Unique sharp local minimum in _1-minimization complete dictionary learning

zbMATH Open1498.68270arXiv1902.08380MaRDI QIDQ4969112FDOQ4969112

Authors:

Publication date: 5 October 2020

Full work available at URL: https://arxiv.org/abs/1902.08380

Recommendations

• Local identifiability of \(\ell_1\)-minimization dictionary learning: a sufficient and almost necessary condition
• Learning sparsely used overcomplete dictionaries via alternating minimization
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD
• The sample complexity of dictionary learning

zbMATH Keywords

nonconvex optimizationdictionary learning\(\ell_1\)-minimizationlocal and global identifiabilitysharp local minimum

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Estimation in multivariate analysis (62H12) Nonconvex programming, global optimization (90C26)

Cites Work

• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Independent component analysis, a new concept?
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Title not available (Why is that?)
• On Sparse Representations in Arbitrary Redundant Bases
• Online learning for matrix factorization and sparse coding
• Title not available (Why is that?)
• Atomic decomposition by basis pursuit
• Dictionary Learning Algorithms for Sparse Representation
• On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them
• Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$-Minimization
• Subgradient method for nonconvex nonsmooth optimization
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
• Learning sparsely used overcomplete dictionaries via alternating minimization
• Local identifiability of \(\ell_1\)-minimization dictionary learning: a sufficient and almost necessary condition
• Local identification of overcomplete dictionaries
• On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD
• On the linear combination of Laplace random variables
• Flat Minima
• Dictionary learning and tensor decomposition via the sum-of-squares method
• A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries
• Sparse and Spurious: Dictionary Learning With Noise and Outliers
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• Bilinear Generalized Approximate Message Passing—Part II: Applications

Cited In (4)

• Learning sparsely used overcomplete dictionaries via alternating minimization
• Local identifiability of \(\ell_1\)-minimization dictionary learning: a sufficient and almost necessary condition
• Sensitivity computation of the ℓ ₁ minimization problem and its application to dictionary design of ill-posed problems
• Weakly convex optimization over Stiefel manifold using Riemannian subgradient-type methods

This page was built for publication: Unique sharp local minimum in \(\ell_1\)-minimization complete dictionary learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969112)