2021/01/19 by Geoffrey Cruttwell, Jonathan Gallagher, Dorette Pronk
Computer Science · Mathematics · #Categorical variable #Computability, Logic, AI Algorithms #Differential (mechanical device) #Distributional semantics #Extension (predicate logic) #Logic, Reasoning, and Knowledge #Logic, programming, and type systems #Semantics (computer science) #Simple (philosophy) #cs.PL #math.CT
paper · pdf · doi:10.4204/eptcs.333.20
published as EPTCS 333, 2021, pp. 289-310 · In Proceedings ACT 2020, arXiv:2101.07888
openalex publication_date 2021/01/19 · arxiv created 2021/01/26 · arxiv updated 2021/01/27 · openalex created_date 2021/02/01 · openalex updated_date 2026/08/05
With the increased interest in machine learning, and deep learning in particular, the use of automatic differentiation has become more wide-spread in computation. There have been two recent developments to provide the theoretical support for this types of structure. One approach, due to Abadi and Plotkin, provides a simple differential programming language. Another approach is the notion of a reverse differential category. In the present paper we bring these two approaches together. In particular, we show how an extension of reverse derivative categories models Abadi and Plotkin's language, and describe how this categorical model allows one to consider potential improvements to the operational semantics of the language.