News for hackers. Stuff that matters.
Re:Automatic Differentiation with Julia by gugagore on Tuesday October 23, 2018 @01:37PM (#18285529)
presumably, source-to-source "AD" could do some symbolic reasoning (whether any systems do, and whether it still counts as AD, I don't actually know). Specifically, I have in mind a source-to-source system that could look at `sqrt(x^2)` and produce a valid sub-gradient at x=0. With AD (whether forward-mode or reverse), you get NaN=Inf*0, because the gradient of x^2 is 0 and the gradient of `sqrt` is Inf.

There are no comments on this comment yet.