Correctness of Automatic Differentiation via Diffeologies and Categorical Gluing

Mathieu Huot*, Sam Staton, Matthijs Vákár

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    We present semantic correctness proofs of Automatic Differentiation (AD). We consider a forward-mode AD method on a higher order language with algebraic data types, and we characterise it as the unique structure preserving macro given a choice of derivatives for basic operations. We describe a rich semantics for differentiable programming, based on diffeological spaces. We show that it interprets our language, and we phrase what it means for the AD method to be correct with respect to this semantics. We show that our characterisation of AD gives rise to an elegant semantic proof of its correctness based on a gluing construction on diffeological spaces. We explain how this is, in essence, a logical relations argument. Finally, we sketch how the analysis extends to other AD methods by considering a continuation-based method.
    Original languageEnglish
    Title of host publicationFoundations of Software Science and Computation Structures - 23rd International Conference, FOSSACS 2020, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2020, Dublin, Ireland, April 25-30, 2020, Proceedings
    EditorsJean Goubault-Larrecq, Barbara König
    PublisherSpringer
    Pages319-338
    Number of pages20
    Volume12077
    ISBN (Electronic)978-3-030-45231-5
    ISBN (Print)978-3-030-45230-8
    DOIs
    Publication statusPublished - 17 Apr 2020

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer

    Fingerprint

    Dive into the research topics of 'Correctness of Automatic Differentiation via Diffeologies and Categorical Gluing'. Together they form a unique fingerprint.

    Cite this