Theoretical guarantees for graph sparse coding

DOI10.1016/J.ACHA.2019.03.003MaRDI QIDQ778037zbMATH OpenOpenAlexWikidataFDO

Authors Yael Yankelevsky, Michael Elad

Publication date 30 June 2020

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

Full work available at URL https://doi.org/10.1016/j.acha.2019.03.003

zbMATH Keywords

manifold learningorthogonal matching pursuitgraph regularizationbasis pursuitsparse representationssignal recoverygraph sparse coding

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Applications of mathematical programming (90C90) Sensitivity, stability, parametric optimization (90C31) Source coding (94A29)

Recommendations

• Provably accurate double-sparse coding
• Learning with Structured Sparsity
• Structured sparsity: discrete and convex approaches
• Graph regularized nonnegative matrix factorization with sparse coding
• Compressive sensing with redundant dictionaries and structured measurements

Cites work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A General Framework for Regularized, Similarity-Based Image Restoration
• Algorithms for simultaneous sparse approximation. I: Greedy pursuit
• Algorithms for simultaneous sparse approximation. II: Convex relaxation
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Atomic decomposition by basis pursuit
• Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms
• Compressed sensing: how sharp is the restricted isometry property?
• Convergence Properties of the Spline Fit
• Decoding by Linear Programming
• Diffusion maps
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Finding GEMS: Multi-Scale Dictionaries For High-Dimensional Graph Signals
• From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
• Graph Regularized Sparse Coding for Image Representation
• Greed is Good: Algorithmic Results for Sparse Approximation
• Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization
• Image Super-Resolution Via Sparse Representation
• Just relax: convex programming methods for identifying sparse signals in noise
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Learning with Structured Sparsity
• Local and nonlocal discrete regularization on weighted graphs for image and mesh processing
• On Lebesgue-type inequalities for greedy approximation
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• Prediction of Partially Observed Dynamical Processes Over Networks via Dictionary Learning
• Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A Unified Framework
• RIP-Based Near-Oracle Performance Guarantees for SP, CoSaMP, and IHT
• Robust Recovery of Signals From a Structured Union of Subspaces
• Sparse and redundant representations. From theory to applications in signal and image processing.
• Stable recovery of sparse overcomplete representations in the presence of noise
• Structured Compressed Sensing: From Theory to Applications
• Theoretical Results on Sparse Representations of Multiple-Measurement Vectors
• Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding

Cited in

(5)

• Nonlinear Sparse-Graph Codes for Lossy Compression
• Beyond linear subspace clustering: a comparative study of nonlinear manifold clustering algorithms
• Sparse Recovery With Graph Constraints
• Sparse codes derived from graphs
• Measurement Bounds for Sparse Signal Ensembles via Graphical Models

Describes a project that uses

Uses Software

• PDCO

This page was built for publication: Theoretical guarantees for graph sparse coding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q778037)