Software-based Automatic Differentiation is Flawed

Daniel Johnson, Trevor Maxfield, Yongxu Jin, Ronald Fedkiw

Abstract: Various software efforts embrace the idea that object oriented programming enables a convenient implementation of the chain rule, facilitating so-called automatic differentiation via backpropagation. Such frameworks have no mechanism for simplifying the expressions (obtained via the chain rule) before evaluating them. As we illustrate below, the resulting errors tend to be unbounded.