arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.01862cs.LGcs.HCstat.ML
收藏

学习服从专家的一致估计量

Consistent Estimators for Learning to Defer to an Expert

Massachusetts Institute of Technology(麻省理工学院)

Hussein Mozannar, David Sontag

摘要:

学习算法在实际应用中经常与专家决策者一起使用,然而在设计这些算法时,这一事实在很大程度上被忽略了。在本文中,我们将探讨如何学习预测器,可以预测或选择推迟决策的下游专家。在只给出专家决策样本的情况下,我们给出了一个基于学习分类器和拒绝器的过程,并从理论上进行了分析。我们的方法是基于一种新的减少成本敏感的学习,我们给了一个一致的替代损失成本敏感的学习,概括了交叉熵损失。我们展示了我们的方法对各种实验任务的有效性。

英文摘要:

Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms. In this paper we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑