early stopping
A regularization technique where training is halted when validation performance stops improving, preventing overfitting by stopping before the model memorizes training noise.
As defined in Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94
Where it comes up · 1
Most important claims · 1 of 1Search all claims for “early stopping” →
- Double descent is a phenomenon where test error exhibits a non-monotonic U-shape as model size increases while data is fixed: performance improves as networks grow, then worsens sharply around the interpolation threshold (where model parameters equal training examples), then improves again as model size continues to grow, and this pattern occurs across virtually all practical deep learning systems without early stopping.Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94