BriefGPT.xyz
Oct, 2007
一种有效的排名归类简化方法
An efficient reduction of ranking to classification
HTML
PDF
Nir Ailon, Mehryar Mohri
TL;DR
本文介绍了一种将排名学习问题有效降至二元分类问题的算法,该算法保证平均成对错误率不超过二进制分类算法误差,适用于更广泛的排名损失函数类,且其时间复杂度在实际应用中较为高效。
Abstract
This paper describes an efficient reduction of the learning problem of
ranking
to
binary classification
. As with a recent result of Balcan et al., the reduction guarantees an average pairwise misranking
→