L1 loss

A loss function that calculates the absolute value of the difference between actual label values and the values that a model predicts. L1 loss is less sensitive to outliers than L2 loss.¹

$$L_1 loss = \sum_{i=0}^{n} | y_i - \hat{y}_i |$$

where:

• $n$ is the number of examples.
• $y$ is the actual value of the label.
• $\hat{y}$ is the value that the model predicts for $y$.

See also

• Mean absolute error is the average L1 loss per example.

Footnotes

1. developers.google.com/machine-learning/glossary#l1-loss ↩