A Dynamic Programming Algorithm for Learning Chain Event Graphs

• Main Authors: Silander T., Tze-Yun LEONG
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2013
• Subjects: chain event graphs; model selection; structure learning; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/2985; http://link.springer.com/chapter/10.1007%2F978-3-642-40897-7_14
• Institution: Singapore Management University

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 prov...