Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.11889/4207
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sayrafi, Bassem | - |
dc.contributor.author | Niepert, Mathias | - |
dc.contributor.author | Van Gucht, Dirk | - |
dc.contributor.author | Gyssens, Marc | - |
dc.date.accessioned | 2017-01-31T13:16:53Z | - |
dc.date.available | 2017-01-31T13:16:53Z | - |
dc.date.issued | 2013 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11889/4207 | - |
dc.description.abstract | A lattice-theoretic framework is introduced that permits the study of the conditional independence (CI) implication problem relative to the class of discrete probability measures. Semi-lattices are associated with CI statements and a finite, sound and complete inference system relative to semi-lattice inclusion is presented. This system is shown to be (1) sound and complete for saturated CI statements, (2) complete for general CI statements, and (3) sound and complete for stable CI statements. These results yield a criterion that can be used to falsify instances of the implication problem and several heuristics are derived that approximate this “latticeexclusion” criterion in polynomial time. Finally, we provide experimental results that relate our work to results obtained from other existing inference algorithms | en_US |
dc.language.iso | en | en_US |
dc.subject | Logic, Symbolic and mathematical | en_US |
dc.subject | Artificial intelligence | en_US |
dc.title | On the Conditional Independence Implication Problem: A Lattice-Theoretic Approach | en_US |
dc.type | Article | en_US |
newfileds.department | Engineering and TechnologyEngineering and Technology | en_US |
newfileds.item-access-type | open_access | en_US |
newfileds.thesis-prog | none | en_US |
newfileds.general-subject | none | en_US |
item.fulltext | With Fulltext | - |
item.languageiso639-1 | other | - |
item.grantfulltext | open | - |
Appears in Collections: | Fulltext Publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1408.2030.pdf | 180.78 kB | Adobe PDF | View/Open |
Page view(s)
103
Last Week
0
0
Last month
2
2
checked on Apr 14, 2024
Download(s)
27
checked on Apr 14, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.