Prague , Czech Republic September 12 − 15 , 2006 Probabilistic Graphical Models

ion and Refinement for Solving Continuous Markov Decision Processes. . . . . . . . . . . . . . .263Alberto Reyes, Pablo Ibargüengoytia, L. Enrique Sucar, and Eduardo Morales Bayesian Model Averaging of TAN Models for Clustering. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .271Guzmán Santafé, Jose A. Lozano, and Pedro Larrañaga Dynamic Weighting A* Search-based MAP Algorithm for Bayesian Networks . . . . . . . . . . . . . . . . . 279Xiaoxun Sun, Marek J. Druzdzel, and Changhe Yuan A Short Note on Discrete Representability of Independence Models . . . . . . . . . . . . . . . . . . . . . . . . . . .287Petr Šimeček Evaluating Causal effects using Chain Event Graphs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 293Peter Thwaites and Jim Smith Severity of Local Maxima for the EM Algorithm: Experiences with HierarchicalLatent Class Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 301Yi Wang and Nevin L. Zhang Optimal Design with Design Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 309Yang Xiang Hybrid Loopy Belief Propagation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 317Changhe Yuan and Marek J. Druzdzel Probabilistic Independence of Causal Influences . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 325Adam Zagorecki and Marek J. Druzdzel Some Variations on the PC Algorithm J. Abellán, M. Gómez-Olmedo, and S. MoralDepartment of Computer Science and Artificial IntelligenceUniversity of Granada18071 Granada, Spain