Show simple item record

dc.contributor.authorBooth, Richard
dc.contributor.authorChevaleyre, Yann
dc.contributor.authorLang, Jérôme
dc.contributor.authorMengin, Jérôme
HAL ID: 184956
dc.contributor.authorSombattheera, Chattrakul
dc.date.accessioned2014-02-11T14:46:01Z
dc.date.available2014-02-11T14:46:01Z
dc.date.issued2010
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/12628
dc.language.isoenen
dc.subjectLP-trees
dc.subject.ddc006.3en
dc.titleLearning conditionally lexicographic preference relations
dc.typeCommunication / Conférence
dc.description.abstractenWe consider the problem of learning a user's ordinal preferences on a multiattribute domain, assuming that her preferences are lexicographic. We introduce a general graphical representation called LP-trees which captures various natural classes of such preference relations, depending on whether the importance order between attributes and/or the local preferences on the domain of each attribute is conditional on the values of other attributes. For each class we determine the Vapnik-Chernovenkis dimension, the communication complexity of preference elicitation, and the complexity of identifying a model in the class consistent with a set of user-provided examples.
dc.identifier.citationpages269-274
dc.relation.ispartoftitleECAI 2010 19th European Conference on Artificial Intelligence 16–20 August 2010, Lisbon, Portugal - proceedings
dc.relation.ispartofeditorWooldridge, Michael
dc.relation.ispartofpublnameIOS Press
dc.relation.ispartofpublcityTokyo
dc.relation.ispartofdate2010
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-1-60750-605-8
dc.relation.confcountryPORTUGAL
dc.relation.forthcomingnonen
dc.description.ssrncandidatenon
dc.description.halcandidateoui
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2017-09-29T16:45:05Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record