Year: 2026
Type: preprint
Abstract: We give a randomized voting rule with expected metric distortion $5/2$, improving the previous best upper bound of $2.753$. Our rule is the equal mixture of a Maximal Lottery [CRWW24] and a lottery obtained by averaging scores in Simultaneous Plurality Veto [KK23] over time. We further show that $5/2$ is optimal within a broader family that allows profile-dependent mixing weights and arbitrary, possibly adaptive, weights over the veto process.
Source: arXiv (Cornell University)
Author: Ye, Qilin
Institution: Stanford University
Language: English
Subfield: Economics and Econometrics
Domain: Social Sciences
Keywords: metric distortion, social choice
Open Access status: green
OpenAlex ID: W7204146916
