
























Abstract:Machine Learning research, including work promoting fair or equitable algorithms, often relies on the concept of a data-generating probability distribution. The standard presumption is that since data points are 'sampled from' such a distribution, one can learn from observed data about this distribution and, thus, predict future data points which are also drawn from it. We argue, however, that such true probability distributions do not exist and that the rhetoric around them is harmful in social settings. We show that alternative frameworks focusing directly on relevant populations rather than abstract distributions are available and leave classical learning theory almost unchanged. Furthermore, we argue that the assumption of true probabilities or data-generating distributions can be misleading and obscure both the choices made and the goals pursued in machine learning practice. Based on these considerations, we suggest avoiding the assumption of data-generating probability distributions in the social world.
| Comments: | Accepted at FAccT'26 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2407.17395 [cs.LG] |
| (or arXiv:2407.17395v5 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2407.17395 arXiv-issued DOI via DataCite |
From: Benedikt Höltgen [view email]
[v1]
Wed, 24 Jul 2024 16:17:14 UTC (33 KB)
[v2]
Wed, 14 Aug 2024 12:17:38 UTC (35 KB)
[v3]
Thu, 12 Sep 2024 09:22:25 UTC (38 KB)
[v4]
Thu, 17 Jul 2025 06:59:59 UTC (77 KB)
[v5]
Wed, 22 Apr 2026 12:07:59 UTC (617 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。