Efficient differentiable programming in a functional array-processing language

We present a system for the automatic differentiation (AD) of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source forward-mode AD and global optimisations such as loop transformations. In combination,...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of ACM on programming languages 2019-08, Vol.3 (ICFP), p.1-30
Main Authors: Shaikhha, Amir, Fitzgibbon, Andrew, Vytiniotis, Dimitrios, Peyton Jones, Simon
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a system for the automatic differentiation (AD) of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source forward-mode AD and global optimisations such as loop transformations. In combination, gradient computation with forward-mode AD can be as efficient as reverse mode, and that the Jacobian matrices required for numerical algorithms such as Gauss-Newton and Levenberg-Marquardt can be efficiently computed.
ISSN:2475-1421
2475-1421
DOI:10.1145/3341701