Removing Algorithmic Discrimination (With Minimal Individual Error)
We address the problem of correcting group discriminations within a score function, while minimizing the individual error. Each group is described by a probability density function on the set of profiles. We first solve the problem analytically in the case of two populations, with a uniform bonus-malus on the zones where each population is a majority. We then address the general case of n populations, where the entanglement of populations does not allow a similar analytical solution. We show that an approximate solution with an arbitrarily high level of precision can be computed with linear programming. Finally, we address the inverse problem where the error should not go beyond a certain value and we seek to minimize the discrimination.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action
Various metrics and interventions have been developed to identify and mitigate unfair outputs of machine learning systems. While individuals and organizations have an obligation to avoid discrimination, the use of fairne…
Decision MakingFairnessFairness in Deep Learning: A Computational Perspective
Deep learning is increasingly being used in high-stake decision making applications that affect individual lives. However, deep learning models might exhibit algorithmic discrimination behaviors with respect to protected…
Decision MakingDeep LearningFairnessUnderrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond
Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discriminat…
Formalising Anti-Discrimination Law in Automated Decision Systems
Algorithmic discrimination is a critical concern as machine learning models are used in high-stakes decision-making in legally protected contexts. Although substantial research on algorithmic bias and discrimination has …
FairnessLegal ReasoningMisconceptionsImplications of the AI Act for Non-Discrimination Law and Algorithmic Fairness
The topic of fairness in AI, as debated in the FATE (Fairness, Accountability, Transparency, and Ethics in AI) communities, has sparked meaningful discussions in the past years. However, from a legal perspective, particu…
Bias DetectionEthicsFairness