L0 regularization

A type of regularization that penalizes the total number of nonzero weights in a model. For example, a model having 11 nonzero weights would be penalized more than a similar model having 10 nonzero weights. L0 regularization is sometimes called L0-norm regularization.

L0 regularization is generally impractical in large models because L0 regularization turns training into a convex optimization problem. ---

Practitioners refer to l0 regularization when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.