English
Related papers

Related papers: A Hitchhiker's Guide to Automatic Differentiation

200 papers

A lift-and-permute scheme of alternating direction method of multipliers (ADMM) is proposed for linearly constrained convex programming. It contains not only the newly developed balanced augmented Lagrangian method and its dual-primal…

Optimization and Control · Mathematics 2022-03-31 Shiru Li , Yong Xia , Tao Zhang

We propose extensions to Fortran which integrate forward and reverse Automatic Differentiation (AD) directly into the programming model. Irrespective of implementation technology, embedding AD constructs directly into the language extends…

Programming Languages · Computer Science 2012-03-09 Alexey Radul , Barak A. Pearlmutter , Jeffrey Mark Siskind

We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based…

Machine Learning · Computer Science 2019-01-04 Bart van Merriënboer , Olivier Breuleux , Arnaud Bergeron , Pascal Lamblin

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is a special case within the general family of automatic…

Machine Learning · Computer Science 2022-02-18 Atılım Güneş Baydin , Barak A. Pearlmutter , Don Syme , Frank Wood , Philip Torr

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Yeongmin Kim , Sotiris Anagnostidis , Yuming Du , Edgar Schönfeld , Jonas Kohler , Markos Georgopoulos , Albert Pumarola , Ali Thabet , Artsiom Sanakoyeu

Automatic differentiation (AD) is a set of techniques that systematically applies the chain rule to compute the gradients of functions without requiring human intervention. Although the fundamentals of this technology were established…

Machine Learning · Computer Science 2025-09-03 Afif Boudaoud , Alexandru Calotoiu , Marcin Copik , Torsten Hoefler

Algorithmic differentiation (AD) allows exact computation of derivatives given only an implementation of an objective function. Although many AD tools are available, a proper and efficient implementation of AD methods is not…

Mathematical Software · Computer Science 2018-07-27 Filip Šrajer , Zuzana Kukelova , Andrew Fitzgibbon

We show how to apply forward and reverse mode Combinatory Homomorphic Automatic Differentiation (CHAD) to total functional programming languages with expressive type systems featuring the combination of - tuple types; - sum types; -…

Programming Languages · Computer Science 2023-11-13 Fernando Lucatelli Nunes , Matthijs Vákár

Reverse-mode automatic differentiation (AD) suffers from the issue of having too much space overhead to trace back intermediate computational states for back-propagation. The traditional method to trace back states is called checkpointing…

Programming Languages · Computer Science 2021-02-02 Jin-Guo Liu , Taine Zhao

Many problems in Physics and Chemistry are formulated as the minimization of a functional. Therefore, methods for solving these problems typically require differentiating maps whose input and/or output are functions -- commonly referred to…

Mathematical Software · Computer Science 2024-06-25 Kangbo Li , Anil Damle

The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters. Recent advances in reverse-mode automatic differentiation allow for optimizing hyperparameters with gradients. The standard way…

Machine Learning · Computer Science 2016-04-07 Jie Fu , Hongyin Luo , Jiashi Feng , Kian Hsiang Low , Tat-Seng Chua

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

Derivatives play a critical role in computational statistics, examples being Bayesian inference using Hamiltonian Monte Carlo sampling and the training of neural networks. Automatic differentiation is a powerful tool to automate the…

Mathematical Software · Computer Science 2019-03-27 Charles C. Margossian

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 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 propose a new method for computing Dynamic Mode Decomposition (DMD) evolution matrices, which we use to analyze dynamical systems. Unlike the majority of existing methods, our approach is based on a variational formulation consisting of…

Numerical Analysis · Mathematics 2019-05-24 Omri Azencot , Wotao Yin , Andrea Bertozzi

In this review we present hyper-dual numbers as a tool for the automatic differentiation of computer programs via operator overloading. We start with a motivational introduction into the ideas of algorithmic differentiation. Then we…

Mathematical Software · Computer Science 2018-01-16 Martin Neuenhofen

Automatic differentiation has become an important tool for optimization problems in computational science, and it has been applied to the Hartree-Fock method. Although the reverse-mode automatic differentiation is more efficient than the…

Chemical Physics · Physics 2022-11-28 Naruki Yoshikawa , Masato Sumita

Computing partial differential equation (PDE) operators via nested backpropagation is expensive, yet popular, and severely restricts their utility for scientific machine learning. Recent advances, like the forward Laplacian and randomizing…

Machine Learning · Computer Science 2025-11-25 Felix Dangel , Tim Siebert , Marius Zeinhofer , Andrea Walther

We show how forward-mode automatic differentiation (AD) can be employed within larger reverse-mode computations to dynamically differentiate broadcast operations in a GPU-friendly manner. Our technique fully exploits the broadcast…

Mathematical Software · Computer Science 2018-10-26 Jarrett Revels , Tim Besard , Valentin Churavy , Bjorn De Sutter , Juan Pablo Vielma