Article De Blog Scientifique Année : 2025

An Illustrated Guide to Automatic Sparse Differentiation

Résumé

In numerous applications of machine learning, Hessians and Jacobians exhibit sparsity, a property that can be leveraged to vastly accelerate their computation. While the usage of automatic differentiation in machine learning is ubiquitous, automatic sparse differentiation (ASD) remains largely unknown. This post introduces ASD, explaining its key components and their roles in the computation of both sparse Jacobians and Hessians. We conclude with a practical demonstration showcasing the performance benefits of ASD.

Fichier non déposé

Dates et versions

hal-05116383 , version 1 (17-06-2025)

Identifiants

  • HAL Id : hal-05116383 , version 1

Citer

Adrian Hill, Guillaume Dalle, Alexis Montoison. An Illustrated Guide to Automatic Sparse Differentiation. 2025. ⟨hal-05116383⟩
81 Consultations
0 Téléchargements

Partager

  • More