mlsanityData to 14 Oct 2026

Reverse Fa`a di Bruno's Formula for Cartesian Reverse Differential Categories

arXiv 2509.20931 ↗First posted 25 Sep 2025cs.LO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Reverse differentiation is an essential operation for automatic differentiation. Cartesian reverse differential categories axiomatize reverse differentiation in a categorical framework, where one of the primary axioms is the reverse chain rule, which is the formula that expresses the reverse derivative of a composition. Here, we present the reverse differential analogue of Faa di Bruno's Formula, which gives a higher-order reverse chain rule in a Cartesian reverse differential category. To properly do so, we also define partial reverse derivatives and higher-order reverse derivatives in a Cartesian reverse differential category.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 16 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

10 of 16 references.

References · 10

  1. 2017Backprop as Functor: A compositional perspective on supervised learningcited by 44
  2. 2021Categorical Foundations of Gradient-Based Learningcited by 44
  3. 2019Reverse derivative categoriescited by 15
  4. 2021Reverse Derivative Ascent: A Categorical Approach to Learning Boolean Circuitscited by 10
  5. 2022Categories of Differentiable Polynomial Circuits for Machine Learningcited by 4
  6. 2021CHAD: Combinatory Homomorphic Automatic Differentiationcited by 3
  7. 2020Linearizing Combinatorscited by 1
  8. 2021Categorical semantics of a simple differential programming languagecited by 1
  9. 2022Monoidal Reverse Differential Categoriescited by 1
  10. 2022Jacobians and Gradients for Cartesian Differential Categoriescited by 1

Built on by

Not cited yet.