MURAL - Maynooth University Research Archive Library



    Confusion of Tagged Perturbations in Forward Automatic Differentiation of Higher-Order Functions


    Manzyuk, Oleksandr and Pearlmutter, Barak A. and Radul, Alexey Andreyevich and Rush, David R. and Siskind, Jeffrey Mark (2012) Confusion of Tagged Perturbations in Forward Automatic Differentiation of Higher-Order Functions. Working Paper. arXiv.

    [img]
    Preview
    Download (94kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Forward Automatic Differentiation (AD) is a technique for augmenting programs to both perform their original calculation and also compute its directional derivative. The essence of Forward AD is to attach a derivative value to each number, and propagate these through the computation. When derivatives are nested, the distinct derivative calculations, and their associated attached values, must be distinguished. In dynamic languages this is typically accomplished by creating a unique tag for each application of the derivative operator, tagging the attached values, and overloading the arithmetic operators. We exhibit a subtle bug, present in fielded implementations, in which perturbations are confused despite the tagging machinery.

    Item Type: Monograph (Working Paper)
    Keywords: Tagged Perturbations; Forward Automatic Differentiation; Higher-Order Functions; Forward AD;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Item ID: 6552
    Identification Number: arXiv:1211.4892
    Depositing User: Barak Pearlmutter
    Date Deposited: 10 Nov 2015 16:43
    Publisher: arXiv
    Funders: Science Foundation Ireland (SFI)
    URI:

      Repository Staff Only(login required)

      View Item Item control page

      Downloads

      Downloads per month over past year