Show simple item record

dc.contributor.authorDimopoulos, Yannisen
dc.contributor.authorMichael, Loizosen
dc.contributor.authorAthienitou, F.en
dc.creatorDimopoulos, Yannisen
dc.creatorMichael, Loizosen
dc.creatorAthienitou, F.en
dc.description.abstractCP-networks have been proposed as a simple and intuitive graphical tool for representing conditional ceteris paribus preference statements over the values of a set of variables. While the problem of reasoning with CP-networks has been receiving some attention, there are very few works that address the problem of learning CP-networks. In this work we investigate the task of learning CP-networks, given access to a set of pairwise comparisons. We first prove that the learning problem is intractable, even under several simplifying assumptions. We then present an algorithm that, under certain assumptions about the observed pair-wise comparisons, identifies a CP-network that entails these comparisons. We finally show that the proposed algorithm is a PAC-learner, and, thus, that the CP-networks it induces accurately predict the user's preferences on previously unseen situations.en
dc.sourceIJCAI International Joint Conference on Artificial Intelligenceen
dc.source21st International Joint Conference on Artificial Intelligence, IJCAI-09en
dc.subjectArtificial intelligenceen
dc.subjectSimplifying assumptionsen
dc.subjectPreference elicitationen
dc.subjectPreference statementsen
dc.subjectGraphical toolsen
dc.subjectLearning problemen
dc.subjectPair-wise comparisonen
dc.titleCeteris paribus preference elicitation with predictive guaranteesen
dc.description.endingpage1895 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied SciencesΤμήμα Πληροφορικής / Department of Computer Science
dc.type.uhtypeConference Objecten
dc.description.notes<p>Sponsors: Int. Jt. Conf. Artif. Intell. (IJCAI)en
dc.description.notesAssociation for the Advancement of Artificial Intelligence (AAAI)en
dc.description.notesUSC Institute for Creative Technologiesen
dc.description.notesNational Science Foundationen
dc.description.notesMicrosoft Researchen
dc.description.notesConference code: 83585en
dc.description.notesCited By :22</p>en
dc.contributor.orcidDimopoulos, Yannis [0000-0001-9583-9754]

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record