Variational Gaussian Copula Inference

Shaobo Han, Xuejun Liao, David Dunson, Lawrence Carin
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:829-838, 2016.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v51-han16, title = {Variational Gaussian Copula Inference}, author = {Han, Shaobo and Liao, Xuejun and Dunson, David and Carin, Lawrence}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {829--838}, year = {2016}, editor = {Gretton, Arthur and Robert, Christian C.}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/han16.pdf}, url = {https://proceedings.mlr.press/v51/han16.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Variational Gaussian Copula Inference %A Shaobo Han %A Xuejun Liao %A David Dunson %A Lawrence Carin %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-han16 %I PMLR %P 829--838 %U https://proceedings.mlr.press/v51/han16.html %V 51 %X 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.
RIS
TY - CPAPER TI - Variational Gaussian Copula Inference AU - Shaobo Han AU - Xuejun Liao AU - David Dunson AU - Lawrence Carin BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-han16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 51 SP - 829 EP - 838 L1 - http://proceedings.mlr.press/v51/han16.pdf UR - https://proceedings.mlr.press/v51/han16.html AB - 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. ER -
APA
Han, S., Liao, X., Dunson, D. & Carin, L.. (2016). Variational Gaussian Copula Inference. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 51:829-838 Available from https://proceedings.mlr.press/v51/han16.html.

Related Material