Learning various classes of models of lexicographic orderings

Booth, Richard; Chevaleyre, Yann; Lang, Jérôme; Mengin, Jérôme; Sombattheera, Chattrakul

dc.contributor.author	Booth, Richard
dc.contributor.author	Chevaleyre, Yann
dc.contributor.author	Lang, Jérôme
dc.contributor.author	Mengin, Jérôme HAL ID: 184956
dc.contributor.author	Sombattheera, Chattrakul
dc.date.accessioned	2010-12-17T10:48:54Z
dc.date.available	2010-12-17T10:48:54Z
dc.date.issued	2009
dc.identifier.uri	https://basepub.dauphine.fr/handle/123456789/5339
dc.language.iso	en	en
dc.subject	preferences
dc.subject	graphical representation
dc.subject	Complexity
dc.subject.ddc	006.3	en
dc.title	Learning various classes of models of lexicographic orderings
dc.type	Communication / Conférence
dc.description.abstracten	We consider the problem of learning a user’s ordinal preferences onmultiattribute domains, assuming that the user’s preferences may be modelled asa kind of lexicographic ordering. We introduce a general graphical representationcalled LP-structures which captures various natural classes of such ordering inwhich both the order of importance between attributes and the local preferencesover each attributemay or may not be conditional on the values of other attributes.For each class we determine the Vapnik-Chernovenkis dimension, the communication complexity of learning preferences, and the complexity of identifying amodel in the class consistent with some given user-provided examples.
dc.description.sponsorshipprivate	oui	en
dc.subject.ddclabel	Intelligence artificielle	en
dc.relation.conftitle	Preference Learning (PL-09) ECML/PKDD-09 Workshop
dc.relation.confcity	Bled
dc.relation.confcountry	SLOVENIA
dc.description.ssrncandidate	non
dc.description.halcandidate	oui
dc.description.readership	recherche
dc.description.audience	International
dc.date.updated	2017-09-29T16:51:37Z