the.ai

Foundations / Supervised

verified

Early Stopping

Watch performance on data the model is not training on, and stop when it stops improving. It is the simplest regularisation available and it costs nothing — no extra term, no hyperparameter to search, just a decision about when to quit — which is why it is in almost every training loop whether or not anyone calls it that.

Viz primitive · loss-curvesteps = 2000 · lr = 0.005 · batch = 128 · params = 10
loss
step 0dashed = held-out2000

Loss over 2000 training steps, starting near 9.0. It falls to about 1.51, with 97% of the total improvement arriving in the first half. A second line shows held-out, ending higher at about 1.71.

A run scored on its training data and on data held back from it. Drag the holdout up to watch the second curve turn upward while the first keeps falling — the crossing is where stopping pays, and the number you read there is not an unbiased estimate of anything.

0.15

Reviewed by opendroid · 2026-08-18

Origin · not linkable

  • Prechelt 1998 — Early Stopping — But When? · Neural Networks: Tricks of the Trade, LNCS 1524, Springer · doi:10.1007/3-540-49430-8_3