English
Related papers

Related papers: Automatic Functional Differentiation in JAX

200 papers

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 characterise it as the unique structure-preserving macro given a…

Programming Languages · Computer Science 2026-05-07 Mathieu Huot , Sam Staton , Matthijs Vákár

In mathematics and computer algebra, automatic differentiation (AD) is a set of techniques to evaluate the derivative of a function specified by a computer program. AD exploits the fact that every computer program, no matter how…

Mathematical Software · Computer Science 2021-02-03 Vassil Vassilev , Aleksandr Efremov , Oksana Shadura

Automatic differentiation (AD) is conventionally understood as a family of distinct algorithms, rooted in two "modes" -- forward and reverse -- which are typically presented (and implemented) separately. Can there be only one? Following up…

Programming Languages · Computer Science 2022-12-07 Alexey Radul , Adam Paszke , Roy Frostig , Matthew Johnson , Dougal Maclaurin

The functional correspondence is a manual derivation technique transforming higher-order evaluators into the semantically equivalent abstract machines. The transformation consists of two well-known program transformations: translation to…

Programming Languages · Computer Science 2021-08-17 Maciej Buszka , Dariusz Biernacki

We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics. JAX MD includes a number of physics simulation environments, as well as interaction potentials and neural networks…

Computational Physics · Physics 2020-12-04 Samuel S. Schoenholz , Ekin D. Cubuk

For a real function, automatic differentiation is such a standard algorithm used to efficiently compute its gradient, that it is integrated in various neural network frameworks. However, despite the recent advances in using complex…

Machine Learning · Computer Science 2021-01-19 Chu Guo , Dario Poletti

In this paper we take a look at Automatic Differentiation through the eyes of Tensor and Operational Calculus. This work is best consumed as supplementary material for learning tensor and operational calculus by those already familiar with…

Symbolic Computation · Computer Science 2018-09-03 Žiga Sajovic

We develop a compositional approach for automatic and symbolic differentiation based on categorical constructions in functional analysis where derivatives are linear functions on abstract vectors rather than being limited to scalars,…

Programming Languages · Computer Science 2022-07-05 Martin Elsman , Fritz Henglein , Robin Kaarsgaard , Mikkel Kragh Mathiesen , Robert Schenck

Automatic differentiation plays a prominent role in scientific computing and in modern machine learning, often in the context of powerful programming systems. The relation of the various embodiments of automatic differentiation to the…

Programming Languages · Computer Science 2020-02-04 Martin Abadi , Gordon D. Plotkin

First-order automatic differentiation is a ubiquitous tool across statistics, machine learning, and computer science. Higher-order implementations of automatic differentiation, however, have yet to realize the same utility. In this paper I…

Computation · Statistics 2019-01-01 Michael Betancourt

We present an automated framework for constructing Taylor series expansions of rovibrational kinetic and potential energy operators for arbitrary molecules, internal coordinate systems, and molecular frame embedding conditions. Expressing…

Atomic and Molecular Clusters · Physics 2025-07-29 Andrey Yachmenev , Emil Vogt , Álvaro Fernández Corral , Yahya Saleh

We present jax-cosmo, a library for automatically differentiable cosmological theory calculations. It uses the JAX library, which has created a new coding ecosystem, especially in probabilistic programming. As well as batch acceleration,…

Cosmology and Nongalactic Astrophysics · Physics 2023-05-01 Jean-Eric Campagne , François Lanusse , Joe Zuntz , Alexandre Boucaud , Santiago Casas , Minas Karamanis , David Kirkby , Denise Lanzieri , Yin Li , Austin Peel

Stencil loops are a common motif in computations including convolutional neural networks, structured-mesh solvers for partial differential equations, and image processing. Stencil loops are easy to parallelise, and their fast execution is…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-07-08 Jan Hückelheim , Navjot Kukreja , Sri Hari Krishna Narayanan , Fabio Luporini , Gerard Gorman , Paul Hovland

We propose the use of automatic differentiation through the programming framework jax for accelerating a variety of analysis tasks throughout gravitational wave (GW) science. Firstly, we demonstrate that complete waveforms which cover the…

Instrumentation and Methods for Astrophysics · Physics 2023-02-13 Thomas D. P. Edwards , Kaze W. K. Wong , Kelvin K. H. Lam , Adam Coogan , Daniel Foreman-Mackey , Maximiliano Isi , Aaron Zimmerman

Reverse-mode differentiation is used for optimization, but it introduces references, which break the purity of the underlying programs, making them notoriously harder to optimize. We present a reverse-mode differentiation on a purely…

Programming Languages · Computer Science 2023-04-27 Mathieu Huot , Amir Shaikhha

This article provides an overview of some of the mathematical principles of Automatic Differentiation (AD). In particular, we summarise different descriptions of the Forward Mode of AD, like the matrix-vector product based approach, the…

Numerical Analysis · Mathematics 2016-07-07 Philipp H. W. Hoffmann

We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The result is a single expression that can represent both the…

Systems and Control · Electrical Eng. & Systems 2025-11-25 Chin-Yun Yu , György Fazekas

Automatic differentiation (AD) is an important family of algorithms which enables derivative based optimization. We show that AD can be simply implemented with effects and handlers by doing so in the Frank language. By considering how our…

Programming Languages · Computer Science 2021-01-21 Jesse Sigal

We describe efficient differentiation methods for computing Jacobians and gradients of a large class of matrix functions including the matrix logarithm $\log(A)$ and $p$-th roots $A^{\frac{1}{p}}$. We exploit contour integrals and conformal…

Computational Physics · Physics 2025-01-06 Tina Torabi , Timon S Gutleb , Christoph Ortner

We introduce Combinatory Homomorphic Automatic Differentiation (CHAD), a principled, pure, provably correct define-then-run method for performing forward- and reverse-mode automatic differentiation (AD) on programming languages with…

Programming Languages · Computer Science 2026-05-05 Matthijs Vákár , Tom Smeding