I'm doing nested cross-validation on a classification problem (inner loop to tune hyperparameters, outer loop to select algorithm).
I've often heard that a reasonable number of folds for standard (I.e.: not nested) cross-validation is 5 or 10.
Is there a similar rule of thumb for nested cross-validation? Should I have more folds in the inner or the outer? How many?
I'm not looking for a definitive answer, I'm just curious to hear what people usually go for. Thanks.