Computational Complexity of Testing Proportional Justified Representation
This resolves a key open problem in computational social choice, with implications for designing fair voting systems, though it is incremental as it builds on prior work.
The paper tackled the open problem of determining the computational complexity of testing proportional justified representation in committee voting, proving it is coNP-complete, and showed efficient algorithms exist when certain parameters are bounded.
We consider a committee voting setting in which each voter approves of a subset of candidates and based on the approvals, a target number of candidates are selected. Aziz et al. (2015) proposed two representation axioms called justified representation and extended justified representation. Whereas the former can be tested as well as achieved in polynomial time, the latter property is coNP-complete to test and no polynomial-time algorithm is known to achieve it. Interestingly, S{á}nchez-Fern{á}ndez et~al. (2016) proposed an intermediate property called proportional justified representation that admits a polynomial-time algorithm to achieve. The complexity of testing proportional justified representation has remained an open problem. In this paper, we settle the complexity by proving that testing proportional justified representation is coNP-complete. We complement the complexity result by showing that the problem admits efficient algorithms if any of the following parameters are bounded: (1) number of voters (2) number of candidates (3) maximum number of candidates approved by a voter (4) maximum number of voters approving a given candidate.