A Data Augmentation Approach for Sampling Gaussian Models in High Dimension

Yosra Marnissi (1) , Dany Abboud (1) , Emilie Chouzenoux (2) , Jean-Christophe Pesquet (2) , Mohamed El-Badaoui (1) , Amel Benazza-Benyahia (3)

1 Safran Tech
2 OPIS - OPtimisation Imagerie et Santé
3 SUP'COM [TUNIS] - Ecole supérieure des communications de Tunis

Recently, methods based on Data Augmentation (DA) strategies have shown their efficiency for dealing with high-dimensional Gaussian sampling within Gibbs samplers compared to iterative-based sampling (e.g., Perturbation-Optimization). However, they are limited by the feasibility of the direct sampling of the auxiliary variable. This paper reviews DA sampling algorithms for Gaussian sampling and proposes a DA method which is especially useful when direct sampling of the auxiliary variable is not straightforward from a computational viewpoint. Experiments in two vibration analysis applications show the good performance of the proposed algorithm.

Mots clés: Data augmentation; Auxiliary variables; MCMC

Domaines: Traitement du signal et de l'image [eess.SP]

Yosra Marnissi, Dany Abboud, Emilie Chouzenoux, Jean-Christophe Pesquet, Mohamed El-Badaoui, et al.. A Data Augmentation Approach for Sampling Gaussian Models in High Dimension. EUSIPCO 2019 - 27th European Signal Processing Conference, Sep 2019, La Corogne, Spain. ⟨10.23919/eusipco.2019.8902496⟩. ⟨hal-02314418⟩