Fairness in Limited Resources Settings

• URL: http://arxiv.org/abs/2602.23026v1
• Date: Thu, 26 Feb 2026 14:07:05 GMT
• Title: Fairness in Limited Resources Settings
• Authors: Eitan Bachmat, Inbal Livni Navon,
• Abstract summary: In recent years many important societal decisions are made by machine-learning algorithms.<n>We consider both the prediction aspect of the decision and the resource allocation aspect.<n>In this work we focus on the fairness of the decisions in such settings.
• Score: 0.48127184936824546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years many important societal decisions are made by machine-learning algorithms, and many such important decisions have strict capacity limits, allowing resources to be allocated only to the highest utility individuals. For example, allocating physician appointments to the patients most likely to have some medical condition, or choosing which children will attend a special program. When performing such decisions, we consider both the prediction aspect of the decision and the resource allocation aspect. In this work we focus on the fairness of the decisions in such settings. The fairness aspect here is critical as the resources are limited, and allocating the resources to one individual leaves less resources for others. When the decision involves prediction together with the resource allocation, there is a risk that information gaps between different populations will lead to a very unbalanced allocation of resources. We address settings by adapting definitions from resource allocation schemes, identifying connections between the algorithmic fairness definitions and resource allocation ones, and examining the trade-offs between fairness and utility. We analyze the price of enforcing the different fairness definitions compared to a strictly utility-based optimization of the predictor, and show that it can be unbounded. We introduce an adaptation of proportional fairness and show that it has a bounded price of fairness, indicating greater robustness, and propose a variant of equal opportunity that also has a bounded price of fairness.

Related papers

• No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need! [56.80767500991973]
  We focus on two canonical settings: $(i)$ online resource allocation where rewards and costs are observed before action selection, and $(ii)$ online learning with resource constraints where they are observed after action selection, under full feedback or bandit feedback.<n>It is well known that achieving sublinear regret in these settings is impossible when reward and cost distributions may change arbitrarily over time.<n>We design general (primal-)dual methods that achieve sublinear regret with respect to baselines that follow the spending plan. Crucially, the performance of our algorithms improves when the spending plan ensures a well-balanced distribution of the budget
  arXiv  Detail & Related papers  (2025-06-16T08:42:31Z)
• Decision-centric fairness: Evaluation and optimization for resource allocation problems [1.5623752145311105]
  We propose a decision-centric fairness methodology that induces fairness only within the decision-making region.<n>We empirically compare our approach to a global fairness approach on multiple (semi-synthetic) datasets.
  arXiv  Detail & Related papers  (2025-04-29T11:12:36Z)
• Resource-constrained Fairness [6.5549655910531195]
  Our research introduces the concept of "resource-constrained fairness" and quantifies the cost of fairness within this framework.<n>We demonstrate that the level of available resources significantly influences this cost, a factor overlooked in previous evaluations.
  arXiv  Detail & Related papers  (2024-06-03T13:01:09Z)
• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time.<n>We show that enforcing a causal constraint often reduces the disparity between demographic groups.<n>We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Deep Reinforcement Learning for Efficient and Fair Allocation of Health Care Resources [47.57108369791273]
  Scarcity of health care resources could result in the unavoidable consequence of rationing. There is no universally accepted standard for health care resource allocation protocols. We propose a transformer-based deep Q-network to integrate the disease progression of individual patients and the interaction effects among patients.
  arXiv  Detail & Related papers  (2023-09-15T17:28:06Z)
• Causal Fairness for Outcome Control [68.12191782657437]
  We study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this.
  arXiv  Detail & Related papers  (2023-06-08T09:31:18Z)
• Resource Allocation to Agents with Restrictions: Maximizing Likelihood with Minimum Compromise [28.2469613376685]
  We show that a Principle chooses a maximum matching randomly so that each agent is matched to a resource with some probability. Agents would like to improve their chances of being matched by modifying their restrictions within certain limits. We experimentally evaluate our methods on synthetic datasets as well as on two novel real-world datasets.
  arXiv  Detail & Related papers  (2022-09-12T11:58:19Z)
• On Fair Selection in the Presence of Implicit and Differential Variance [22.897402186120434]
  We study a model where the decision maker receives a noisy estimate of each candidate's quality, whose variance depends on the candidate's group. We show that both baseline decision makers yield discrimination, although in opposite directions.
  arXiv  Detail & Related papers  (2021-12-10T16:04:13Z)
• Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There? [0.0]
  We show that metrics implementing equality of opportunity only apply when resource allocations are based on deservingness, but fail when allocations should reflect concerns about egalitarianism, sufficiency, and priority. We argue that by cleanly distinguishing between prediction tasks and decision tasks, research on fair machine learning could take better advantage of the rich literature on distributive justice.
  arXiv  Detail & Related papers  (2021-05-04T12:09:26Z)
• Fairness, Welfare, and Equity in Personalized Pricing [88.9134799076718]
  We study the interplay of fairness, welfare, and equity considerations in personalized pricing based on customer features. We show the potential benefits of personalized pricing in two settings: pricing subsidies for an elective vaccine, and the effects of personalized interest rates on downstream outcomes in microcredit.
  arXiv  Detail & Related papers  (2020-12-21T01:01:56Z)
• Learning Strategies in Decentralized Matching Markets under Uncertain Preferences [91.3755431537592]
  We study the problem of decision-making in the setting of a scarcity of shared resources when the preferences of agents are unknown a priori. Our approach is based on the representation of preferences in a reproducing kernel Hilbert space. We derive optimal strategies that maximize agents' expected payoffs.
  arXiv  Detail & Related papers  (2020-10-29T03:08:22Z)
• 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)

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.