Join GitHub today
GaussianCriterion gradient issue #13
In GaussianCriterion.lua the gradient with respect to log(sigma^2) is computed as:
But it seems to me that the multiplication should be by -0.5, not -1, such that
which would also be consistent with the expression in your comment (after flipping the sign for neg. log likelihood):
I am seeing a gradient check fail with the original code but it passes after the change.