arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.08598cs.GT
收藏

认知层级与投票操纵

Cognitive Hierarchy and Voting Manipulation

Edith Elkind, Umberto Grandi, Francesca Rossi, Arkadii Slinko

摘要:

根据Gibbard-Satterthwaite定理,每一个合理的三个或更多选择的投票规则都容易被操纵:存在这样的选举,一个或多个选民可以通过单方面修改他们的投票来改变选举结果。当一次选举中有几个这样的选民时,策略性投票就变成了潜在操纵者之间的游戏:当其他选民诚实时,操纵性投票会带来更好的结果,当其他选民也选择操纵时,可能会导致灾难性的结果。我们从有限理性选民的角度考虑这种情况,并使用认知层次框架来确定好的策略。然后,我们调查相关的算法问题下的k-批准投票规则。我们得到了积极的算法结果为k=1和2,NP-和coNP-硬度结果为k>3。

英文摘要:

By the Gibbard--Satterthwaite theorem, every reasonable voting rule for three or more alternatives is susceptible to manipulation: there exist elections where one or more voters can change the election outcome in their favour by unilaterally modifying their vote. When a given election admits several such voters, strategic voting becomes a game among potential manipulators: a manipulative vote that leads to a better outcome when other voters are truthful may lead to disastrous results when other voters choose to manipulate as well. We consider this situation from the perspective of a boundedly rational voter, and use the cognitive hierarchy framework to identify good strategies. We then investigate the associated algorithmic questions under the k-approval voting rule. We obtain positive algorithmic results for k=1 and 2, and NP- and coNP-hardness results for k>3.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑