Simple alternating minimization provably solves complete dictionary learning
From MaRDI portal
Cites work
- rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- A more efficient rank-one covariance matrix update for evolution strategies
- Analysis of fast structured dictionary learning
- Complete dictionary learning via ^4-norm maximization over the orthogonal group
- Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
- Compressed dictionary learning
- Convergence radius and sample complexity of ITKM algorithms for dictionary learning
- Dictionary Identification—Sparse Matrix-Factorization via \ell₁-Minimization
- Dictionary learning -- from local towards global and adaptive
- Dictionary learning and tensor decomposition via the sum-of-squares method
- High-dimensional probability. An introduction with applications in data science
- Identifiability of complete dictionary learning
- Learning sparsely used overcomplete dictionaries via alternating minimization
- Local identification of overcomplete dictionaries
- Matrix factorizations and their perturbations
- Nearly unbiased variable selection under minimax concave penalty
- New Perturbation Bounds for the Unitary Polar Factor
- Sparse and Spurious: Dictionary Learning With Noise and Outliers
Cited in
(1)
This page was built for publication: Simple alternating minimization provably solves complete dictionary learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6944084)
