Algorithmic Fairness from a Non-ideal Perspective

• URL: http://arxiv.org/abs/2001.09773v1
• Date: Wed, 8 Jan 2020 18:44:41 GMT
• Title: Algorithmic Fairness from a Non-ideal Perspective
• Authors: Sina Fazelpour, Zachary C. Lipton
• Abstract summary: We argue that the increasingly apparent shortcomings of proposed fair machine learning algorithms reflect broader troubles faced by the ideal approach. We conclude with a critical discussion of the harms of misguided solutions, a reinterpretation of impossibility results, and directions for future research.
• Score: 26.13086713244309
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inspired by recent breakthroughs in predictive modeling, practitioners in both industry and government have turned to machine learning with hopes of operationalizing predictions to drive automated decisions. Unfortunately, many social desiderata concerning consequential decisions, such as justice or fairness, have no natural formulation within a purely predictive framework. In efforts to mitigate these problems, researchers have proposed a variety of metrics for quantifying deviations from various statistical parities that we might expect to observe in a fair world and offered a variety of algorithms in attempts to satisfy subsets of these parities or to trade off the degree to which they are satisfied against utility. In this paper, we connect this approach to \emph{fair machine learning} to the literature on ideal and non-ideal methodological approaches in political philosophy. The ideal approach requires positing the principles according to which a just world would operate. In the most straightforward application of ideal theory, one supports a proposed policy by arguing that it closes a discrepancy between the real and the perfectly just world. However, by failing to account for the mechanisms by which our non-ideal world arose, the responsibilities of various decision-makers, and the impacts of proposed policies, naive applications of ideal thinking can lead to misguided interventions. In this paper, we demonstrate a connection between the fair machine learning literature and the ideal approach in political philosophy, and argue that the increasingly apparent shortcomings of proposed fair machine learning algorithms reflect broader troubles faced by the ideal approach. We conclude with a critical discussion of the harms of misguided solutions, a reinterpretation of impossibility results, and directions for future research.

Related papers

• Algorithmic Fairness: A Tolerance Perspective [31.882207568746168]
  This survey delves into the existing literature on algorithmic fairness, specifically highlighting its multifaceted social consequences. We introduce a novel taxonomy based on 'tolerance', a term we define as the degree to which variations in fairness outcomes are acceptable. Our systematic review covers diverse industries, revealing critical insights into the balance between algorithmic decision making and social equity.
  arXiv  Detail & Related papers  (2024-04-26T08:16:54Z)
• The Fairness Fair: Bringing Human Perception into Collective Decision-Making [16.300744216179545]
  We argue that not only fair solutions should be deemed desirable by social planners (designers), but they should be governed by human and societal cognition. We discuss how achieving this goal requires a broad transdisciplinary approach ranging from computing and AI to behavioral economics and human-AI interaction.
  arXiv  Detail & Related papers  (2023-12-22T03:06:24Z)
• Reconciling Predictive and Statistical Parity: A Causal Approach [68.59381759875734]
  We propose a new causal decomposition formula for the fairness measures associated with predictive parity. We show that the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions.
  arXiv  Detail & Related papers  (2023-06-08T09:23:22Z)
• Fair Off-Policy Learning from Observational Data [30.77874108094485]
  We propose a novel framework for fair off-policy learning. We first formalize different fairness notions for off-policy learning. We then propose a neural network-based framework to learn optimal policies under different fairness notions.
  arXiv  Detail & Related papers  (2023-03-15T10:47:48Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Impact Remediation: Optimal Interventions to Reduce Inequality [10.806517393212491]
  We develop a novel algorithmic framework for tackling pre-existing real-world disparities. The purpose of our framework is to measure real-world disparities and discover optimal intervention policies. In contrast to most work on optimal policy learning, we explore disparity reduction itself as an objective.
  arXiv  Detail & Related papers  (2021-07-01T16:35:12Z)
• Understanding the origin of information-seeking exploration in probabilistic objectives for control [62.997667081978825]
  An exploration-exploitation trade-off is central to the description of adaptive behaviour. One approach to solving this trade-off has been to equip or propose that agents possess an intrinsic 'exploratory drive' We show that this combination of utility maximizing and information-seeking behaviour arises from the minimization of an entirely difference class of objectives.
  arXiv  Detail & Related papers  (2021-03-11T18:42:39Z)
• Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy [13.037143215464132]
  We show that fairness-accuracy trade-offs in many applications are negligible in practice. We find that explicitly focusing on achieving equity and using our proposed post-hoc disparity mitigation methods, fairness was substantially improved without sacrificing accuracy.
  arXiv  Detail & Related papers  (2020-12-05T08:10:47Z)
• Forecasting: theory and practice [65.71277206849244]
  This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches. We then demonstrate how such theoretical concepts are applied in a variety of real-life contexts.
  arXiv  Detail & Related papers  (2020-12-04T16:56:44Z)
• End-to-End Learning and Intervention in Games [60.41921763076017]
  We provide a unified framework for learning and intervention in games. We propose two approaches, respectively based on explicit and implicit differentiation. The analytical results are validated using several real-world problems.
  arXiv  Detail & Related papers  (2020-10-26T18:39:32Z)
• On Consequentialism and Fairness [64.35872952140677]
  We provide a consequentialist critique of common definitions of fairness within machine learning. We conclude with a broader discussion of the issues of learning and randomization.
  arXiv  Detail & Related papers  (2020-01-02T05:39:48Z)

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.