L1 loss is a loss function based on the absolute difference between predicted and actual values. It is less sensitive to large outliers than squared-error loss and is commonly used in regression and robust optimization contexts.
A loss function that calculates the absolute value of the difference between actual label values and the values that a model predicts. For example, here's the calculation of L~1~ loss for a batch of five examples: Model's predicted value --- 6 4 11 6 8 L~1~ loss is less sensitive to outliers than L~2~ loss. The Mean Absolute Error is the average L~1~ loss per example. where: - $n$ is the number of examples. - $y$ is the actual value of the label. - $\\\\y\$ is the value that the model predicts for $y$. See Linear regression: Loss in Machine Learning Crash Course for more information.