Zobrazeno 1 - 10
of 257
pro vyhledávání: '"Loi Michele"'
In the field of algorithmic fairness, many fairness criteria have been proposed. Oftentimes, their proposal is only accompanied by a loose link to ideas from moral philosophy -- which makes it difficult to understand when the proposed criteria should
Externí odkaz:
http://arxiv.org/abs/2407.12488
By combining the philosophical literature on statistical evidence and the interdisciplinary literature on algorithmic fairness, we revisit recent objections against classification parity in light of causal analyses of algorithmic fairness and the dis
Externí odkaz:
http://arxiv.org/abs/2402.12062
Group fairness metrics are an established way of assessing the fairness of prediction-based decision-making systems. However, these metrics are still insufficiently linked to philosophical theories, and their moral meaning is often unclear. In this p
Externí odkaz:
http://arxiv.org/abs/2206.02897
In prediction-based decision-making systems, different perspectives can be at odds: The short-term business goals of the decision makers are often in conflict with the decision subjects' wish to be treated fairly. Balancing these two perspectives is
Externí odkaz:
http://arxiv.org/abs/2206.02891
Autor:
Loi, Michele, Heitz, Christoph
Publikováno v:
2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT '22), June 21-24, 2022, Seoul, Republic of Korea
In this paper, we provide a moral analysis of two criteria of statistical fairness debated in the machine learning literature: 1) calibration between groups and 2) equality of false positive and false negative rates between groups. In our paper, we f
Externí odkaz:
http://arxiv.org/abs/2205.05512
A recent paper (Hedden 2021) has argued that most of the group fairness constraints discussed in the machine learning literature are not necessary conditions for the fairness of predictions, and hence that there are no genuine fairness metrics. This
Externí odkaz:
http://arxiv.org/abs/2204.10305
Autor:
Cangiotti, Nicolò, Loi, Michele
We argue that an imperfect criminal law procedure cannot be group-fair, if 'group fairness' involves ensuring the same chances of acquittal or convictions to all innocent defendants independently of their morally arbitrary features. We show mathemati
Externí odkaz:
http://arxiv.org/abs/2202.03880
Publikováno v:
In Computer Law & Security Review: The International Journal of Technology Law and Practice April 2024 52
Autor:
Loi, Michele, Spielkamp, Matthias
We argue that the phenomena of distributed responsibility, induced acceptance, and acceptance through ignorance constitute instances of imperfect delegation when tasks are delegated to computationally-driven systems. Imperfect delegation challenges h
Externí odkaz:
http://arxiv.org/abs/2105.01434
A crucial but often neglected aspect of algorithmic fairness is the question of how we justify enforcing a certain fairness metric from a moral perspective. When fairness metrics are proposed, they are typically argued for by highlighting their mathe
Externí odkaz:
http://arxiv.org/abs/2011.02079