Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
On the hardness of approximate reasoning
Artificial Intelligence
Bucket elimination: a unifying framework for reasoning
Artificial Intelligence
Journal of Computer and System Sciences - Special issue on the fourteenth annual IEE conference on computational complexity
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Stochastic Boolean Satisfiability
Journal of Automated Reasoning
Treewidth: Algorithmoc Techniques and Results
MFCS '97 Proceedings of the 22nd International Symposium on Mathematical Foundations of Computer Science
The complexity of homomorphism and constraint satisfaction problems seen from the other side
Journal of the ACM (JACM)
FOCS '07 Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science
Treewidth: characterizations, applications, and computations
WG'06 Proceedings of the 32nd international conference on Graph-Theoretic Concepts in Computer Science
Efficiently approximating Markov tree bagging for high-dimensional density estimation
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part III
Parameterized complexity results for exact bayesian network structure learning
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
Algorithms for probabilistic inference in Bayesian networks are known to have running times that are worst-case exponential in the size of the network. For networks with a moralised graph of bounded treewidth, however, these algorithms take a time which is linear in the network's size. In this paper, we show that under the assumption of the Exponential Time Hypothesis (ETH), small treewidth of the moralised graph actually is a necessary condition for a Bayesian network to render inference efficient by an algorithm accepting arbitrary instances. We thus show that no algorithm can exist that performs inference on arbitrary Bayesian networks of unbounded treewidth in polynomial time, unless the ETH fails.