Provably correct, asymptotically efficient, higher-order reverse-mode automatic differentiation
View / Open Files
Authors
Krawiec, F
Peyton Jones, S
Krishnaswami, N
Ellis, T
Eisenberg, RA
Fitzgibbon, A
Publication Date
2022Journal Title
Proceedings of the ACM on Programming Languages
ISSN
2475-1421
Publisher
Association for Computing Machinery (ACM)
Volume
6
Issue
POPL
Pages
1-30
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Krawiec, F., Peyton Jones, S., Krishnaswami, N., Ellis, T., Eisenberg, R., & Fitzgibbon, A. (2022). Provably correct, asymptotically efficient, higher-order reverse-mode automatic differentiation. Proceedings of the ACM on Programming Languages, 6 (POPL), 1-30. https://doi.org/10.1145/3498710
Abstract
<jats:p>In this paper, we give a simple and efficient implementation of reverse-mode automatic differentiation, which both extends easily to higher-order functions, and has run time and memory consumption linear in the run time of the original program. In addition to a formal description of the translation, we also describe an implementation of this algorithm, and prove its correctness by means of a logical relations argument.</jats:p>
Identifiers
External DOI: https://doi.org/10.1145/3498710
This record's URL: https://www.repository.cam.ac.uk/handle/1810/334648
Rights
Attribution-NoDerivatives 4.0 International
Licence URL: https://creativecommons.org/licenses/by-nd/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.
Recommended or similar items
The current recommendation prototype on the Apollo Repository will be turned off on 03 February 2023. Although the pilot has been fruitful for both parties, the service provider IKVA is focusing on horizon scanning products and so the recommender service can no longer be supported. We recognise the importance of recommender services in supporting research discovery and are evaluating offerings from other service providers. If you would like to offer feedback on this decision please contact us on: support@repository.cam.ac.uk