Automatic Differentiation via Effects and Handlers: An Implementation in Frank

01/20/2021

∙

by   Jesse Sigal, et al.

∙

0

∙

share

Automatic differentiation (AD) is an important family of algorithms which enables derivative based optimization. We show that AD can be simply implemented with effects and handlers by doing so in the Frank language. By considering how our implementation behaves in Frank's operational semantics, we show how our code performs the dynamic creation of programs during evaluation.