Thumbnail

Learning conditionally lexicographic preference relations

Booth, Richard; Chevaleyre, Yann; Lang, Jérôme; Mengin, Jérôme; Sombattheera, Chattrakul (2010), Learning conditionally lexicographic preference relations, in Wooldridge, Michael, ECAI 2010 19th European Conference on Artificial Intelligence 16–20 August 2010, Lisbon, Portugal - proceedings, IOS Press : Tokyo, p. 269-274

View/Open
Type
Communication / Conférence
Date
2010
Conference country
PORTUGAL
Book title
ECAI 2010 19th European Conference on Artificial Intelligence 16–20 August 2010, Lisbon, Portugal - proceedings
Book author
Wooldridge, Michael
Publisher
IOS Press
Published in
Tokyo
ISBN
978-1-60750-605-8
Pages
269-274
Metadata
Show full item record
Author(s)
Booth, Richard
Chevaleyre, Yann
Lang, Jérôme
Mengin, Jérôme
Sombattheera, Chattrakul
Abstract (EN)
We 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.
Subjects / Keywords
LP-trees