Abstract
Expectation Propagation (EP) extends belief propagation by approximating messages with expectations of statistics, in which users can choose the statistics. In this paper, we discuss how a choice of statistics affects accuracy of EP’s estimates. We approximate estimation error of EP via perturbation analysis based on information geometry. By comparing the approximated estimation error, we show that adding statistics does not necessarily improve the accuracy of EP. A numerical example confirms validity of our analytical results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Minka, T.: A Family of Algorithms for Approximate Bayesian Inference. Ph.D. thesis, Massachusetts Institute of Technology (2001)
Heskes, T., Opper, M., Wiegerinck, W., Winther, O., Zoeter, O.: Approximate inference techniques with expectation constraints. J. Stat. Mech.: Theory Exp., P11015 (2005)
Wainwright, M.J.: Stochastic Processes on Graphs with Cycles. Ph.D. thesis, Massachusetts Institute of Technology (2002)
Amari, S., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs, vol. 191. American Mathematical Society (2001)
Ikeda, S., Tanaka, T., Amari, S.: Information geometry of turbo and low-density parity-check codes. IEEE Trans. Info. Theory 50, 1097–1114 (2004)
Ikeda, S., Tanaka, T., Amari, S.: Stochastic reasoning, free energy, and information geometry. Neural Comput. 16, 1779–1810 (2004)
Welling, M.: On the choice of regions for generalized belief propagation. In: Proc. 20th Conf. Uncertainty in AI, pp. 585–592 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matsui, H., Tanaka, T. (2009). Analysis on Equilibrium Point of Expectation Propagation Using Information Geometry. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5507. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03040-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-03040-6_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03039-0
Online ISBN: 978-3-642-03040-6
eBook Packages: Computer ScienceComputer Science (R0)