paper-with-me

홈 › Papers

Removing Algorithmic Discrimination (With Minimal Individual Error)

2018-06-07 · El Mahdi El Mhamdi, Rachid Guerraoui, Lê Nguyên Hoang, Alexandre Maurer

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.

📄 PDF Abstract BibTeX arXiv:1806.02510

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action

2024-04-18 · Hilde Weerts, Raphaële Xenidis, Fabien Tarissan, Henrik Palmer Olsen 외

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 MakingFairness

Fairness in Deep Learning: A Computational Perspective

2019-08-23 · Mengnan Du, Fan Yang, Na Zou, Xia Hu

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 LearningFairness

Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond

2025-07-09 · Marina Ceccon, Giandomenico Cornacchia, Davide Dalle Pezze, Alessandro Fabris 외 arxiv

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

2024-06-29 · Holli Sargeant, Måns Magnusson

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 ReasoningMisconceptions

Implications of the AI Act for Non-Discrimination Law and Algorithmic Fairness

2024-03-29 · Luca Deck, Jan-Laurin Müller, Conradin Braun, Domenique Zipperling 외

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