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 1602.08151cs.LGstat.ML
收藏

学习放弃二元预测

Learning to Abstain from Binary Prediction

University of California, San Diego(加州大学圣地亚哥分校)

Akshay Balsubramani

摘要:

一个能够避免进行标签预测的二元分类器有两个紧张的目标:最小化错误,并避免不必要的经常放弃。在这项工作中,我们确切地描述了这两个目标之间的最佳可实现的权衡,在一般的半监督设置,给定的不同能力的预测以及未标记的数据,我们希望预测或弃权的合奏。我们给出了一个算法,学习分类器在这种设置中,权衡其错误与弃权的最小最大的最佳方式,是有效的线性学习和预测,并证明是实用的。我们的分析扩展到一个大类的损失函数和其他情况下,包括合奏组成的专家,可以自己弃权。

英文摘要:

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between these two goals in a general semi-supervised setting, given an ensemble of predictors of varying competence as well as unlabeled data on which we wish to predict or abstain. We give an algorithm for learning a classifier in this setting which trades off its errors with abstentions in a minimax optimal manner, is as efficient as linear learning and prediction, and is demonstrably practical. Our analysis extends to a large class of loss functions and other scenarios, including ensembles comprised of specialists that can themselves abstain.

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。

↑