Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms
arXiv:1903.09284 · doi:10.1109/TSP.2019.2952046
Abstract
This work addresses the problem of learning sparse representations of tensor data using structured dictionary learning. It proposes learning a mixture of separable dictionaries to better capture the structure of tensor data by generalizing the separable dictionary learning model. Two different approaches for learning mixture of separable dictionaries are explored and sufficient conditions for local identifiability of the underlying dictionary are derived in each case. Moreover, computational algorithms are developed to solve the problem of learning mixture of separable dictionaries in both batch and online settings. Numerical experiments are used to show the usefulness of the proposed model and the efficacy of the developed algorithms.
18 pages, 4 figures, 3 tables; Published in IEEE Trans. Signal Processing
References in corpus (10)
- Tensor Decomposition for Signal Processing and Machine Learning
- Tensorizing Neural Networks
- Covariance Estimation in High Dimensions via Kronecker Product Expansions
- New Algorithms for Learning Incoherent and Overcomplete Dictionaries
- On the Identifiability of Overcomplete Dictionaries via the Minimisation Principle Underlying K-SVD
- Denoising and Completion of 3D Data via Multidimensional Dictionary Learning
- Minimax Lower Bounds on Dictionary Learning for Tensor Data
- Separable Dictionary Learning
- When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
- Identifiability of Kronecker-structured Dictionaries for Tensor Data