Header logo is

Expectation Propagation on the Maximum of Correlated Normal Variables

2009

Technical Report

ei

pn


Many inference problems involving questions of optimality ask for the maximum or the minimum of a finite set of unknown quantities. This technical report derives the first two posterior moments of the maximum of two correlated Gaussian variables and the first two posterior moments of the two generating variables (corresponding to Gaussian approximations minimizing relative entropy). It is shown how this can be used to build a heuristic approximation to the maximum relationship over a finite set of Gaussian variables, allowing approximate inference by Expectation Propagation on such quantities.

Author(s): Hennig, P.
Year: 2009
Month: July
Day: 0

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

Institution: Cavendish Laboratory: University of Cambridge

Digital: 0

Links: Web

BibTex

@techreport{Hennig2009,
  title = {Expectation Propagation on the Maximum of Correlated Normal Variables},
  author = {Hennig, P.},
  institution = {Cavendish Laboratory: University of Cambridge},
  month = jul,
  year = {2009},
  doi = {},
  month_numeric = {7}
}