Automatic Differentiation of Algorithms for Machine Learning
It addresses the underutilization of AD tools in machine learning and other fields, providing an educational resource to bridge this gap.
The paper reviews automatic differentiation (AD), explaining its two main modes and how it benefits machine learning practitioners, aiming to make the technique accessible by assuming only elementary calculus knowledge.
Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and generalizes the method of backwards propagation of errors used in machine learning. Despite this, practitioners in a variety of fields, including machine learning, have been little influenced by automatic differentiation, and make scant use of available tools. Here we review the technique of automatic differentiation, describe its two main modes, and explain how it can benefit machine learning practitioners. To reach the widest possible audience our treatment assumes only elementary differential calculus, and does not assume any knowledge of linear algebra.