A Taxonomy of Automatic Differentiation Pitfalls
Author
Hückelheim, Jan
Menon, Harshitha
Moses, William
Christianson, Bruce
Hovland, Paul
Hascoët, Laurent
Attention
2299/28117
Abstract
Automatic differentiation is a popular technique for computing derivatives of computer programs. While automatic differentiation has been successfully used in countless engineering, science, and machine learning applications, it can sometimes nevertheless produce surprising results. In this paper, we categorize problematic usages of automatic differentiation, and illustrate each category with examples such as chaos, time-averages, discretizations, fixed-point loops, lookup tables, linear solvers, and probabilistic programs, in the hope that readers may more easily avoid or detect such pitfalls. We also review debugging techniques and their effectiveness in these situations. This article is categorized under: Technologies > Machine Learning.