An upper bound for BDeu local scores

James Cussens

An upper bound for BDeu local scores

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

An upper bound on BDeu log local scores is derived using an existing upper bound on the beta function with $r$ variables. Two bounds on this bound are derived, one of which is suitable for pruning the search for optimal parent sets of a variable in Bayesian network learning. Empirical results concerning the tightness of bounds are given.

Original language	English
Title of host publication	Proc. ECAI-2012 workshop on algorithmic issues for inference in graphical models (AIGM 2012)
Publication status	Published - 2012

Access to Document

Cite this

@inproceedings{d97260835c2e4b9d8a08452639734f10,

title = "An upper bound for BDeu local scores",

abstract = "An upper bound on BDeu log local scores is derived using an existing upper bound on the beta function with $r$ variables. Two bounds on this bound are derived, one of which is suitable for pruning the search for optimal parent sets of a variable in Bayesian network learning. Empirical results concerning the tightness of bounds are given.",

author = "James Cussens",

year = "2012",

language = "English",

booktitle = "Proc. ECAI-2012 workshop on algorithmic issues for inference in graphical models (AIGM 2012)",

}

TY - GEN

T1 - An upper bound for BDeu local scores

AU - Cussens, James

PY - 2012

Y1 - 2012

N2 - An upper bound on BDeu log local scores is derived using an existing upper bound on the beta function with $r$ variables. Two bounds on this bound are derived, one of which is suitable for pruning the search for optimal parent sets of a variable in Bayesian network learning. Empirical results concerning the tightness of bounds are given.

AB - An upper bound on BDeu log local scores is derived using an existing upper bound on the beta function with $r$ variables. Two bounds on this bound are derived, one of which is suitable for pruning the search for optimal parent sets of a variable in Bayesian network learning. Empirical results concerning the tightness of bounds are given.

M3 - Conference contribution

BT - Proc. ECAI-2012 workshop on algorithmic issues for inference in graphical models (AIGM 2012)

ER -