Nonconvex optimization for robust tensor completion from grossly sparse observations

DOI10.1007/s10915-020-01356-0zbMath1472.65056OpenAlexW3096898654MaRDI QIDQ2219800

Xueying Zhao, Michael Kwok-Po Ng, Min-Ru Bai

Publication date: 21 January 2021

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10915-020-01356-0

zbMATH Keywords

difference of convex functionssparsitylow-rank approximationimpulse noisesrobust tensor completion

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Multilinear algebra, tensor calculus (15A69) Numerical linear algebra (65F99)

Related Items

Tensor completion via fully-connected tensor network decomposition with regularized factors, Nonlinear transform induced tensor nuclear norm for tensor completion, Fully-connected tensor network decomposition for robust tensor completion problem, Tensor completion via multi-directional partial tensor nuclear norm with total variation regularization, A generalized non-convex method for robust tensor completion, Provable stochastic algorithm for large-scale fully-connected tensor network decomposition, Proximal gradient algorithm for nonconvex low tubal rank tensor recovery, The nonconvex tensor robust principal component analysis approximation model via the weighted \(\ell_p\)-norm regularization, Robust Tensor Completion: Equivalent Surrogates, Error Bounds, and Algorithms, Multi-dimensional image recovery via fully-connected tensor network decomposition under the learnable transforms

Uses Software

• tproduct

Cites Work

• Unnamed Item
• Unnamed Item
• Tensor Decompositions and Applications
• Nearly unbiased variable selection under minimax concave penalty
• A rank-corrected procedure for matrix completion with fixed basis coefficients
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Factorization strategies for third-order tensors
• Alternating direction method of multipliers with difference of convex functions
• Convergence of a subgradient method for computing the bound norm of matrices
• Convex analysis approach to d. c. programming: Theory, algorithms and applications
• Low Tucker rank tensor recovery via ADMM based on exact and inexact iteratively reweighted algorithms
• Global convergence of ADMM in nonconvex nonsmooth optimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Learning with tensors: a framework based on convex optimization and spectral regularization
• Adaptive correction procedure for TVL1 image deblurring under impulse noise
• Robust Low-Rank Tensor Recovery: Models and Algorithms
• Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
• Robust principal component analysis?
• Tensor completion and low-n-rank tensor recovery via convex optimization
• An Adaptive Correction Approach for Tensor Completion
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography
• A TVSCAD approach for image deblurring with impulsive noise
• Sparse Approximate Solutions to Linear Systems
• Alternating Direction Method of Multipliers for a Class of Nonconvex and Nonsmooth Problems with Applications to Background/Foreground Extraction
• Third-Order Tensors as Operators on Matrices: A Theoretical and Computational Framework with Applications in Imaging
• Difference-of-Convex Learning: Directional Stationarity, Optimality, and Sparsity