arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.02035cs.LGstat.ML
收藏

带弃权的排序

Ranking with Abstention

Courant Institute of Mathematical Sciences(库朗数学科学研究所);Google Research(谷歌研究院)

Anqi Mao, Mehryar Mohri, Yutao Zhong

AI总结:

本文提出带弃权的排序框架,允许学习器以有限代价放弃预测,并给出线性函数和单隐层神经网络的H-一致性界,实验验证了其有效性。

摘要:

我们引入了一个新颖的带弃权的排序框架,在该框架中,学习器可以在支付一定有限代价 $c$ 的情况下弃权(不执行)预测。我们对该框架进行了广泛的理论分析,包括针对线性函数族和具有一个隐藏层的神经网络族的一系列 $H$-一致性界。这些理论保证是文献中最先进的一致性保证,它们是假设集 $H$ 中预测器目标损失估计误差的上界,用该预测器的替代损失估计误差来表示。我们进一步论证,在实践中使用常见的等度连续假设集时,我们提出的弃权方法非常重要。我们报告了实验结果,展示了带弃权的排序的有效性。

英文摘要:

We introduce a novel framework of ranking with abstention, where the learner can abstain from making prediction at some limited cost $c$. We present a extensive theoretical analysis of this framework including a series of $H$-consistency bounds for both the family of linear functions and that of neural networks with one hidden-layer. These theoretical guarantees are the state-of-the-art consistency guarantees in the literature, which are upper bounds on the target loss estimation error of a predictor in a hypothesis set $H$, expressed in terms of the surrogate loss estimation error of that predictor. We further argue that our proposed abstention methods are important when using common equicontinuous hypothesis sets in practice. We report the results of experiments illustrating the effectiveness of ranking with abstention.

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。

↑