Mean squared error

The average loss per example when L2 loss is used. Calculate MSE as follows:¹

1. Calculate the L2 loss for a batch.
2. Divide the L2 loss by the number of examples in the batch.

Mean Squared Error is a popular training optimizer, particularly for linear regression.¹

Formula

$$MSE = \frac{1}{N}\sum_{i=0}^{N} (y_i - \hat{y}_i)^2$$

where:

• $n$ is the number of examples.
• $y$ is the actual value of the label.
• $\hat{y}$ is the model’s prediction for $y$.

See also

• Mean absolute error
• Root mean squared error

Footnotes

1. developers.google.com/machine-learning/glossary#MSE ↩ ↩²