Flexible Multi-layer Sparse Approximations of Matrices and Applications - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Journal of Selected Topics in Signal Processing Year : 2016

Flexible Multi-layer Sparse Approximations of Matrices and Applications

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.
Fichier principal
Vignette du fichier
ieeeJSTSP.pdf (1.16 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01167948 , version 1 (25-06-2015)
hal-01167948 , version 2 (29-03-2016)

Identifiers

Cite

Luc Le Magoarou, Rémi Gribonval. Flexible Multi-layer Sparse Approximations of Matrices and Applications. IEEE Journal of Selected Topics in Signal Processing, 2016, 10 (4), pp.688-700. ⟨10.1109/JSTSP.2016.2543461⟩. ⟨hal-01167948v2⟩
1497 View
1377 Download

Altmetric

Share

Gmail Facebook X LinkedIn More