Max-norm optimization for robust matrix recovery

DOI10.1007/s10107-017-1159-yzbMath1414.90265arXiv1609.07664OpenAlexW2964316995MaRDI QIDQ681486

Kim-Chuan Toh, Ethan X. Fang, Wen-Xin Zhou, Han Liu

Publication date: 12 February 2018

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

Full work available at URL: https://arxiv.org/abs/1609.07664

Mathematics Subject Classification ID

Convex programming (90C25) Multi-objective and goal programming (90C29) Norms of matrices, numerical range, applications of functional analysis to matrix theory (15A60)

Related Items

Matrix completion via max-norm constrained optimization, Column $\ell_{2,0}$-Norm Regularized Factorization Model of Low-Rank Matrix Recovery and Its Computation, A low-rank spectral method for learning Markov models, Low-rank matrix completion using nuclear norm minimization and facial reduction, Robust parameter estimation of regression models under weakened moment assumptions

Uses Software

• SNLSDP
• GADMM
• ADMM_QAP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Matrix completion via max-norm constrained optimization
• Extreme point inequalities and geometry of the rank sparsity ball
• Estimation of high-dimensional low-rank matrices
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Complexity measures of sign matrices
• Convex multi-task feature learning
• ADMM for the SDP relaxation of the QAP
• Online optimization for max-norm regularization
• Noisy low-rank matrix completion with general sampling distribution
• Matrix concentration inequalities via the method of exchangeable pairs
• Generalized alternating direction method of multipliers: new theoretical insights and applications
• Exact matrix completion via convex optimization
• Robust principal component analysis?
• A Singular Value Thresholding Algorithm for Matrix Completion
• Matrix completion via an alternating direction method
• Interior-Point Method for Nuclear Norm Approximation with Application to System Identification
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• A Simpler Approach to Matrix Completion
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Finding Approximately Rank-One Submatrices with the Nuclear Norm and $\ell_1$-Norm
• Learning Theory