Improving on Expectation Propagation

Part of Advances in Neural Information Processing Systems 21 (NIPS 2008)

Bibtex Metadata Paper

Authors

Manfred Opper, Ulrich Paquet, Ole Winther

Abstract

We develop as series of corrections to Expectation Propagation (EP), which is one of the most popular methods for approximate probabilistic inference. These corrections can lead to improvements of the inference approximation or serve as a sanity check, indicating when EP yields unrealiable results.