Back
Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference
We propose a novel algorithm to solve the expectation propagation relaxation of Bayesian inference for continuous-variable graphical models. In contrast to most previous algorithms, our method is provably convergent. By marrying convergent EP ideas from (Opper&Winther, 2005) with covariance decoupling techniques (Wipf&Nagarajan, 2008; Nickisch&Seeger, 2009), it runs at least an order of magnitude faster than the most common EP solver.
@inproceedings{SeegerN2011, title = {Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference }, booktitle = {JMLR Workshop and Conference Proceedings Volume 15: AISTATS 2011}, abstract = {We propose a novel algorithm to solve the expectation propagation relaxation of Bayesian inference for continuous-variable graphical models. In contrast to most previous algorithms, our method is provably convergent. By marrying convergent EP ideas from (Opper&Winther, 2005) with covariance decoupling techniques (Wipf&Nagarajan, 2008; Nickisch&Seeger, 2009), it runs at least an order of magnitude faster than the most common EP solver. }, pages = {652-660}, editors = {Gordon, G. , D. Dunson, M. Dudík }, publisher = {MIT Press}, address = {Cambridge, MA, USA}, month = apr, year = {2011}, slug = {seegern2011}, author = {Seeger, M. and Nickisch, H.}, month_numeric = {4} }