Double descent is a machine learning phenomenon in which test error can decrease, then increase near the point where model capacity matches the training data, and then decrease again as capacity becomes very large. It challenges the classical expectation that increasing model complexity monotonically worsens generalization after overfitting begins.
A phenomenon in statistics and machine learning where a model with a small number of parameters and a model with an extremely large number of parameters have a small test error, but a model whose number of parameters is about the same as the number of data points used to train the model will have a large error. This phenomenon has been considered surprising, as it contradicts assumptions about overfitting in classical machine learning.