Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization

DOI10.1137/140979861zbMath1358.90104arXiv1310.7991OpenAlexW2963697946WikidataQ90317917 ScholiaQ90317917MaRDI QIDQ3179269

Animashree Anandkumar, Prateek Jain, Praneeth Netrapalli, Alekh Agarwal

Publication date: 21 December 2016

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1310.7991

zbMATH Keywords

lassodictionary learningsparse codingalternating minimizationincoherenceRIP

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Pattern recognition, speech recognition (68T10)

Related Items (18)

Role of sparsity and structure in the optimization landscape of non-convex matrix sensing ⋮ Unnamed Item ⋮ Unnamed Item ⋮ $(L_r,L_r,1)$-Decompositions, Sparse Component Analysis, and the Blind Separation of Sums of Exponentials ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ Fast overcomplete dictionary construction with probabilistic guarantees ⋮ Learning semidefinite regularizers ⋮ Combinatorial rigidity of incidence systems and application to dictionary learning ⋮ The Alternating Descent Conditional Gradient Method for Sparse Inverse Problems ⋮ Unnamed Item ⋮ A geometric analysis of phase retrieval ⋮ Structured overcomplete sparsifying transform learning with convergence guarantees and applications ⋮ Compressed dictionary learning ⋮ Accelerated Alternating Projections for Robust Principal Component Analysis ⋮ Efficient Matrix Sensing Using Rank-1 Gaussian Measurements ⋮ Unnamed Item ⋮ Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods ⋮ Identifiability of Complete Dictionary Learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Smooth sparse coding via marginal regression for learning sparse representations
• On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD
• The restricted isometry property and its implications for compressed sensing
• Sparse and Spurious: Dictionary Learning With Noise and Outliers
• A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
• Parametric Dictionary Design for Sparse Coding
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$-Minimization
• Image Super-Resolution Via Sparse Representation
• Low-rank matrix completion using alternating minimization
• Information Theory and Statistics: A Tutorial
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers

This page was built for publication: Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization