Communication Dans Un Congrès Année : 2024

Unrolled Expectation Maximization for Sparse Radio Interferometric Imaging

Résumé

This paper introduces an unrolled Expectation Maximization (EM) algorithm for sparse image reconstruction from radio interferometric measurements in the presence of a compound Gaussian distribution noise. Traditional model-based reconstruction methods, rooted in inference and optimization fields, provide an initial foundation with theoretical guarantees, but their performance is highly linked to the model accuracy and the choice of hyperparameter values. The popularity of supervised machine learning rose over the last decade, yet they faced hurdles related to interpretability and theoretical foundations. The emergence of unrolled algorithms addresses these limitations by combining the strengths of both approaches. We specifically focus on unrolling a regularized EM algorithm as a feedforward neural network with a residual connection. Experimental results showcase improvements over the iterative EM version.

Fichier principal
Vignette du fichier
0002197.pdf (903.85 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05136860 , version 1 (30-06-2025)

Licence

Identifiants

Citer

Nawel Arab, Yassine Mhiri, Isabelle Vin, Mohammed Nabil El Korso, Pascal Larzabal. Unrolled Expectation Maximization for Sparse Radio Interferometric Imaging. 32nd European Signal Processing Conference (EUSIPCO), Aug 2024, Lyon, France. pp.2197-2201, ⟨10.23919/EUSIPCO63174.2024.10715472⟩. ⟨hal-05136860⟩
1777 Consultations
229 Téléchargements

Altmetric

Partager

  • More