Minimax regret based elicitation of generalized additive utilities

We describe the semantic foundations for elicitation of generalized additively independent (GAI) utilities using the minimax regret criterion, and propose several new query types and strategies for this purpose. Computational feasibility is obtained by exploiting the local GAI structure in the model...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2012-06
Main Authors: Braziunas, Darius, Boutilier, Craig
Format: Article
Language:English
Subjects:
Minimax technique
Optimization
Utilities
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe the semantic foundations for elicitation of generalized additively independent (GAI) utilities using the minimax regret criterion, and propose several new query types and strategies for this purpose. Computational feasibility is obtained by exploiting the local GAI structure in the model. Our results provide a practical approach for implementing preference-based constrained configuration optimization as well as effective search in multiattribute product databases.
ISSN:2331-8422