Possible Winners in Noisy Elections
Abstract
We consider the problem of predicting winners in elections, for the case where we are given complete knowledge about all possible candidates, all possible voters (together with their preferences), but where it is uncertain either which candidates exactly register for the election or which voters cast their votes. Under reasonable assumptions, our problems reduce to counting variants of election control problems. We either give polynomialtime algorithms or prove #Pcompleteness results for counting variants of control by adding/deleting candidates/voters for Plurality, kApproval, Approval, Condorcet, and Maximin voting rules. We consider both the general case, where voters' preferences are unrestricted, and the case where voters' preferences are singlepeaked.
 Publication:

arXiv eprints
 Pub Date:
 May 2014
 arXiv:
 arXiv:1405.6630
 Bibcode:
 2014arXiv1405.6630W
 Keywords:

 Computer Science  Computer Science and Game Theory;
 Computer Science  Computational Complexity;
 Computer Science  Multiagent Systems;
 I.2.11;
 F.2.2
 EPrint:
 34 pages