Required sample size for learning sparse Bayesian networks with many variables
| dc.creator | Wocjan, Pawel | |
| dc.creator | Janzing, Dominik | |
| dc.creator | Beth, Thomas | |
| dc.date | 2002-04-26 | |
| dc.date.accessioned | 2026-07-26T00:01:14Z | |
| dc.description | 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. | |
| dc.description | 9 pages | |
| dc.identifier | https://arxiv.org/abs/cs/0204052 | |
| dc.identifier | http://arxiv.org/abs/cs/0204052 | |
| dc.identifier.uri | https://dspace.dare.co.zw/handle/123456789/103392 | |
| dc.subject | Machine Learning | |
| dc.subject | Probability | |
| dc.subject | I.2.6 | |
| dc.title | Required sample size for learning sparse Bayesian networks with many variables | |
| dc.type | text |