English
Related papers

Related papers: Automatic Functional Differentiation in JAX

200 papers

We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and…

Mathematical Software · Computer Science 2018-06-07 Amir Shaikhha , Andrew Fitzgibbon , Dimitrios Vytiniotis , Simon Peyton Jones , Christoph Koch

Recent theoretical work on automatic differentiation (autodiff) has focused on characteristics such as correctness and efficiency while assuming that all derivatives are automatically generated by autodiff using program transformation, with…

Programming Languages · Computer Science 2024-08-15 Sam Estep

We present a simple functional programming language, called Dual PCF, that implements forward mode automatic differentiation using dual numbers in the framework of exact real number computation. The main new feature of this language is the…

Logic in Computer Science · Computer Science 2025-02-03 Pietro Di Gianantonio , Abbas Edalat , Ran Gutin

JAX is widely used in machine learning and scientific computing, the latter of which often relies on existing high-performance code that we would ideally like to incorporate into JAX. Reimplementing the existing code in JAX is often…

Instrumentation and Methods for Astrophysics · Physics 2024-06-28 Jakob Roth , Martin Reinecke , Gordian Edenhofer

We decompose reverse-mode automatic differentiation into (forward-mode) linearization followed by transposition. Doing so isolates the essential difference between forward- and reverse-mode AD, and simplifies their joint implementation. In…

Programming Languages · Computer Science 2021-05-21 Roy Frostig , Matthew J. Johnson , Dougal Maclaurin , Adam Paszke , Alexey Radul

Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program. This technique is considered as the de-facto standard for computing the differentiation in many machine learning and…

Programming Languages · Computer Science 2022-12-21 Amir Shaikhha , Mathieu Huot , Shabnam Ghasemirad , Andrew Fitzgibbon , Simon Peyton Jones , Dimitrios Vytiniotis

Autodiff refers to the core of the automatic differentiation systems developed in projects like JAX and Dex. Autodiff has recently been formalised in a linear typed calculus by Radul et al in arXiv:2204.10923. Although this formalisation…

Programming Languages · Computer Science 2025-10-29 Giulia Giusti , Michele Pagani

Among numerical libraries capable of computing gradient descent optimization, JAX stands out by offering more features, accelerated by an intermediate representation known as Jaxpr language. However, editing the Jaxpr code is not directly…

Programming Languages · Computer Science 2024-03-19 Pierrick Pochelu

We present ForwardDiff, a Julia package for forward-mode automatic differentiation (AD) featuring performance competitive with low-level languages like C++. Unlike recently developed AD tools in other popular high-level languages such as…

Mathematical Software · Computer Science 2016-07-28 Jarrett Revels , Miles Lubin , Theodore Papamarkou

We present the classical coordinate-free formalism for forward and backward mode ad in the real and complex setting. We show how to formally derive the forward and backward formulae for a number of matrix functions starting from basic…

Machine Learning · Computer Science 2022-07-14 Mario Lezcano-Casado

Derivative-based algorithms are ubiquitous in statistics, machine learning, and applied mathematics. Automatic differentiation offers an algorithmic way to efficiently evaluate these derivatives from computer programs that execute relevant…

Computation · Statistics 2022-03-01 Charles C. Margossian , Michael Betancourt

Automatic differentiation (autodiff) has revolutionized machine learning. It allows to express complex computations by composing elementary ones in creative ways and removes the burden of computing their derivatives by hand. More recently,…

We show that Automatic Differentiation (AD) operators can be provided in a dynamic language without sacrificing numeric performance. To achieve this, general forward and reverse AD functions are added to a simple high-level dynamic…

Programming Languages · Computer Science 2016-11-11 Jeffrey Mark Siskind , Barak A. Pearlmutter

We show how to define forward- and reverse-mode automatic differentiation source-code transformations or on a standard higher-order functional language. The transformations generate purely functional code, and they are principled in the…

Programming Languages · Computer Science 2021-01-25 Matthijs Vákár

Fractional-order differentiation has many characteristics different from integer-order differentiation. These characteristics can be applied to the optimization algorithms of artificial neural networks to obtain better results. However, due…

Machine Learning · Computer Science 2025-06-10 Xiaojun zhou , Chunna Zhao , Yaqun Huang , Chengli Zhou , Junjie Ye , Kemeng Xiang

Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in these libraries such as thresholding, Boolean logic, discrete…

Machine Learning · Computer Science 2026-03-11 Anselm Paulus , A. René Geist , Vít Musil , Sebastian Hoffmann , Onur Beker , Georg Martius

A critical step in topology optimization (TO) is finding sensitivities. Manual derivation and implementation of the sensitivities can be quite laborious and error-prone, especially for non-trivial objectives, constraints and material…

Mathematical Software · Computer Science 2022-01-31 Aaditya Chandrasekhar , Saketh Sridhara , Krishnan Suresh

Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT) in Python. It takes numeric functions written in a syntactic…

Mathematical Software · Computer Science 2017-11-09 Bart van Merriënboer , Alexander B. Wiltschko , Dan Moldovan

The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tools. In this work, we explore techniques from the field of…

Machine Learning · Computer Science 2018-09-27 Bart van Merriënboer , Dan Moldovan , Alexander B Wiltschko

Differentiable simulators are an emerging concept with applications in several fields, from reinforcement learning to optimal control. Their distinguishing feature is the ability to calculate analytic gradients with respect to the input…

Machine Learning · Computer Science 2021-11-10 Antonio Stanziola , Simon R. Arridge , Ben T. Cox , Bradley E. Treeby
‹ Prev 1 2 3 10 Next ›