Differential structure, tangent structure, and SDG
JRB Cockett, GSH Cruttwell - Applied Categorical Structures, 2014 - Springer
In 1984, J. Rosický gave an abstract presentation of the structure associated to tangent
bundle functors in differential and algebraic geometry. By slightly generalizing this notion …
bundle functors in differential and algebraic geometry. By slightly generalizing this notion …
Fundamental Components of Deep Learning: A category-theoretic approach
B Gavranović - arXiv preprint arXiv:2403.13001, 2024 - arxiv.org
Deep learning, despite its remarkable achievements, is still a young field. Like the early
stages of many scientific disciplines, it is marked by the discovery of new phenomena, ad …
stages of many scientific disciplines, it is marked by the discovery of new phenomena, ad …
On generalized metric spaces for the simply typed lambda-calculus
P Pistone - 2021 36th Annual ACM/IEEE Symposium on Logic …, 2021 - ieeexplore.ieee.org
Generalized metrics, arising from Lawvere's view of metric spaces as enriched categories,
have been widely applied in denotational semantics as a way to measure to which extent …
have been widely applied in denotational semantics as a way to measure to which extent …
Higher order automatic differentiation of higher order functions
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 …
forward-mode AD method on a higher order language with algebraic data types, and we …
Cartesian differential storage categories
Cartesian differential categories were introduced to provide an abstract axiomatization of
categories of differentiable functions. The fundamental example is the category whose …
categories of differentiable functions. The fundamental example is the category whose …
Categorical semantics of a simple differential programming language
G Cruttwell, J Gallagher, D Pronk - arXiv preprint arXiv:2101.10491, 2021 - arxiv.org
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 …
automatic differentiation has become more wide-spread in computation. There have been …
[HTML][HTML] Change actions: models of generalised differentiation
M Alvarez-Picallo, CHL Ong - … Conference, FOSSACS 2019, Held as Part …, 2019 - Springer
Change structures, introduced by Cai et al., have recently been proposed as a semantic
framework for incremental computation. We generalise change actions, an alternative to …
framework for incremental computation. We generalise change actions, an alternative to …
[HTML][HTML] Exponential functions in cartesian differential categories
JSP Lemay - Applied Categorical Structures, 2021 - Springer
In this paper, we introduce differential exponential maps in Cartesian differential categories,
which generalizes the exponential function e^ x ex from classical differential calculus. A …
which generalizes the exponential function e^ x ex from classical differential calculus. A …
[HTML][HTML] Cartesian differential categories as skew enriched categories
We exhibit the cartesian differential categories of Blute, Cockett and Seely as a particular
kind of enriched category. The base for the enrichment is the category of commutative …
kind of enriched category. The base for the enrichment is the category of commutative …
A Tangent Category Alternative to the Fa\a di Bruno Construction
JS Lemay - arXiv preprint arXiv:1805.01774, 2018 - arxiv.org
The Fa\a di Bruno construction, introduced by Cockett and Seely, constructs a comonad
$\mathsf {Fa {\grave {a}}} $ whose coalgebras are precisely Cartesian differential categories …
$\mathsf {Fa {\grave {a}}} $ whose coalgebras are precisely Cartesian differential categories …