On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD

DOI10.1016/J.ACHA.2014.01.005zbMath1297.94018arXiv1301.3375OpenAlexW2034683677MaRDI QIDQ741264

Karin Schnass

Publication date: 11 September 2014

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1301.3375

zbMATH Keywords

sparse representationdictionary learningsparse codingsparse component analysissampling complexityK-SVDdictionary identificationfinite sample sizeminimisation criterion

Mathematics Subject Classification ID

Factorization of matrices (15A23) Learning and adaptive systems in artificial intelligence (68T05) Sampling theory in information and communication theory (94A20) Source coding (94A29)

Related Items (12)

Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization ⋮ Unnamed Item ⋮ Fast overcomplete dictionary construction with probabilistic guarantees ⋮ Learning semidefinite regularizers ⋮ Convergence radius and sample complexity of ITKM algorithms for dictionary learning ⋮ Unnamed Item ⋮ Customized dictionary learning for subdatasets with fine granularity ⋮ An efficient algorithm for overcomplete sparsifying transform learning with signal denoising ⋮ On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD ⋮ Compressed dictionary learning ⋮ Compressive sensing and neural networks from a statistical learning perspective ⋮ Multilinear Compressive Sensing and an Application to Convolutional Linear Networks

Uses Software

• PDCO
• CoSaMP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Iterative thresholding for sparse approximations
• Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms
• On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD
• On the conditioning of random subdictionaries
• CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
• On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them
• Blind Source Separation by Sparse Decomposition in a Signal Dictionary
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Stable recovery of sparse overcomplete representations in the presence of noise
• Greed is Good: Algorithmic Results for Sparse Approximation
• Dictionary Learning for L1-Exact Sparse Coding
• Iteratively reweighted least squares minimization for sparse recovery
• Ten Lectures on Wavelets
• Dictionary Learning Algorithms for Sparse Representation
• Dictionary Learning for Sparse Approximations With the Majorization Method
• Recursive Least Squares Dictionary Learning Algorithm
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• $K$-Dimensional Coding Schemes in Hilbert Spaces
• Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$-Minimization
• Fast Discrete Curvelet Transforms
• Compressed sensing
• An introduction to frames and Riesz bases
• Adaptive greedy approximations

This page was built for publication: On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD