Skip to Main content Skip to Navigation
Journal articles

Flexible Multi-layer Sparse Approximations of Matrices and Applications

Luc Le Magoarou 1 Rémi Gribonval 1
1 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
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.
Complete list of metadatas

Cited literature [50 references]  Display  Hide  Download

https://hal.inria.fr/hal-01167948
Contributor : Luc Le Magoarou <>
Submitted on : Tuesday, March 29, 2016 - 9:31:39 AM
Last modification on : Friday, March 6, 2020 - 1:37:50 AM
Document(s) archivé(s) le : Thursday, June 30, 2016 - 10:22:33 AM

File

ieeeJSTSP.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Luc Le Magoarou, Rémi Gribonval. Flexible Multi-layer Sparse Approximations of Matrices and Applications. IEEE Journal of Selected Topics in Signal Processing, IEEE, 2016, ⟨10.1109/JSTSP.2016.2543461⟩. ⟨hal-01167948v2⟩

Share

Metrics

Record views

2083

Files downloads

716