paper-with-me

홈 › Papers

Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds

2024-05-12 · Meiyu Zhong, Ravi Tandon

With the growing adoption of machine learning (ML) systems in areas like law enforcement, criminal justice, finance, hiring, and admissions, it is increasingly critical to guarantee the fairness of decisions assisted by ML. In this paper, we study the tradeoff between fairness and accuracy under the statistical notion of equalized odds. We present a new upper bound on the accuracy (that holds for any classifier), as a function of the fairness budget. In addition, our bounds also exhibit dependence on the underlying statistics of the data, labels and the sensitive group attributes. We validate our theoretical upper bounds through empirical analysis on three real-world datasets: COMPAS, Adult, and Law School. Specifically, we compare our upper bound to the tradeoffs that are achieved by various existing fair classifiers in the literature. Our results show that achieving high accuracy subject to a low-bias could be fundamentally limited based on the statistical disparity across the groups.

📄 PDF Abstract BibTeX arXiv:2405.07393

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning

2025-08-20 · Yijin Ni, Xiaoming Huo arxiv

This paper introduces a novel kernel-based formulation of the Equalized Odds (EO) criterion, denoted as $EO_k$, for fair representation learning (FRL) in supervised settings. The central goal of FRL is to mitigate discri…

Representation Learning

Differentially Private Fair Learning

2018-12-06 · Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea 외

Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we …

AttributeFairness

A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition

2024-06-07 · Faisal Hamman, Sanghamitra Dutta

This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is we…

Fairness

Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning

2023-11-30 · Kangkang Sun, Xiaojin Zhang, Xi Lin, Gaolei Li 외

Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm that guarantees user privacy and prevents the risk of data leakage due to the advantage of the client's local training. Research…

FairnessFederated Learning

A Stochastic Optimization Framework for Fair Risk Minimization

2021-02-24 · NeurIPS 2021 12 · Andrew Lowy, Sina Baharlouei, Rakesh Pavan, Meisam Razaviyayn 외

Despite the success of large-scale empirical risk minimization (ERM) at achieving high accuracy across a variety of machine learning tasks, fair ERM is hindered by the incompatibility of fairness constraints with stochas…

Binary ClassificationFairnessStochastic Optimization