Programme
The workshop will be held on 17-19 September 2014. It will consist of three days of plenary sessions. There will be a welcome reception on September 17 and the conference dinner will be on September 18.Technical Programme
Wednesday, September 17
08:30-09:00 Registration
09:00-10:15 Opening and Session 1: Causal Discovery
Chair: Stijn Meganck
10:15-10:45 Coffee break
- Elena Sokolova, Perry Groot, Tom Claassen and Tom Heskes: Causal discovery from databases with discrete and continuous variables
- Sofia Triantafillou, Ioannis Tsamardinos and Anna Roumpelaki: Learning neighborhoods of high confidence in constraint-based causal discovery
- Martijn de Jongh and Marek Druzdzel: Evaluation of Rules for Coping with Insufficient Data in Constraint-based Search Algorithms
10:45-12:25 Session 2: Multi-label Classification
Chair: Helge Langseth
12:25-14:15 Lunch
- Giorgio Corani, Alessandro Antonucci, Denis Mauá and Sandra Gabaglio: Trading off speed and accuracy in multilabel classification
- Gherardo Varando, Concha Bielza and Pedro Larrañaga: Expressive Power of Binary Relevance and Chain Classifiers Based on Bayesian Networks for Multi-Label Classification
- Jacinto Arias, José A. Gámez, Thomas D. Nielsen and José M. Puerta: A pairwise class interaction framework for multilabel classification
- Mallinali Ramírez-Corona, Luis Enrique Sucar and Eduardo Morales: Multi-label Classification for Tree and Directed Acyclic Graphs Hierachies
14:15-15:55 Session 3: Inference
Chair: Thomas D. Nielsen
15:55-16:30 Refreshments break
- Cory Butz, Jhonatan de S. Oliveira and Anders Madsen: Bayesian Network Inference Using Marginal Trees
- Andrés Cano Utrera, Manuel Gómez-Olmedo, Serafín Moral Callejón and Cora B. Pérez-Ariza: Extended Probability Trees for Probabilistic Graphical Models
- Cedric De Boom, Jasper De Bock, Arthur Van Camp and Gert De Cooman: Robustifying the Viterbi algorithm
- Jirka Vomlel and Petr Tichavský: An approximate tensor-based inference method applied to the game of Minesweeper
16:30-17:45 Session 4: Knowledge-based Learning
Chair: Ann E. Nicholson
- Jidapa Kraisangka and Marek Druzdzel: Discrete Bayesian Network Interpretation of the Cox's Proportional Hazards Model
- Yun Zhou, Norman Fenton and Martin Neil: An Extended MPL-C Model for Bayesian Network Parameter Learning with Exterior Constraints
- Marcus Bendtsen and Jose M. Peña: Learning Gated Bayesian Networks for Algorithmic Trading
17:45-18:30 Guided tour to Domplein18:30-20:00 Welcome reception in the Dom church courtyard
Thursday, September 18
08:30-09:00 Coffee
09:00-10:15 Invited talk by Robert Cowell: Analysis of DNA Mixtures using Bayesian networks10:15-10:45 Coffee break
10:45-12:25 Session 5: Foundations
Chair: Jirka Vomlel
12:25-14:15 Lunch
- Ali Ben Mrad, Véronique Delcroix, Sylvain Piechowiak and Philip Leicester: From information to evidence in a Bayesian network
- Johan Kwisthout: Minimizing relative entropy in Hierarchical Predictive Coding
- Denis Mauá: Equivalences Between Maximum A Posteriori Inference in Bayesian Networks and Maximum Expected Utility Computation in Influence Diagrams
- Johan Kwisthout: Treewidth and the Computational Complexity of MAP Approximations
14:15-15:55 Session 6: Structure Learning
Chair: Antonio Salmerón
15:55-16:30 Refreshments break
- Mauro Scanagatta, Cassio de Campos and Marco Zaffalon: Min-BDeu and Max-BDeu Scores for Learning Bayesian Networks
- Aritz Pérez, Christian Blum and Jose A. Lozano: Learning maximum weighted (k+1)-order decomposable graphs by Integer Linear Programming
- José M. Peña: Learning Marginal AMP Chain Graphs under Faithfulness
- Joe Suzuki: Learning Bayesian network structures when discrete and continous variables are present
16:30-17:20 Session 7: Influence Diagrams
Chair: Silja Renooij
- Rafael Cabañas, Andrés Cano, Manuel Gómez-Olmedo and Anders Madsen: On SPI-Lazy Evaluation of Influence Diagrams
- Denis Mauá and Fabio Cozman: Speeding Up k-Neighborhood Local Search in Limited Memory Influence Diagrams
17:30-18:00 Bussiness meeting18:30-23:00: Conference dinner at Paushuize
Friday, September 19
08:30-09:00 Coffee
09:00-10:15 Session 8: Analysis
Chair: Marek J. Druzdzel
10:15-10:45 Coffee break
- Gabor Hullam and Peter Antal: Towards a Bayesian decision theoretic analysis of contextual effect modifiers
- David Albrecht, Ann Nicholson and Chris Whittle: Structural Sensitivity for the Knowledge Engineering of Bayesian Networks
- Janneke Bolt and Silja Renooij: Local Sensitivity of Bayesian Networks to Multiple Simultaneous Parameter Shifts
10:45-12:25 Session 9: Parameter Models
Chair: Peter Lucas
12:25-14:15 Lunch
- Krzysztof Nowak and Marek Druzdzel: Learning Parameters in Canonical Models using Weighted Least Squares
- Maarten van der Heijden and Arjen Hommersom: Causal Independence Models for Continuous Time Bayesian Networks
- Wannes Meert and Joost Vennekens: Inhibited effects in CP-logic
- Barry Cobb: Mixture of Polynomials Probability Distributions for Grouped Sample Data
14:15-15:55 Session 10: Representation
Chair: José M. Peña
15:55-16:30 Refreshments break
- Nevin L. Zhang, Xiaofei Wang and Peixian Chen: A Study of Recently Discovered Equalities about Latent Tree Models using Inverse Edges
- Anders Madsen, Frank Jensen, Martin Karlsen and Nicolaj Søndberg-Jeppesen: Bayesian Networks with Function Nodes
- Yang Xiang and Qing Liu: Compression of Bayesian Networks with NIN-AND Tree Modeling
- Dag Sonntag: On Expressiveness of the AMP Chain Graph Interpretation
16:30-17:45 Session 11: Classifier Learning
Chair: Alessandro Antonucci
- Anders Madsen, Frank Jensen, Antonio Salmerón, Martin Karlsen, Helge Langseth and Thomas Nielsen: A New Method for Vertical Parallelisation of TAN Learning Based on Balanced Incomplete Block Designs
- Cassio De Campos, Marco Cuccu, Giorgio Corani and Marco Zaffalon: Extended Tree Augmented Naive Classifier
- Antonio Fernández, Rafael Rumí, José Del Sagrado and Antonio Salmerón: Supervised Classification Using Hybrid Probabilistic Decision Graphs