Number of the records: 1
Efficient algorithms for conditional independence inference
- 1.
SYSNO ASEP 0353652 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Efficient algorithms for conditional independence inference Author(s) Bouckaert, R. (NZ)
Hemmecke, R. (DE)
Lindner, S. (DE)
Studený, Milan (UTIA-B) RID, ORCIDSource Title Journal of Machine Learning Research - ISSN 1532-4435
Roč. 11, č. 1 (2010), s. 3453-3479Number of pages 27 s. Language eng - English Country US - United States Keywords conditional independence inference ; linear programming approach Subject RIV BA - General Mathematics R&D Projects GA201/08/0539 GA ČR - Czech Science Foundation (CSF) 1M0572 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) CEZ AV0Z10750506 - UTIA-B (2005-2011) UT WOS 000286637200006 Annotation The topic of the paper is computer testing of (probabilistic) conditional independence (CI) implications by an algebraic method of structural imsets. The basic idea is to transform CI statements into certain integral vectors and to verify by a computer the corresponding algebraic relation between the vectors, called the independence implication. The main contribution of the paper is a new method, based on linear programming (LP), which overcomes the limitation of former methods to the number of involved variables. The computational experiments, described in the paper, also show that the new method is faster than the previous ones. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2011
Number of the records: 1