1
$\begingroup$

In the following training scenario (Orange: training loss, Blue: validation loss), what epoch is the best time for stopping the training? Validation is almost steady as we continue training, but training keeps decreasing. In other words, having two models where both have the same validation loss, is the one with the lower training loss better? enter image description here

$\endgroup$
1
  • $\begingroup$ You could stop when the probability that the validation loss is decreasing is small. One method: blog.dlib.net/2018/02/… $\endgroup$
    – Sycorax
    Apr 23, 2020 at 15:14

1 Answer 1

1
$\begingroup$

Here's what I'd do:

  1. Try with different training/test splits. It might be idiosyncratic. Especially with so few epochs.
  2. I assume that you're using different hyperparameters? Perhaps save the parameters and resume with a different set of hyperparameters. This comment really depends on how you're doing hyperparameter optimization.
  3. Depending on how costly it is to train the model and evaluate it, consider bagging your models, akin to how a random forest operates. In others words, fit your model to many different train/test splits, and average the model outputs, either in terms of a majority classification vote, or an averaging of the predicted probabilities. In this case, I'd err on the side of a slightly overfit model, because of the way that averaging can mitigate overfitting. But I wouldn't train to death either, unless you're going to fit very very many neural nets, and somehow ensure that you're decorrelating them akin to the method of random subspaces from random forests.
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.