Restricted Manipulation in Iterative Voting: Convergence and Condorcet Efficiency

TL;DR

This paper investigates iterative voting with restricted manipulation, proving convergence and demonstrating that such methods often improve Condorcet efficiency compared to non-iterative rules.

Contribution

It introduces a framework for restricted manipulation in iterative voting, proving convergence and showing improved Condorcet efficiency through experiments.

Findings

Iterative voting rules converge under restricted manipulation.

Most iterative voting rules have higher Condorcet efficiency.

Restricted manipulation is computationally easy and requires little information.

Abstract

In collective decision making, where a voting rule is used to take a collective decision among a group of agents, manipulation by one or more agents is usually considered negative behavior to be avoided, or at least to be made computationally difficult for the agents to perform. However, there are scenarios in which a restricted form of manipulation can instead be beneficial. In this paper we consider the iterative version of several voting rules, where at each step one agent is allowed to manipulate by modifying his ballot according to a set of restricted manipulation moves which are computationally easy and require little information to be performed. We prove convergence of iterative voting rules when restricted manipulation is allowed, and we present experiments showing that most iterative voting rules have a higher Condorcet efficiency than their non-iterative version.