Variational Gaussian copula inference
Conference Paper
We utilize copulas to constitute a unified framework for constructing and optimizing variational proposals in hierarchical Bayesian models. For models with continuous and non-Gaussian hidden variables, we propose a semiparametric and automated variational Gaussian copula approach, in which the parametric Gaussian copula family is able to preserve multivariate posterior dependence, and the nonparametric transformations based on Bernstein polynomials provide ample flexibility in characterizing the univariate marginal posteriors.
Duke Authors
Cited Authors
- Han, S; Liao, X; Dunson, DB; Carin, L
Published Date
- January 1, 2016
Published In
- Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, Aistats 2016
Start / End Page
- 829 - 838
Citation Source
- Scopus