Output details
11 - Computer Science and Informatics
University of York
Output title
Bayesian network learning by compiling to weighted MAX-SAT
Type
E - Conference contribution
DOI
-
Name of conference/published proceedings
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence (UAI 2008)
Volume number
-
Issue number
-
First page of article
105
ISSN of proceedings
-
Year of publication
2008
Number of additional authors
0
Additional information
<13>This paper is the first to show that Bayesian network learning can be represented as a weighted MAX-SAT problem . It is among those studied in a module "Constraint Solving Meets Machine Learning and Data Mining" at U. Helsinki. It was also extensively discussed in this IJCAI-13 tutorial "SAT in AI: high performance search methods with applications". This work led to work applying weighted MAX-SAT to data clustering, published in the paper “Searching a multivariate partition space using MAX-SAT” which I co-authored with colleagues in the Warwick Statistics Dept. UAI-08 acceptance rate: 28%
Interdisciplinary
-
Cross-referral requested
-
Research group
G - Artificial Intelligence
Citation count
5
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-