mlsanityData to 14 Oct 2026

Achievement and Fragility of Long-term Equitability

arXiv 2206.12333 ↗First posted 24 Jun 2022math.OC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Equipping current decision-making tools with notions of fairness, equitability, or other ethically motivated outcomes, is one of the top priorities in recent research efforts in machine learning, AI, and optimization. In this paper, we investigate how to allocate limited resources to {locally interacting} communities in a way to maximize a pertinent notion of equitability. In particular, we look at the dynamic setting where the allocation is repeated across multiple periods (e.g., yearly), the local communities evolve in the meantime (driven by the provided allocation), and the allocations are modulated by feedback coming from the communities themselves. We employ recent mathematical tools stemming from data-driven feedback online optimization, by which communities can learn their (possibly unknown) evolution, satisfaction, as well as they can share information with the deciding bodies. We design dynamic policies that converge to an allocation that maximize equitability in the long term. We further demonstrate our model and methodology with realistic examples of healthcare and education subsidies design in Sub-Saharian countries. One of the key empirical takeaways from our setting is that long-term equitability is fragile, in the sense that it can be easily lost when deciding bodies weigh in other factors (e.g., equality in allocation) in the allocation strategy. Moreover, a naive compromise, while not providing significant advantage to the communities, can promote inequality in social outcomes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 46 references that are in the map. First posted on arXiv 24 Jun 2022.

Builds on

20 of 46 references.

References · 20

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2019Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combinationcited by 79
  3. 2021Towards Long-term Fairness in Recommendationcited by 77
  4. 2020Controlling Fairness and Bias in Dynamic Learning-to-Rankcited by 68
  5. 2019Algorithms for Fairness in Sequential Decision Makingcited by 56
  6. 2018A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunitycited by 53
  7. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 49
  8. 2019Causal Modeling for Fairness in Dynamical Systemscited by 47
  9. 2018Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Makingcited by 46
  10. 2018Data-Enabled Predictive Control: In the Shallows of the DeePCcited by 38
  11. 2018From Fair Decision Making to Social Equalitycited by 36
  12. 2021Towards Return Parity in Markov Decision Processescited by 13
8 more
  1. 2021Allocating Opportunities in a Dynamic Model of Intergenerational Mobilitycited by 12
  2. 2019A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairnesscited by 11
  3. 2021Recommendation Fairness: From Static to Dynamiccited by 10
  4. 2019Protecting the Protected Group: Circumventing Harmful Fairnesscited by 9
  5. 2020Distributed Personalized Gradient Tracking with Convex Parametric Modelscited by 7
  6. 2019Personalized Optimization with User's Feedbackcited by 5
  7. 2021Online Stochastic Optimization for Unknown Linear Systems: Data-Driven Synthesis and Controller Analysiscited by 3
  8. 2021Data-Driven Synthesis of Optimization-Based Controllers for Regulation of Unknown Linear Systemscited by 1

Built on by

Not cited yet.