arXiv1802.05581OpenAlexW2991366040WikidataQ126641191 ScholiaQ126641191MaRDI QIDQ2227534

Dan Garber, Atara Kaplan, Shoham Sabach

Publication date: 15 February 2021

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1802.05581

zbMATH Keywords

convex optimizationsemidefinite programmingconditional gradient methodlow-rank matrix recoveryrobust PCAFrank-Wolfe algorithmnuclear norm minimizationlow-rank optimization

Mathematics Subject Classification ID

Semidefinite programming (90C22) Large-scale problems in mathematical programming (90C06) Randomized algorithms (68W20) Online algorithms; streaming algorithms (68W27) Robustness in mathematical programming (90C17)

Related Items (3)

Linear convergence of Frank-Wolfe for rank-one matrix recovery without strong convexity ⋮ Affine Invariant Convergence Rates of the Conditional Gradient Method ⋮ On the Convergence of Projected-Gradient Methods with Low-Rank Projections for Smooth Convex Minimization over Trace-Norm Balls and Related Problems

Cites Work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Introductory lectures on convex optimization. A basic course.
• Scalable Robust Matrix Recovery: Frank--Wolfe Meets Proximal Methods
• Robust principal component analysis?
• Robust PCA via Outlier Pursuit
• Regularization and Variable Selection Via the Elastic Net
• A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization

This page was built for publication: Improved complexities of conditional gradient-type methods with applications to robust matrix recovery problems