Multistage Convex Relaxation Approach to Rank Regularized Minimization Problems Based on Equivalent Mathematical Program with a Generalized Complementarity Constraint

DOI10.1137/15M1037160zbMath1369.90173OpenAlexW2745004303MaRDI QIDQ5348478

Shujun Bi, Shaohua Pan

Publication date: 18 August 2017

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/15m1037160

zbMATH Keywords

error boundsexact penaltymultistage convex relaxationrank regularized minimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33) Numerical methods of relaxation type (49M20)

Related Items (5)

Second-order optimality conditions for mathematical program with semidefinite cone complementarity constraints and applications ⋮ Calmness of partial perturbation to composite rank constraint systems and its applications ⋮ Several Classes of Stationary Points for Rank Regularized Minimization Problems ⋮ Two-stage convex relaxation approach to low-rank and sparsity regularized least squares loss ⋮ Equivalent Lipschitz surrogates for zero-norm and rank optimization problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A rank-corrected procedure for matrix completion with fixed basis coefficients
• Mathematical programs with semidefinite cone complementarity constraints: constraint qualifications and optimality conditions
• First order optimality conditions for mathematical programs with semidefinite cone complementarity constraints
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Some sharp performance bounds for least squares regression with \(L_1\) regularization
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• Optimal low-rank approximation to a correlation matrix
• Noisy low-rank matrix completion with general sampling distribution
• Exact matrix completion via convex optimization
• Mathematical Programs with Complementarity Constraints: Stationarity, Optimality, and Sensitivity
• Improved Iteratively Reweighted Least Squares for Unconstrained Smoothed $\ell_q$ Minimization
• Review Paper. Interest–rate term–structure pricing models: a review
• A Singular Value Thresholding Algorithm for Matrix Completion
• Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning
• Interior-Point Method for Nuclear Norm Approximation with Application to System Identification
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Constraint Qualifications and Necessary Optimality Conditions for Optimization Problems with Variational Inequality Constraints
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• A Simpler Approach to Matrix Completion
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Convex Analysis

This page was built for publication: Multistage Convex Relaxation Approach to Rank Regularized Minimization Problems Based on Equivalent Mathematical Program with a Generalized Complementarity Constraint