精神错乱的危险:关于分类器的精度最小化噪声鲁棒凸损失
The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss
摘要:
Van Rooyen等人引入了凸损失函数对随机分类噪声具有鲁棒性的概念,并建立了“无铰链”损失函数在这个意义上是鲁棒的。在本说明中,我们研究了通过最小化精神错乱损失获得的二元分类器的准确性,并观察到即使对于简单的线性可分数据分布,最小化精神错乱损失也可能只会产生准确性并不比随机猜测更好的二元分类器。
英文摘要:
Van Rooyen et al. introduced a notion of convex loss functions being robust to random classification noise, and established that the "unhinged" loss function is robust in this sense. In this note we study the accuracy of binary classifiers obtained by minimizing the unhinged loss, and observe that even for simple linearly separable data distributions, minimizing the unhinged loss may only yield a binary classifier with accuracy no better than random guessing.
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。