A Common Interface for Automatic Differentiation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dalle, Guillaume, Hill, Adrian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908367485665280
author Dalle, Guillaume
Hill, Adrian
author_facet Dalle, Guillaume
Hill, Adrian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05542
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Common Interface for Automatic Differentiation
Dalle, Guillaume
Hill, Adrian
Mathematical Software
Machine Learning
Numerical Analysis
G.1.4
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.
title A Common Interface for Automatic Differentiation
topic Mathematical Software
Machine Learning
Numerical Analysis
G.1.4
url https://arxiv.org/abs/2505.05542