Assuming I have loss function f(y_pred,y_target) that I will use to train my neural network. In this case the loss function is a regression, and let's say it should work on something that is not directly solvable by something like a mean squared error loss function. An example would be an angle, which gives the rotation of an object, due to the definition of the circle**.

I am not asking for a loss function for this problem, I want to know if there is a good way to test, if your loss function is correct.

I made two assumption which must be true for a loss function for work:

  1. The higher the discontent with the result, the higher the loss
  2. The derivation of the loss function should only be zero when the loss function itself is zero

One could now test this mathematically, however I am looking for a more programmable approach, like using a stochastic input and an error with a certain distribution added and expecting the same distribution in the loss function.

So, is there a typical approach to this? Some kind of "roadmap" to test the loss function itself to guarantee, that it will do the right job?

** a simple regression will not work, because 0 and 2pi,4pi and so on will mean the same

  • $\begingroup$ For reference (you aren't asking for this but others coming upon your question might), regression with circular dependent variables is provided by the R circular package. An example of a loss function for angles is on this page. There is a circular-statistics tag on this site. $\endgroup$
    – EdM
    Oct 10, 2019 at 18:09

1 Answer 1


On the paper "Outline of forecast theoryusing generalized cost functions" 1 Clive Granger (a nobel prize winner no less!) gives the following properties of a loss function $L(x)$:

  1. $L(0) = 0$ (no error, no loss).

  2. $\min L(x) = 0$, so $L(x)\geq 0$.

  3. $L(x)$ is monotonically non-decreasing as $x$ moves away from zero. (similar to your first requirement)

You could write your code to check these conditions

Also interesting is the paper "Loss Functions in Time Series Forecasting" 2 by Lee


  • 1
    $\begingroup$ This answer would be more helpful if you could please include specific references to the papers that you cite. Links to them would be ideal, but specifying the journal, volume, year, and page numbers would suffice. $\endgroup$
    – EdM
    Oct 10, 2019 at 18:11
  • $\begingroup$ Links added :). $\endgroup$
    – Ken Grimes
    Oct 11, 2019 at 7:32

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.