Online estimation of MGGD : the Riemannian Averaged Natural Gradient method - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Online estimation of MGGD : the Riemannian Averaged Natural Gradient method

Estimation en ligne pour les paramètres d'une distribution MGGD : La méthode du gradient naturel riemannien moyenné

Résumé

Multivariate Generalized Gaussian Distributions (MGGD) are a rich class of multivariate distributions, which have gained importance across many engineering applications (image processing, computer vision, radar and biomedical signal processsing). Unfortunately, estimating the parameters of MGGD leads to non-linear matrix equations, whose solution becomes unpractical in high-dimensional problems, or when dealing with very large datasets. To overcome this difficulty, the present paper proposes a new method for online estimation of MGGD parameters, called the Riemannian Averaged Natural Gradient (RANG) method. The RANG method is suitable for application with high-dimensional and large datasets, since it requires modest memory and computational resources. The present paper formulates this new method, and presents some computer simulations, to showcase its performance. It is seen that, while the RANG method makes less exhaustive use of available data, it still achieves identical performance, to classical maximum-likelihood estimation, for sufficiently large datasets.
Fichier principal
Vignette du fichier
ZHOU_CAMSAP_2019.pdf (372.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02530279 , version 1 (02-04-2020)

Identifiants

Citer

Jialun Zhou, Salem Said, Yannick Berthoumieu. Online estimation of MGGD : the Riemannian Averaged Natural Gradient method. 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Dec 2019, Le gosier, France. pp.515-519, ⟨10.1109/CAMSAP45676.2019.9022517⟩. ⟨hal-02530279⟩
33 Consultations
125 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More