Identifiability of Complete Dictionary Learning

DOI10.1137/18M1233339OpenAlexW3098099002MaRDI QIDQ5025788

Jeremy Cohen, Nicolas Gillis

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.08765

zbMATH Keywords

uniquenessidentifiabilitymatrix factorizationdictionary learningsparse component analysis

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Factorization of matrices (15A23) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

$(L_r,L_r,1)$-Decompositions, Sparse Component Analysis, and the Blind Separation of Sums of Exponentials ⋮ Simplex-Structured Matrix Factorization: Sparsity-Based Identifiability and Provably Correct Algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Tensor Decompositions and Applications
• Multiarray signal processing: tensor decomposition meets compressed sensing
• Sparse principal component analysis via regularized low rank matrix approximation
• On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them
• When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
• A note on the sample complexity of the Er-SpUD algorithm by Spielman, Wang and Wright for exact recovery of sparsely used dictionaries
• On the Uniqueness of the Canonical Polyadic Decomposition of Third-Order Tensors---Part II: Uniqueness of the Overall Decomposition
• Generalized power method for sparse principal component analysis
• When Can Dictionary Learning Uniquely Recover Sparse Data From Subsamples?
• Sparse and Spurious: Dictionary Learning With Noise and Outliers
• A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries
• 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
• The Double Dixie Cup Problem
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• An improved analysis of the ER-SpUD dictionary learning algorithm
• Learning the parts of objects by non-negative matrix factorization
• Dictionary Learning for Stereo Image Representation
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• A Direct Formulation for Sparse PCA Using Semidefinite Programming

This page was built for publication: Identifiability of Complete Dictionary Learning