Optimal Use of Preferences in Artificial Intelligence Algorithms
收藏NBER2026-02-01 更新2026-02-07 收录
下载链接：
https://www.nber.org/papers/w34780
下载链接
链接失效反馈官方服务：
资源简介：
Machine learning systems embed preferences either in training losses or through post-processing of calibrated predictions. Applying information design methods from Strack and Yang (2024), this paper provides decision-problem-agnostic conditions under which separationtraining preference-free and
提供机构：
美国国家经济研究局
创建时间：
2026-02-01
