A Review of Bayesian Networks and Structure Learning

Timo J.T. Koski, and John Noble. "A Review of Bayesian Networks and Structure Learning." Mathematica Applicanda 40.1 (2012): null. <http://eudml.org/doc/292706>.

@article{TimoJ2012,
abstract = {This article reviews the topic of Bayesian networks. A Bayesian network  is a factorisation of a probability distribution along a directed acyclic graph. The relation between graphical d-separation and independence is described. A short article by Arthur Cayley (1853) [7] is discussed, which laid ideas later used in Bayesian networks: factorisation, the noisy `or' gate, applications of algebraic geometry to Bayesian networks. The ideas behind Pearl's intervention calculus when the DAG represents a causal dependence structure; the relation between the work of Cayley and Pearl is commented on.Most of the discussion is about structure learning, outlining the two main approaches; search and score versus constraint based. Constraint based algorithms often rely on the assumption of faithfulness, that the data to which the algorithm is applied is generated from distributions satisfying a faithfulness assumption where graphical d- separation and independence are equivalent. The article presents some considerations for constraint based algorithms based on recent data analysis, indicating a variety of situations where the faithfulness assumption does not hold.},
author = {Timo J.T. Koski, John Noble},
journal = {Mathematica Applicanda},
keywords = {Bayesian networks, directed acyclic graph, Arthur Cayley, intervention calculus, graphical Markov model, Markov equivalence, structure learning},
language = {eng},
number = {1},
pages = {null},
title = {A Review of Bayesian Networks and Structure Learning},
url = {http://eudml.org/doc/292706},
volume = {40},
year = {2012},
}

TY - JOUR
AU - Timo J.T. Koski
AU - John Noble
TI - A Review of Bayesian Networks and Structure Learning
JO - Mathematica Applicanda
PY - 2012
VL - 40
IS - 1
SP - null
AB - This article reviews the topic of Bayesian networks. A Bayesian network  is a factorisation of a probability distribution along a directed acyclic graph. The relation between graphical d-separation and independence is described. A short article by Arthur Cayley (1853) [7] is discussed, which laid ideas later used in Bayesian networks: factorisation, the noisy `or' gate, applications of algebraic geometry to Bayesian networks. The ideas behind Pearl's intervention calculus when the DAG represents a causal dependence structure; the relation between the work of Cayley and Pearl is commented on.Most of the discussion is about structure learning, outlining the two main approaches; search and score versus constraint based. Constraint based algorithms often rely on the assumption of faithfulness, that the data to which the algorithm is applied is generated from distributions satisfying a faithfulness assumption where graphical d- separation and independence are equivalent. The article presents some considerations for constraint based algorithms based on recent data analysis, indicating a variety of situations where the faithfulness assumption does not hold.
LA - eng
KW - Bayesian networks, directed acyclic graph, Arthur Cayley, intervention calculus, graphical Markov model, Markov equivalence, structure learning
UR - http://eudml.org/doc/292706
ER -