A Dynamic Programming Algorithm for Learning Chain Event Graphs
Conference Proceeding Article
Chain event graphs are a model family particularly suited for asymmetric causal discrete domains. This paper describes a dynamic programming algorithm for exact learning of chain event graphs from multivariate data. While the exact algorithm is slow, it allows reasonably fast approximations and provides clues for implementing more scalable heuristic algorithms. © 2013 Springer-Verlag.
chain event graphs, model selection, structure learning
Theory and Algorithms
Intelligent Systems and Decision Analytics
16th International Conference, Discovery Science 2013, Singapore, October 6-9, 2013. Proceedings
City or Country
Silander T. and Tze-Yun LEONG.
A Dynamic Programming Algorithm for Learning Chain Event Graphs. (2013). 16th International Conference, Discovery Science 2013, Singapore, October 6-9, 2013. Proceedings. 201-216. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2985