Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference

2010

Technical Report

ei


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 05) with covariance decoupling techniques (Wipf&Nagarajan 08, Nickisch&Seeger 09), it runs at least an order of magnitude faster than the most commonly used EP solver.

Author(s): Seeger, M. and Nickisch, H.
Year: 2010
Month: December
Day: 0

Department(s): Empirical Inference
Bibtex Type: Technical Report (techreport)

Institution: Max Planck Institute for Biological Cybernetics

Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: Web

BibTex

@techreport{6995,
  title = {Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference},
  author = {Seeger, M. and Nickisch, H.},
  organization = {Max-Planck-Gesellschaft},
  institution = {Max Planck Institute for Biological Cybernetics},
  school = {Biologische Kybernetik},
  month = dec,
  year = {2010},
  month_numeric = {12}
}