JMLR

A Common Interface for Automatic Differentiation

Authors
Guillaume Dalle Adrian Hill
View Full Paper
Paper Information
  • Journal:
    Journal of Machine Learning Research
  • Added to Tracker:
    Mar 03, 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.

Author Details
Guillaume Dalle
Author
Adrian Hill
Author
Citation Information
APA Format
Guillaume Dalle & Adrian Hill . A Common Interface for Automatic Differentiation. Journal of Machine Learning Research .
BibTeX Format
@article{paper989,
  title = { A Common Interface for Automatic Differentiation },
  author = { Guillaume Dalle and Adrian Hill },
  journal = { Journal of Machine Learning Research },
  url = { https://www.jmlr.org/papers/v27/25-1024.html }
}
Back to Papers