Impartial Selection with Predictions

2025-10-21

AI Summary

This paper studies the impartial agent selection problem based on mutual nominations, aiming to design an unbiased selection mechanism that achieves both consistency—i.e., near-optimal performance when predictions about high-nomination sets are accurate—and robustness—i.e., guaranteed performance even under prediction errors. It introduces, for the first time, prediction-augmented design into impartial mechanism design, proposing a general framework grounded in combinatorial optimization and probabilistic analysis. Theoretically, for the $k$-selection setting, the mechanism attains $1 - O(1/k)$ consistency and $1 - 1/e - O(1/k)$ robustness; for the single-nomination setting, it achieves exact $1$-consistency and $1/2$-robustness—both matching respective information-theoretic upper bounds asymptotically. These results significantly advance the approximation guarantees and reliability of prediction-enhanced mechanisms in applications such as committee elections and AI alignment.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We study the selection of agents based on mutual nominations, a theoretical problem with many applications from committee selection to AI alignment. As agents both select and are selected, they may be incentivized to misrepresent their true opinion about the eligibility of others to influence their own chances of selection. Impartial mechanisms circumvent this issue by guaranteeing that the selection of an agent is independent of the nominations cast by that agent. Previous research has established strong bounds on the performance of impartial mechanisms, measured by their ability to approximate the number of nominations for the most highly nominated agents. We study to what extent the performance of impartial mechanisms can be improved if they are given a prediction of a set of agents receiving a maximum number of nominations. Specifically, we provide bounds on the consistency and robustness of such mechanisms, where consistency measures the performance of the mechanisms when the prediction is accurate and robustness its performance when the prediction is inaccurate. For the general setting where up to $k$ agents are to be selected and agents nominate any number of other agents, we give a mechanism with consistency $1-Oig(frac{1}{k}ig)$ and robustness $1-frac{1}{e}-Oig(frac{1}{k}ig)$. For the special case of selecting a single agent based on a single nomination per agent, we prove that $1$-consistency can be achieved while guaranteeing $frac{1}{2}$-robustness. A close comparison with previous results shows that (asymptotically) optimal consistency can be achieved with little to no sacrifice in terms of robustness.

Problem

• Improving impartial selection mechanisms using nomination predictions
• Establishing bounds for consistency and robustness in agent selection
• Achieving optimal consistency with minimal robustness trade-offs

Innovation

• Impartial mechanisms with nomination predictions
• Consistency bounds for accurate predictions
• Robustness guarantees under prediction inaccuracy