Inherent tradeoffs in learning fair representations
Real-world applications of machine learning tools in high-stakes domains are often
regulated to be fair, in the sense that the predicted target should satisfy some quantitative …
regulated to be fair, in the sense that the predicted target should satisfy some quantitative …
A statistical test for probabilistic fairness
Algorithms are now routinely used to make consequential decisions that affect human lives.
Examples include college admissions, medical interventions or law enforcement. While …
Examples include college admissions, medical interventions or law enforcement. While …
What is fair? exploring pareto-efficiency for fairness constrained classifiers
The potential for learned models to amplify existing societal biases has been broadly
recognized. Fairness-aware classifier constraints, which apply equality metrics of …
recognized. Fairness-aware classifier constraints, which apply equality metrics of …
Fair classification and social welfare
L Hu, Y Chen - Proceedings of the 2020 conference on fairness …, 2020 - dl.acm.org
Now that machine learning algorithms lie at the center of many important resource allocation
pipelines, computer scientists have been unwittingly cast as partial social planners. Given …
pipelines, computer scientists have been unwittingly cast as partial social planners. Given …
Taking advantage of multitask learning for fair classification
A central goal of algorithmic fairness is to reduce bias in automated decision making. An
unavoidable tension exists between accuracy gains obtained by using sensitive information …
unavoidable tension exists between accuracy gains obtained by using sensitive information …
Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds
M Zhong, R Tandon - arXiv preprint arXiv:2405.07393, 2024 - arxiv.org
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 …
criminal justice, finance, hiring, and admissions, it is increasingly critical to guarantee the …
Equal improvability: A new fairness notion considering the long-term impact
Devising a fair classifier that does not discriminate against different groups is an important
problem in machine learning. Although researchers have proposed various ways of defining …
problem in machine learning. Although researchers have proposed various ways of defining …
An empirical study of rich subgroup fairness for machine learning
Kearns, Neel, Roth, and Wu [ICML 2018] recently proposed a notion of rich subgroup
fairness intended to bridge the gap between statistical and individual notions of fairness …
fairness intended to bridge the gap between statistical and individual notions of fairness …
Active fairness in algorithmic decision making
A Noriega-Campero, MA Bakker… - Proceedings of the …, 2019 - dl.acm.org
Society increasingly relies on machine learning models for automated decision making. Yet,
efficiency gains from automation have come paired with concern for algorithmic …
efficiency gains from automation have come paired with concern for algorithmic …
Pareto efficient fairness in supervised learning: From extraction to tracing
As algorithmic decision-making systems are becoming more pervasive, it is crucial to ensure
such systems do not become mechanisms of unfair discrimination on the basis of gender …
such systems do not become mechanisms of unfair discrimination on the basis of gender …