Premium
On expectation propagation for generalised, linear and mixed models
Author(s) -
Kim Andy S.I.,
Wand Matt P.
Publication year - 2018
Publication title -
australian and new zealand journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 1369-1473
DOI - 10.1111/anzs.12199
Subject(s) - expectation propagation , graphical model , factor graph , computation , inference , approximate inference , mathematics , belief propagation , bayesian inference , algebraic number , approximate bayesian computation , theoretical computer science , algorithm , bayesian probability , computer science , artificial intelligence , statistics , gaussian process , mathematical analysis , physics , decoding methods , quantum mechanics , gaussian
Summary Expectation propagation is a general approach to deterministic approximate Bayesian inference for graphical models, although its literature is confined mostly to machine learning applications. We investigate the utility of expectation propagation in generalised, linear, and mixed model settings. We show that, even though the algebra and computations are complicated, the notion of message passing on factor graphs affords streamlining of the required calculations and we list the algorithmic steps explicitly. Numerical studies indicate expectation propagation is marginally more accurate than a competing method for the models considered, but at the expense of bigger algebraic and computational overheads.