Required sample size for learning sparse Bayesian networks with many variables

dc.creatorWocjan, Pawel
dc.creatorJanzing, Dominik
dc.creatorBeth, Thomas
dc.date2002-04-26
dc.date.accessioned2026-07-26T00:01:14Z
dc.descriptionLearning joint probability distributions on n random variables requires exponential sample size in the generic case. Here we consider the case that a temporal (or causal) order of the variables is known and that the (unknown) graph of causal dependencies has bounded in-degree Delta. Then the joint measure is uniquely determined by the probabilities of all (2 Delta+1)-tuples. Upper bounds on the sample size required for estimating their probabilities can be given in terms of the VC-dimension of the set of corresponding cylinder sets. The sample size grows less than linearly with n.
dc.description9 pages
dc.identifierhttps://arxiv.org/abs/cs/0204052
dc.identifierhttp://arxiv.org/abs/cs/0204052
dc.identifier.urihttps://dspace.dare.co.zw/handle/123456789/103392
dc.subjectMachine Learning
dc.subjectProbability
dc.subjectI.2.6
dc.titleRequired sample size for learning sparse Bayesian networks with many variables
dc.typetext

Files