A non-Euclidean gradient descent method with sketching for unconstrained matrix minimization

DOI10.1016/j.orl.2019.08.001zbMath1476.90257OpenAlexW2968003974MaRDI QIDQ2294351

Nadav Hallak, Marc Teboulle

Publication date: 10 February 2020

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.orl.2019.08.001

zbMATH Keywords

convergence analysismatrix minimizationmatrix sketchingnon-Euclidean gradient method

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Methods of reduced gradient type (90C52)

Cites Work

• Unnamed Item
• Unnamed Item
• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Matrix recipes for hard thresholding methods
• Computational Advertising: Techniques for Targeting Relevant Ads
• Introduction to Nonlinear Optimization
• Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Practical Sketching Algorithms for Low-Rank Matrix Approximation
• A Non-Euclidean Gradient Descent Framework for Non-Convex Matrix Factorization
• Randomized sketch descent methods for non-separable linearly constrained optimization