A regularized nonnegative third order tensor decomposition using a Primal-Dual Projected Gradient Algorithm: application to 3D fluorescence spectroscopy

K. El Qate 1 M. El Rhabi 2 A. Hakim 1 E. Moreau 3, 4, 5 Nadège Thirion-Moreau 3, 4, 5
1 UCA - Université Cadi Ayyad [Marrakech]
2 ENPC - École des Ponts ParisTech
3 LIS - Laboratoire d'Informatique et Systèmes
4 SIIM - Signal et Image
LIS - Laboratoire d'Informatique et Systèmes
5 UTLN SeaTech - Université de Toulon - École d’ingénieurs SeaTech
Abstract : This paper investigates the use of Primal-Dual optimization algorithms on multidimensional signal processing problems. The data blocks interpreted in a tensor way can be modeled by means of multi-linear decomposition. Here we will focus on the Canonical Polyadic Decomposition (CPD), and we will present an application to fluorescence spectroscopy using this decomposition. In order to estimate the factors or latent variables involved in these decompositions, it is usual to use criteria optimization algorithms. A classical cost function consists of a measure of the modeling error (fidelity term) to which a regularization term can be added if necessary. Here, we consider one of the most efficient optimization methods, Primal-Dual Projected Gradient. The effectiveness and the robustness of the proposed approach are shown through numerical examples.
Keywords : Primal-Dual Regularization Projected Gradient Nonnegative tensor decomposition Constrained optimization
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download
https://hal-amu.archives-ouvertes.fr/hal-01858112
Contributor : Eric Moreau <>
Submitted on : Wednesday, March 20, 2019 - 10:19:48 AM
Last modification on : Friday, August 9, 2019 - 3:18:07 PM
Long-term archiving on : Friday, June 21, 2019 - 1:31:29 PM

File

Modified Paper ICMM.pdf
Files produced by the author(s)

Identifiers

Collections

UNIV-AMU | UNIV-TLN | CNRS | LIS-LAB | ENPC | PARISTECH

Citation

K. El Qate, M. El Rhabi, A. Hakim, E. Moreau, Nadège Thirion-Moreau. A regularized nonnegative third order tensor decomposition using a Primal-Dual Projected Gradient Algorithm: application to 3D fluorescence spectroscopy. International Conference on Smart Multimedia, Aug 2018, Toulon, France. ⟨10.1007/978-3-030-04375-9_16⟩. ⟨hal-01858112⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

150

Files downloads

110

Contact

CCSD