Outer Diversity of Structured Domains
Piotr Faliszewski, Krzysztof Sornat, Stanisław Szufa, Tomasz Wąs
TL;DR
This paper introduces outer diversity for ordinal preference domains and analyzes it across key structured domains (single-peaked, single-crossing, group-separable, and Euclidean). It develops sampling-based algorithms to compute outer diversity, characterizes computational aspects for each domain, and provides extensive empirical comparisons. The results identify ${\mathrm{GS/cat}}$ as the most diverse among studied domains and show that outer diversity aligns with intuitions from inner diversity, offering a robust benchmark for evaluating domain richness in elections. The work offers practical guidance for simulation studies and opens avenues to formally relate outer and inner diversity while suggesting further exploration of hard instances and domain design.
Abstract
An ordinal preference domain is a subset of preference orders that the voters are allowed to cast in an election. We introduce and study the notion of outer diversity of a domain and evaluate its value for a number of well-known structured domains, such as the single-peaked, single-crossing, group-separable, and Euclidean ones.
