![architecture](https://i-blog.csdnimg.cn/blog_migrate/238235b814ddeffc65471648955435d0.webp?x-image-process=image/format,png)
0-1 Loss:
L01(mi(w))=I[mi(w)<0]
Log loss:
Llog(mi(w))=log(1+e−mi(w))
Hingle loss:
Lhingle(mi(w))=max(0,1−mi(w))
其中, w 表示weight vector, ti 表示class label, xi 表示feature vector, mi(w)=tifw(xi) 。
Reference
[1]. Algorithms for Direct 0–1 Loss Optimization in Binary Classification