A variational Bayesian framework for graphical models

@misc{citeulike:519793, abstract = {This paper presents a novel practical framework for Bayesian model averaging and model selection in probabilistic graphical models. Our approach approximates full posterior distributions over model parameters and structures, as well as latent variables, in an analytical manner. These posteriors fall out of a free-form optimization procedure, which naturally incorporates conjugate priors. Unlike in large sample approximations, the posteriors are generally nonGaussian and no Hessian needs...}, author = {Attias, H. }, citeulike-article-id = {519793}, keywords = {bayesian, graphical, models, variational\_inference}, posted-at = {2008-06-26 16:25:27}, priority = {2}, title = {A variational Bayesian framework for graphical models}, url = {http://citeseer.ist.psu.edu/attias00variational.html}, year = {2000} }

TY - GEN ID - citeulike:519793 L3 - citeulike-article-id:519793 TI - A variational Bayesian framework for graphical models N2 - This paper presents a novel practical framework for Bayesian model averaging and model selection in probabilistic graphical models. Our approach approximates full posterior distributions over model parameters and structures, as well as latent variables, in an analytical manner. These posteriors fall out of a free-form optimization procedure, which naturally incorporates conjugate priors. Unlike in large sample approximations, the posteriors are generally nonGaussian and no Hessian needs... KW - bayesian KW - graphical KW - models KW - variational_inference AU - Attias, H PY - 2000/// UR - http://citeseer.ist.psu.edu/attias00variational.html ER -