I am doing k-fold cross validation across my training set with the goal of finding the best structure for a neural network.

Within each fold, should I A) train the network for a constant number of epochs? OR B) train each fold until the error on the current fold starts increasing?

If I do B) then each parameter set will be trained for different number of epochs. This gives me an additional hyper parameter (number of epochs) which I could use but I am planning on using an additional holdout set to test the performance. Should I then just ignore the number of epochs that the cross validation found and train on the entire training set until the error on the holdout set increases ??


You could do A but it is not recommended. The steps most often employed are described in pg 245 of the text (pg 264/764 in the pdf)


An important caveat: The book recommends Often a “one-standard error” rule is used with cross-validation, in which we choose the most parsimonious model whose error is no more than one standard error above the error of the best model.. I have seen some papers where they chose the minimum error model also. There is nothing right or wrong in either method. These are typically caveats based on heuristics. The one std. error rule they describe is motivated by the bias-variance tradeoff.

The number of iterations is typically not relevant; the convergence criteria is. Is there a reason you care about the number of iterations?

  • $\begingroup$ Thanks for your answer. I was interested in the number of epochs as I am implementing this in code and need to know when to stop training each fold (some sets of hyper parameters will no doubt take longer than others to reach a minima). $\endgroup$
    – nixon
    Apr 3 '18 at 4:58
  • 1
    $\begingroup$ During cross validation, you are assuming that the data barring the fold you are using for validation is your train set, so train all the way through till your error starts increasing, much like is suggested in part B of your post $\endgroup$
    – Sid
    Apr 3 '18 at 5:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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