Skip to Main content Skip to Navigation
Conference papers

A Partially Collapsed Gibbs Sampler with Accelerated Convergence for EEG Source Localization

Facundo Costa 1 Hadj Batatia 1 Thomas Oberlin 2 Jean-Yves Tourneret 3, 4
1 IRIT-TCI - Traitement et Compréhension d’Images
IRIT - Institut de recherche en informatique de Toulouse
2 IRIT-SC - Signal et Communications
IRIT - Institut de recherche en informatique de Toulouse
3 IRIT-MINDS - CoMputational imagINg anD viSion
IRIT - Institut de recherche en informatique de Toulouse
Abstract : This paper addresses the problem of designing efficient sampling moves in order to accelerate the convergence of MCMC methods. The Partially collapsed Gibbs sampler (PCGS) takes advantage of variable reordering, marginalization and trimming to accelerate the convergence of the traditional Gibbs sampler. This work studies two specific moves which allow the convergence of the PCGS to be further improved. It considers a Bayesian model where structured sparsity is enforced using a multivariate Bernoulli Laplacian prior. The posterior distribution associated with this model depends on mixed discrete and continuous random vectors. Due to the discrete part of the posterior, the conventional PCGS gets easily stuck around local maxima. Two Metropolis-Hastings moves based on multiple dipole random shifts and inter-chain proposals are proposed to overcome this problem. The resulting PCGS is applied to EEG source localization. Experiments conducted with synthetic data illustrate the effectiveness of this PCGS with accelerated convergence.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01466637
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Monday, February 13, 2017 - 4:25:40 PM
Last modification on : Wednesday, June 9, 2021 - 10:00:35 AM
Long-term archiving on: : Sunday, May 14, 2017 - 3:02:20 PM

File

costa_17176.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01466637, version 1
  • OATAO : 17176

Citation

Facundo Costa, Hadj Batatia, Thomas Oberlin, Jean-Yves Tourneret. A Partially Collapsed Gibbs Sampler with Accelerated Convergence for EEG Source Localization. IEEE Workshop on statistical signal processing (SSP 2016), Jun 2016, Palma de Mallorca, Spain. pp. 1-5. ⟨hal-01466637⟩

Share

Metrics

Record views

266

Files downloads

326