aiqbench analysis
This research advances stochastic deadline scheduling by integrating fairness constraints into the Whittle index policy for restless multi-armed bandits. By employing a virtual queue mechanism, the proposed outcome-fair model ensures long-term completion rate guarantees for structurally disadvantaged demographic groups while analyzing the inherent trade-off between equity and profit. The study provides critical insights for deploying AI-driven resource allocation systems that balance efficiency with ethical considerations in real-world scheduling applications.
Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling
arXiv:2607.23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle index policy. The goal in RMAB is to maximize the expected cumulative discounted reward maximization. The Whittle index policy maximizes reward, but is not fair among two classes. In this paper, we introduce fairness criteria and study an outcome-fair model for RMAB which allows fairness for jobs and users structurally disadvantaged demographic classes. We formulate an outcome fair stochastic deadline scheduling problem as RMAB, and we develop the outcome fair Whittle index policy. We define a virtual queue mechanism that dynamically enforces long-term completion rate guaranties across demographic groups. We analyze a standard Whittle index policy and the outcome-fair index policy. We demonstrate the performance of our algorithms with numerical examples. We compare policies---Whittle index policy (no fairness), input-fairness Whittle index policy, outcome fair Whittle index policy. We observe that the outcome-fair Whittle index policy provides better fairness among classes compared to other policies. We demonstrate a trade off between fairness and profit. This decreases as the server capacity increases.
Abstract:We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle index policy. The goal in RMAB is to maximize the expected cumulative discounted reward maximization. The Whittle index policy maximizes reward, but is not fair among two classes. In this paper, we introduce fairness criteria and study an outcome-fair model for RMAB which allows fairness for jobs and users structurally disadvantaged demographic classes. We formulate an outcome fair stochastic deadline scheduling problem as RMAB, and we develop the outcome fair Whittle index policy. We define a virtual queue mechanism that dynamically enforces long-term completion rate guaranties across demographic groups. We analyze a standard Whittle index policy and the outcome-fair index policy. We demonstrate the performance of our algorithms with numerical examples. We compare policies---Whittle index policy (no fairness), input-fairness Whittle index policy, outcome fair Whittle index policy. We observe that the outcome-fair Whittle index policy provides better fairness among classes compared to other policies. We demonstrate a trade off between fairness and profit. This decreases as the server capacity increases.
Systems and Control (eess.SY); Artificial Intelligence (cs.AI)
arXiv:2607.23772 [eess.SY]
(or arXiv:2607.23772v1 [eess.SY] for this version)
https://doi.org/10.48550/arXiv.2607.23772 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 279 words
Related coverage
Procedural Fairness in Multi-Agent Bandits
arXiv · Jul 31, 2026
Regret Analysis of Retry-Based Bandits
arXiv · Oct 1, 2026
Restless Bandits with Individual Penalty Constraints: Near-Optimal Indices and Deep Reinforcement Learning
arXiv · Sep 30, 2026
Bayesian Learning to Select Fair Classifiers
arXiv · Oct 15, 2026