Flexible Multi-layer Sparse Approximations of Matrices and Applications
Preprint
Abstract
The computational cost of many signal processing and machine learning techniques is often dominated by the cost of applying certain linear operators to high-dimensional vectors. This paper introduces an algorithm aimed at reducing the complexity of applying linear operators in high dimension by approximately factorizing the corresponding matrix into few sparse factors. The approach relies on recent advances in non-convex optimization. It is first explained and analyzed in details and then demonstrated experimentally on various problems including dictionary learning for image denoising, and the approximation of large matrices arising in inverse problems.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Toward Fast Transform LearningInternational Journal of Computer Vision, 2014
- MNE software for processing MEG and EEG dataNeuroImage, 2014
- Proximal alternating linearized minimization for nonconvex and nonsmooth problemsMathematical Programming, 2013
- Mixed-norm estimates for the M/EEG inverse problem using accelerated gradient methodsPhysics in Medicine & Biology, 2012
- Iterative Thresholding for Sparse ApproximationsJournal of Fourier Analysis and Applications, 2008
- Combining sparsity and rotational invariance in EEG/MEG source reconstructionNeuroImage, 2008
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraintCommunications on Pure and Applied Mathematics, 2004
- A Sparse Matrix Arithmetic Based on $\Cal H$ -Matrices. Part I: Introduction to ${\Cal H}$ -MatricesComputing, 1999
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989