Automatic Differentiation in PCF - Laboratoire d'Informatique de Paris-Nord Accéder directement au contenu
Article Dans Une Revue Proceedings of the ACM on Programming Languages Année : 2021

Automatic Differentiation in PCF

Résumé

We study the correctness of automatic differentiation (AD) in the context of a higher-order, Turing-complete language (PCF with real numbers), both in forward and reverse mode. Our main result is that, under mild hypotheses on the primitive functions included in the language, AD is almost everywhere correct, that is, it computes the derivative or gradient of the program under consideration except for a set of Lebesgue measure zero. Stated otherwise, there are inputs on which AD is incorrect, but the probability of randomly choosing one such input is zero. Our result is in fact more precise, in that the set of failure points admits a more explicit description: for example, in case the primitive functions are just constants, addition and multiplication, the set of points where AD fails is contained in a countable union of zero sets of polynomials.
Fichier principal
Vignette du fichier
AutoDiffPCF(1).pdf (414.7 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03379031 , version 1 (14-10-2021)

Identifiants

Citer

Damiano Mazza, Michele Pagani. Automatic Differentiation in PCF. Proceedings of the ACM on Programming Languages, 2021, 5, pp.1 - 27. ⟨10.1145/3434309⟩. ⟨hal-03379031⟩
28 Consultations
58 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More