Analysis of fast structured dictionary learning
From MaRDI portal
dictionary learningfast algorithmsgenerative modelsalternating minimizationsparse representationsconvergence guaranteestransform learning
Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)
Abstract: Sparsity-based models and techniques have been exploited in many signal processing and imaging applications. Data-driven methods based on dictionary and sparsifying transform learning enable learning rich image features from data, and can outperform analytical models. In particular, alternating optimization algorithms have been popular for learning such models. In this work, we focus on alternating minimization for a specific structured unitary sparsifying operator learning problem, and provide a convergence analysis. While the algorithm converges to the critical points of the problem generally, our analysis establishes under mild assumptions, the local linear convergence of the algorithm to the underlying sparsifying model of the data. Analysis and numerical simulations show that our assumptions hold for standard probabilistic data models. In practice, the algorithm is robust to initialization.
Recommendations
- Learning sparsely used overcomplete dictionaries via alternating minimization
- Proximal alternating method for dictionary learning
- Structured overcomplete sparsifying transform learning with convergence guarantees and applications
- A fast algorithm for learning overcomplete dictionary for sparse representation based on proximal operators
- Sparsity and nullity: paradigms for analysis dictionary learning
Cited in
(10)- Simple alternating minimization provably solves complete dictionary learning
- Data-driven methods for quantitative imaging
- Cardinality minimization, constraints, and regularization: a survey
- Alternating proximal regularized dictionary learning
- FRIST-flipping and rotation invariant sparsifying transform learning and applications
- Sparsity and nullity: paradigms for analysis dictionary learning
- Structured overcomplete sparsifying transform learning with convergence guarantees and applications
- Toward fast transform learning
- Learning sparsely used overcomplete dictionaries via alternating minimization
- Analysis K-SVD: A Dictionary-Learning Algorithm for the Analysis Sparse Model
This page was built for publication: Analysis of fast structured dictionary learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5006539)
