Abstract | ||
---|---|---|
In this work, we develop a novel robust Bayesian approach to inverse problems with data errors following a skew-t distribution. A hierarchical Bayesian model is developed in the inverse problem setup. The Bayesian approach contains a natural mechanism for regularization in the form of a prior distribution, and a LASSO type prior distribution is used to strongly induce sparseness. We propose a variational type algorithm by minimizing the Kullback-Leibler divergence between the true posterior distribution and a separable approximation. The proposed method is illustrated on several two-dimensional linear and nonlinear inverse problems, e.g. Cauchy problem and permeability estimation problem. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1016/j.jcp.2015.07.062 | Journal of Computational Physics |
Keywords | Field | DocType |
Bayesian inverse problems,Hierarchical Bayesian model,Variational approximation,Kullback–Leibler divergence | Bayesian experimental design,Mathematical optimization,Categorical distribution,Bayesian linear regression,Inverse-chi-squared distribution,Bayesian hierarchical modeling,Dirichlet distribution,Bayesian statistics,Mathematics,Scaled inverse chi-squared distribution | Journal |
Volume | Issue | ISSN |
301 | C | 0021-9991 |
Citations | PageRank | References |
2 | 0.42 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nilabja Guha | 1 | 10 | 2.29 |
Xiaoqing Wu | 2 | 2 | 0.42 |
Yalchin Efendiev | 3 | 581 | 67.04 |
Bangti Jin | 4 | 297 | 34.45 |
Bani K. Mallick | 5 | 202 | 20.05 |