L2 regularization Machine Learning
noun phrase
Definition: A regularization technique that adds an L2 penalty term, based on the squared magnitude of the weights, to the loss function in order to reduce overfitting [scikit-learn Documentation].
Example in context: “To reduce the overfitting of the training data, we use L2 regularization on each layer of neural networks.” [Liu et al. 2022]
Synonym: ridge regularization
Related terms: weight decay, regularization