Computer Science – Learning
Scientific paper
2002-04-26
Computer Science
Learning
9 pages
Scientific paper
Learning 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.
Beth Thomas
Janzing Dominik
Wocjan Pawel
No associations
LandOfFree
Required sample size for learning sparse Bayesian networks with many variables does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Required sample size for learning sparse Bayesian networks with many variables, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Required sample size for learning sparse Bayesian networks with many variables will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-397264