Mean Squared Error (Mse)

• AKA MSE
• AKA L2-loss
• MSE is used in Regression problems
• Sensitive to large errors for the squaring
• Gradient decreases as loss gets closer to 0

[!def] Mean Squared Error Formula
$$
MSE = \frac{1}{n} \sum_{i=1}^n (Y_i - \hat{Y}_i)^2
$$

Pros:

1. Convex function, so one Global Minima
2. No Local Minima
3. If error is big, penalizes higher by squaring them
4. Good for predicting outliers as give more weight to them

Cons:

1. Bad at Handling Outliers
2. Same error for one big error and many small errors