Reverse derivative categories

DOI10.4230/LIPICS.CSL.2020.18MaRDI QIDQ6327285arXivFDO

Authors J. R. B. Cockett, G. S. H. Cruttwell, Jonathan Gallagher, Jean-Simon Pacaud Lemay, Benjamin MacAdam, Gordon D. Plotkin, Dorette Pronk

Publication date 15 October 2019

Published in arXiv

Full work available at URL https://doi.org/10.4230/LIPICS.CSL.2020.18

Mathematics Subject Classification ID

Logic in computer science (03B70) Computer science (68-XX)

arXiv classification

cs.LOmath.CT

Abstract: The reverse derivative is a fundamental operation in machine learning and automatic differentiation. This paper gives a direct axiomatization of a category with a reverse derivative operation, in a similar style to that given by Cartesian differential categories for a forward derivative. Intriguingly, a category with a reverse derivative also has a forward derivative, but the converse is not true. In fact, we show explicitly what a forward derivative is missing: a reverse derivative is equivalent to a forward derivative with a dagger structure on its subcategory of linear maps. Furthermore, we show that these linear maps form an additively enriched category with dagger biproducts.

This page was built for publication: Reverse derivative categories

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6327285)