Analysis of singular value thresholding algorithm for matrix completion

DOI10.1007/S00041-019-09688-8MaRDI QIDQ2338558zbMATH OpenOpenAlexWikidataFDO

Authors Yunwen Lei, Ding-Xuan Zhou

Publication date 21 November 2019

Published in The Journal of Fourier Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s00041-019-09688-8

zbMATH Keywords

Bregman distancematrix completionmirror descentsingular-value thresholding

Mathematics Subject Classification ID

Matrix completion problems (15A83) Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25)

Recommendations

• A Singular Value Thresholding Algorithm for Matrix Completion
• Matrix completion by singular value thresholding: sharp bounds
• A lower bound guaranteeing exact matrix completion via singular value thresholding algorithm
• A singular value thresholding with diagonal-update algorithm for low-rank matrix completion
• A singular value \(p\)-shrinkage thresholding algorithm for low rank matrix recovery
• Matrix estimation by universal singular value thresholding
• Half thresholding eigenvalue algorithm for semidefinite matrix completion
• Transformed Schatten-1 iterative thresholding algorithms for low rank matrix completion
• A matrix completion algorithm using randomized SVD
• Fast singular value thresholding without singular value decomposition

Cites work

• A randomized Kaczmarz algorithm with exponential convergence
• A Singular Value Thresholding Algorithm for Matrix Completion
• Analysis of Online Composite Mirror Descent Algorithm
• Bregman Iterative Algorithms for \ell₁-Minimization with Applications to Compressed Sensing
• Convergence of online mirror descent
• Convergence of the linearized Bregman iteration for \(\ell _1\)-norm minimization
• Exact matrix completion via convex optimization
• Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• Infinite-dimensional log-determinant divergences between positive definite trace class operators
• Introductory lectures on convex optimization. A basic course.
• Learning theory of randomized Kaczmarz algorithm
• Learning theory of randomized sparse Kaczmarz method
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• On regularization algorithms in learning theory
• Regularization techniques for learning with matrices
• Spectral Algorithms for Supervised Learning
• Support Vector Machines
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Thresholded spectral algorithms for sparse approximations
• Unregularized online learning algorithms with general loss functions

Cited in

(7)

• Parametrized quasi-soft thresholding operator for compressed sensing and matrix completion
• A singular value thresholding with diagonal-update algorithm for low-rank matrix completion
• Fast singular value thresholding without singular value decomposition
• A Singular Value Thresholding Algorithm for Matrix Completion
• A lower bound guaranteeing exact matrix completion via singular value thresholding algorithm
• Convergence analysis of the rank-restricted soft SVD algorithm
• Matrix completion by singular value thresholding: sharp bounds

This page was built for publication: Analysis of singular value thresholding algorithm for matrix completion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2338558)