Preference Learning Along Multiple Criteria: A Game-Theoretic Perspective
Abstract
The literature on ranking from ordinal data is vast, and there are several ways to aggregate overall preferences from pairwise comparisons between objects. In particular, it is well-known that any Nash equilibrium of the zero-sum game induced by the preference matrix defines a natural solution concept (winning distribution over objects) known as a von Neumann winner. Many real-world problems, however, are inevitably multi-criteria, with different pairwise preferences governing the different criteria. In this work, we generalize the notion of a von Neumann winner to the multi-criteria setting by taking inspiration from Blackwell’s approachability. Our framework allows for non-linear aggregation of preferences across criteria, and generalizes the linearization-based approach from multi-objective optimization.
Cite
Text
Bhatia et al. "Preference Learning Along Multiple Criteria: A Game-Theoretic Perspective." Neural Information Processing Systems, 2020.Markdown
[Bhatia et al. "Preference Learning Along Multiple Criteria: A Game-Theoretic Perspective." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/bhatia2020neurips-preference/)BibTeX
@inproceedings{bhatia2020neurips-preference,
title = {{Preference Learning Along Multiple Criteria: A Game-Theoretic Perspective}},
author = {Bhatia, Kush and Pananjady, Ashwin and Bartlett, Peter L. and Dragan, Anca and Wainwright, Martin J.},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/bhatia2020neurips-preference/}
}