Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand

• URL: http://arxiv.org/abs/2606.10472v1
• Date: Tue, 09 Jun 2026 06:41:04 GMT
• Title: Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand
• Abstract summary: We propose a neural allocation mechanism that reconciles fairness with utility.<n>We first formalize fairness in the dynamic setting via stepwise loss functions.<n>We parameterized the solutions by constraining allocations to the subspace of demand.
• Score: 8.838518847441728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must be distributed fairly without knowledge of future demands. Existing methods emphasize fairness guarantees such as Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, but often overlook system utility. Moreover, these fairness criteria are mutually incompatible, preventing strict enforcement of them at the same time. We propose a neural allocation mechanism that reconciles fairness with utility through multi-objective optimization during sequential rollout. We first formalize fairness in the dynamic setting via stepwise loss functions for Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, enabling differentiable training. Leveraging non-wastefulness, we parameterized the solutions by constraining allocations to the subspace of demand while allowing elastic over-allocation when resources remain available. Empirical results demonstrate that our learned allocator achieves substantially higher utility at comparable levels of fairness, uncovering clear Pareto-frontier-like tradeoffs across metrics.

Related papers

• Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss [91.61796429377041]
  The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks.<n>We investigate whether different surrogates achieve consistency with classification and ranking metrics, and analyze their gradient dynamics to reveal distinct convergence behaviors.<n>Our results establish a principled foundation and offer practical guidance for loss selections in large-class machine learning applications.
  arXiv  Detail & Related papers  (2026-01-30T09:24:52Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• A General Incentives-Based Framework for Fairness in Multi-agent Resource Allocation [4.930376365020355]
  We introduce the General Incentives-based Framework for Fairness (GIFF)<n>GIFF is a novel approach for fair multi-agent resource allocation that infers fair decision-making from standard value functions.
  arXiv  Detail & Related papers  (2025-10-30T17:37:51Z)
• MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs [2.0019258650495493]
  mmm-fair is an open-source tool for exploring multi-dimensional fairness and related trade-offs.<n>It combines in-depth multi-attribute fairness, multi-objective optimization, a no-code, chat-based interface, LLM-powered explanations, and deployment-ready models.
  arXiv  Detail & Related papers  (2025-09-09T21:30:45Z)
• DECAF: Learning to be Fair in Multi-agent Resource Allocation [4.788163807490197]
  We propose methods to learn fair and efficient policies in centralized resource allocation.<n>Our methods are applied to learning long-term fairness in a novel and general framework for fairness in multi-agent systems.
  arXiv  Detail & Related papers  (2025-02-06T18:29:11Z)
• Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning [30.605881670761853]
  We propose a Reinforcement Learning approach to achieve fairness in finite-horizon episodic MDPs. We show that such an approach achieves sub-linear regret in terms of the number of episodes.
  arXiv  Detail & Related papers  (2023-06-01T03:43:53Z)
• Online Learning with Knapsacks: the Best of Both Worlds [54.28273783164608]
  We casting online learning problems in which a decision maker wants to maximize their expected reward without violating a finite set of $m$m resource constraints. Our framework allows the decision maker to handle its evidence flexibility and costoretic functions.
  arXiv  Detail & Related papers  (2022-02-28T12:10:48Z)
• Online Learning Demands in Max-min Fairness [91.37280766977923]
  We describe mechanisms for the allocation of a scarce resource among multiple users in a way that is efficient, fair, and strategy-proof. The mechanism is repeated for multiple rounds and a user's requirements can change on each round. At the end of each round, users provide feedback about the allocation they received, enabling the mechanism to learn user preferences over time.
  arXiv  Detail & Related papers  (2020-12-15T22:15:20Z)
• Coordinated Online Learning for Multi-Agent Systems with Coupled Constraints and Perturbed Utility Observations [91.02019381927236]
  We introduce a novel method to steer the agents toward a stable population state, fulfilling the given resource constraints. The proposed method is a decentralized resource pricing method based on the resource loads resulting from the augmentation of the game's Lagrangian.
  arXiv  Detail & Related papers  (2020-10-21T10:11:17Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)
• Regularized Online Allocation Problems: Fairness and Beyond [7.433931244705934]
  We introduce the emphregularized online allocation problem, a variant that includes a non-linear regularizer acting on the total resource consumption. In this problem, requests repeatedly arrive over time and, for each request, a decision maker needs to take an action that generates a reward and consumes resources. The objective is to simultaneously maximize additively separable rewards and the value of a non-separable regularizer subject to the resource constraints.
  arXiv  Detail & Related papers  (2020-07-01T14:24:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.