Complexity of approximating MAPs for belief networks with bounded probabilities

Artificial Intelligence

Volumn 124, Issue 2, 2000, Pages 283-288

  Abdelbar, Ashraf M ^a   Hedetniemi, Stephen T ^b   Hedetniemi, Sandra M ^b  

^a AMERICAN UNIVERSITY IN CAIRO   (Egypt)

^b Clemson University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; INFERENCE ENGINES; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES;

BAYESIAN BELIEF NETWORKS; BIPARTITE NETWORKS; LOCAL VARIANCE BOUND THEORY;

ARTIFICIAL INTELLIGENCE;

EID: 0034502875     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(00)00076-X     Document Type: Article

References (9)

1. Abdelbar A.M., Hedetniemi S.M. Approximating MAPs on belief networks is NP-hard and other theorems. Artificial Intelligence. 102:1998;21-38.
2. Cooper G.F. The computational complexity of probabilistic inference using Bayesian belief networks. Artificial Intelligence. 42:1990;393-405.
3. Dagum P., Luby M. Approximating probabilistic inference in Bayesian belief networks is NP-hard. Artificial Intelligence. 60:1993;141-153.
4. Dagum P., Luby M. An optimal approximation algorithm for Bayesian inference. Artificial Intelligence. 93:1997;1-27.
5. Garey M., Johnson D. Computers and Intractability: A Guide to the Theory of NP-Completeness. 1979;Freeman, New York.
6. Papadimitriou C. Computational Complexity. 1994;Addison-Wesley, Reading, MA.
7. Pearl J. Fusion, propagation, and structuring in belief networks. Artificial Intelligence. 29:1986;241-288.
8. Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. 1988;Morgan Kauffman, San Mateo, CA.
9. Shimony S.E. Finding MAPs for belief networks is NP-hard. Artificial Intelligence. 68:1994;399-410.