A Common Interface for Automatic Differentiation
Guillaume Dalle, Adrian Hill; 27(25):1−13, 2026.
Abstract
For scientific machine learning tasks with a lot of custom code, picking the right Automatic Differentiation (AD) system matters. Our Julia package DifferentiationInterface.jl provides a common frontend to a dozen AD backends, unlocking easy comparison and modular development. In particular, its built-in preparation mechanism leverages the strengths of each backend by amortizing one-time computations. This is key to enabling sophisticated features like sparsity handling without putting additional burdens on the user.
[abs]
[pdf][bib] [code]| © JMLR 2026. (edit, beta) |