PulseAugur
实时 10:23:28
English(EN) Unfair Utilities and First Steps Towards Improving Them

新的公平性框架分析效用函数,而非仅仅是策略

研究人员提出了一个新的框架来分析机器学习中的公平性,该框架侧重于效用函数本身,而不是对预测策略施加约束。这种被称为“信息公平价值”的方法认为,当没有推断受保护属性的动机时,就实现了公平性。作者们演示了如何修改效用函数来满足这一原则,并讨论了对最优策略的影响,将该框架应用于假设场景和COMPAS数据集。 AI

影响 引入了一种新颖的AI公平性理论方法,可能影响未来的模型开发和评估。

排序理由 该集群包含一篇学术论文,详细介绍了机器学习中公平性的一种新理论框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的公平性框架分析效用函数,而非仅仅是策略

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇学术论文,详细介绍了机器学习中公平性的一种新理论框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Frederik Hytting J{\o}rgensen, Sebastian Weichwald, Jonas Peters ·

    不公平的公用事业及改善它们的初步措施

    arXiv:2306.00636v3 Announce Type: replace-cross Abstract: Many fairness criteria constrain the policy or choice of predictors, which can have unwanted consequences, in particular, when optimizing the policy under such constraints. Here, we in- stead suggest that fairness can be d…