Bayesian Orthogonal Component Analysis for Sparse Representation

DOI10.1109/TSP.2010.2041594MaRDI QIDQ4570254zbMATH OpenOpenAlexWikidataFDO

Authors Nicolas Dobigeon, Jean-Yves Tourneret

Publication date 9 July 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0908.4489

Mathematics Subject Classification ID

Bayesian inference (62F15) Factor analysis and principal components; correspondence analysis (62H25) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: This paper addresses the problem of identifying a lower dimensional space where observed data can be sparsely represented. This under-complete dictionary learning task can be formulated as a blind separation problem of sparse sources linearly mixed with an unknown orthogonal mixing matrix. This issue is formulated in a Bayesian framework. First, the unknown sparse sources are modeled as Bernoulli-Gaussian processes. To promote sparsity, a weighted mixture of an atom at zero and a Gaussian distribution is proposed as prior distribution for the unobserved sources. A non-informative prior distribution defined on an appropriate Stiefel manifold is elected for the mixing matrix. The Bayesian inference on the unknown parameters is conducted using a Markov chain Monte Carlo (MCMC) method. A partially collapsed Gibbs sampler is designed to generate samples asymptotically distributed according to the joint posterior distribution of the unknown model parameters and hyperparameters. These samples are then used to approximate the joint maximum a posteriori estimator of the sources and mixing matrix. Simulations conducted on synthetic data are reported to illustrate the performance of the method for recovering sparse representations. An application to sparse coding on under-complete dictionary is finally investigated.

Recommendations

• An Iterative Bayesian Algorithm for Sparse Component Analysis in Presence of Noise
• Bayesian robust principal component analysis with structured sparse component
• Bayesian sparse partial least squares
• Sparse Non-Gaussian Component Analysis
• Bayesian sparse covariance decomposition with a graphical structure
• Sparse Bayesian Methods for Low-Rank Matrix Estimation
• Simultaneous Bayesian Sparse Approximation With Structured Sparse Models
• Sparse Bayesian Learning for Robust PCA: Algorithms and Analyses
• Sparse Bayesian Learning for Basis Selection

Cited in

(8)

• Toward fast transform learning
• Sparse variational Bayesian approximations for nonlinear inverse problems: applications in nonlinear elastography
• Geodesic Monte Carlo on embedded manifolds
• An Iterative Bayesian Algorithm for Sparse Component Analysis in Presence of Noise
• Some recent developments in Markov chain Monte Carlo for cointegrated time series
• Discussion on the Paper by Byrne and Girolami
• Functional principal component models for sparse and irregularly spaced data by Bayesian inference
• Variational Bayesian strategies for high-dimensional, stochastic design problems

This page was built for publication: Bayesian Orthogonal Component Analysis for Sparse Representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4570254)