# Hinge
- Classification
- [SVM](SVM.md)
- the w are weights of the model
- labels are 1 or -1
- $\mathrm{max}\left( 0, 1 + \mathrm{max}\left( w_{y} \cdot x - w_{t} \cdot x \right) \right)$
- $L(y, \hat y) = \Sigma_{i}max(0, 1- y_{i}\hat y_{i})$
- maximum margin classification