BriefGPT.xyz
May, 2023
二元分类的替代风险的敌对一致性
The Adversarial Consistency of Surrogate Risks for Binary Classification
HTML
PDF
Natalie Frank, Jonathan Niles-Weed
TL;DR
本文研究了健壮二分类的代理风险的一致性，为任何数据分配，在原始对抗性风险的最小化序列不受影响的情况下，给出了一组一致的代理损失函数的简单和完整的刻画。
Abstract
We study the
consistency
of
surrogate risks
for
robust binary classification
. It is common to learn robust classifiers by
→