Affiliation:
1. MCS Division Argonne National Laboratory Lemont Illinois USA
2. CASC Lawrence Livermore National Laboratory Livermore California USA
3. MIT CSAIL Cambridge Massachusetts USA
4. School of Physics, Engineering & Computer Science University of Hertfordshire Hatfield UK
5. Inria Sophia‐Antipolis Team Ecuador Valbonne France
Abstract
AbstractAutomatic 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