5. Mean Squared Error

Implement the Mean Squared Error (MSE) loss function.

Given a vector of true values $\mathbf{y}$ and predicted values $\hat{\mathbf{y}}$:

$\text{MSE} = \frac{1}{n} \sum_{i=1}^{n} (y_i - \hat{y}_i)^2$

MSE is one of the most common loss functions for regression tasks. Squaring the errors penalises large deviations more heavily than small ones.

Example

y_true = [1, 2, 3]
y_pred = [1, 2, 3]
Output: 0.0          # perfect predictions

y_true = [0, 0, 0]
y_pred = [1, 1, 1]
Output: 1.0

Constraints

• Both inputs will always have the same length $n \geq 1$.
• Return a plain Python float.