What is the difference between L1 and L2 Loss?

What is the difference between L1 and L2 Loss?

Approach: Compare Mean Absolute Error (MAE) and Mean Squared Error (MSE).

L1 loss (MAE) is the sum of absolute differences between actual and predicted values. L2 loss (MSE) is the sum of the squares of the differences. L2 is more sensitive to outliers, while L1 is more robust.

Follow-up: Why is L2 more commonly used in optimization?

Key concepts: outliers, robustness, sensitivity.