Looks interesting, thanks for posting and commenting here!
Does it in any way attempt to find the global minimum, or will it merely enhance the decent to any local minimum of the cost function?
(I am one of the authors) Generally speaking, the latter. The purpose of DiscoGrad is just to deliver useful gradients. These provide information about the local behavior of the cost function around the currently evaluated point to an optimizer of your choice, e.g., gradient descent. Interestingly, the smoothing and noise can sometimes prevent getting stuck in undesired (shallow) local minima when using gradient descent.
