Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making

• URL: http://arxiv.org/abs/2109.08792v4
• Date: Mon, 12 Feb 2024 20:17:04 GMT
• Title: Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making
• Authors: Alex Chohlas-Wood, Madison Coots, Henry Zhu, Emma Brunskill, Sharad Goel
• Abstract summary: We present an alternative framework for designing equitable algorithms. In our approach, one first elicits stakeholder preferences over the space of possible decisions. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility.
• Score: 21.152377319502705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program that provides transportation assistance to low-income people with upcoming court dates. Following this literature, one might allocate rides to those with the highest estimated treatment effect per dollar, while constraining spending to be equal across race groups. That approach, however, ignores the downstream consequences of such constraints, and, as a result, can induce unexpected harms. For instance, if one demographic group lives farther from court, enforcing equal spending would necessarily mean fewer total rides provided, and potentially more people penalized for missing court. Here we present an alternative framework for designing equitable algorithms that foregrounds the consequences of decisions. In our approach, one first elicits stakeholder preferences over the space of possible decisions and the resulting outcomes--such as preferences for balancing spending parity against court appearance rates. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility. To do so, we develop an algorithm for efficiently learning these optimal policies from data for a large family of expressive utility functions. In particular, we use a contextual bandit algorithm to explore the space of policies while solving a convex optimization problem at each step to estimate the best policy based on the available information. This consequentialist paradigm facilitates a more holistic approach to equitable decision-making.

Related papers

• Reduced-Rank Multi-objective Policy Learning and Optimization [57.978477569678844]
  In practice, causal researchers do not have a single outcome in mind a priori. In government-assisted social benefit programs, policymakers collect many outcomes to understand the multidimensional nature of poverty. We present a data-driven dimensionality-reduction methodology for multiple outcomes in the context of optimal policy learning.
  arXiv  Detail & Related papers  (2024-04-29T08:16:30Z)
• 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)
• Designing Equitable Algorithms [1.9006392177894293]
  Predictive algorithms are now used to help distribute a large share of our society's resources and sanctions. These algorithms can improve the efficiency and equity of decision-making. But they could entrench and exacerbate disparities, particularly along racial, ethnic, and gender lines.
  arXiv  Detail & Related papers  (2023-02-17T22:00:44Z)
• Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency [0.0]
  This paper focuses on the fairness concepts of PPV parity, false omission rate (FOR) parity, and sufficiency. We show that group-specific threshold rules are optimal for PPV parity and FOR parity. We also provide a solution for the optimal decision rules satisfying the fairness constraint sufficiency.
  arXiv  Detail & Related papers  (2022-06-05T18:47:34Z)
• Efficient Algorithms for Planning with Participation Constraints [74.74967476995572]
  We consider the problem of planning with participation constraints introduced in [Zhang et al., 2022] In this problem, a principal chooses actions in a decision process, resulting in separate utilities for the principal and the agent. We provide the first-time exact algorithm for this problem for finite-horizon settings, where previously only an additive $varepsilon$-approximation was known.
  arXiv  Detail & Related papers  (2022-05-16T15:47:41Z)
• Fair Algorithm Design: Fair and Efficacious Machine Scheduling [0.0]
  There is often a dichotomy between fairness and efficacy: fair algorithms may proffer low social welfare solutions whereas welfare optimizing algorithms may be very unfair. In this paper, we prove that this dichotomy can be overcome if we allow for a negligible amount of bias.
  arXiv  Detail & Related papers  (2022-04-13T14:56:22Z)
• Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability [59.81339109121384]
  We study the $K$ contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes emphpreference-based feedback suggesting that one decision was better than the other. We provide a new algorithm that achieves the optimal regret rate for a new notion of best response regret, which is a strictly stronger performance measure than those considered in prior works.
  arXiv  Detail & Related papers  (2021-11-24T07:14:57Z)
• Understanding the Effect of Stochasticity in Policy Optimization [86.7574122154668]
  We show that the preferability of optimization methods depends critically on whether exact gradients are used. Second, to explain these findings we introduce the concept of committal rate for policy optimization. Third, we show that in the absence of external oracle information, there is an inherent trade-off between exploiting geometry to accelerate convergence versus achieving optimality almost surely.
  arXiv  Detail & Related papers  (2021-10-29T06:35:44Z)
• Algorithmic Challenges in Ensuring Fairness at the Time of Decision [6.228560624452748]
  Algorithmic decision-making in societal contexts can be framed as optimization under bandit feedback. Recent lawsuits accuse companies that deploy algorithmic pricing practices of price gouging. We introduce the well-studied fairness notion of envy-freeness within the context of convex optimization.
  arXiv  Detail & Related papers  (2021-03-16T19:06:28Z)
• Fair Policy Targeting [0.6091702876917281]
  One of the major concerns of targeting interventions on individuals in social welfare programs is discrimination. This paper addresses the question of the design of fair and efficient treatment allocation rules.
  arXiv  Detail & Related papers  (2020-05-25T20:45:25Z)
• Public Bayesian Persuasion: Being Almost Optimal and Almost Persuasive [57.47546090379434]
  We study the public persuasion problem in the general setting with: (i) arbitrary state spaces; (ii) arbitrary action spaces; (iii) arbitrary sender's utility functions. We provide a quasi-polynomial time bi-criteria approximation algorithm for arbitrary public persuasion problems that, in specific settings, yields a QPTAS.
  arXiv  Detail & Related papers  (2020-02-12T18:59:18Z)

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.