English
Related papers

Related papers: AD for an Array Language with Nested Parallelism

200 papers

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

Recent work has shown that forward- and reverse- mode automatic differentiation (AD) over the reals is almost always correct in a mathematically precise sense. However, actual programs work with machine-representable numbers (e.g.,…

Machine Learning · Computer Science 2023-06-07 Wonyeol Lee , Sejun Park , Alex Aiken

Classical reverse-mode automatic differentiation (AD) imposes only a small constant-factor overhead in operation count over the original computation, but has storage requirements that grow, in the worst case, in proportion to the time…

Programming Languages · Computer Science 2018-07-18 Jeffrey Mark Siskind , Barak A. Pearlmutter

The application of operator overloading algorithmic differentiation (AD) to computer programs in order to compute the derivative is quite common. But, the replacement of the underlying computational floating point type with the specialized…

Mathematical Software · Computer Science 2026-02-18 Max Sagebaum , Nicolas R. Gauger

An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been proposed to improve the DNN accuracy but also consume…

Machine Learning · Computer Science 2022-09-23 Cong Guo , Yuxian Qiu , Jingwen Leng , Chen Zhang , Ying Cao , Quanlu Zhang , Yunxin Liu , Fan Yang , Minyi Guo

Machine learning and neural network models in particular have been improving the state of the art performance on many artificial intelligence related tasks. Neural network models are typically implemented using frameworks that perform…

Machine Learning · Computer Science 2021-10-18 Davan Harrison

Automatic Differentiation (AD) is instrumental for science and industry. It is a tool to evaluate the derivative of a function specified through a computer program. The range of AD application domain spans from Machine Learning to Robotics…

Mathematical Software · Computer Science 2023-03-01 Ioana Ifrim , Vassil Vassilev , David J Lange

The deep learning community has devised a diverse set of methods to make gradient optimization, using large datasets, of large and highly complex models with deeply cascaded nonlinearities, practical. Taken as a whole, these methods…

Machine Learning · Computer Science 2016-11-14 Atılım Güneş Baydin , Barak A. Pearlmutter , Jeffrey Mark Siskind

We propose a methodology for automatic generation of divide-and-conquer parallel implementations of sequential nested loops. We focus on a class of loops that traverse read-only multidimensional collections (lists or arrays) and compute a…

Programming Languages · Computer Science 2019-04-03 Azadeh Farzan , Victor Nicolet

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 2020-04-02 Mathieu Huot , Sam Staton , Matthijs Vákár

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

A large class of non-smooth practical optimization problems can be written as minimization of a sum of smooth and partly smooth functions. We examine such structured problems which also depend on a parameter vector and study the problem of…

Optimization and Control · Mathematics 2024-10-28 Sheheryar Mehmood , Peter Ochs

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

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

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

The last improvements in programming languages, programming models, and frameworks have focused on abstracting the users from many programming issues. Among others, recent programming frameworks include simpler syntax, automatic memory…

Programming Languages · Computer Science 2018-10-29 Cristian Ramon-Cortes , Ramon Amela , Jorge Ejarque , Philippe Clauss , Rosa M. Badia

We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. Our system evaluates derivatives using per-element…

Graphics · Computer Science 2026-02-03 Ahmed H. Mahmoud , Rahul Goel , Jonathan Ragan-Kelley , Justin Solomon

Online synaptic plasticity rules derived from gradient descent achieve high accuracy on a wide range of practical tasks. However, their software implementation often requires tediously hand-derived gradients or using gradient…

Neural and Evolutionary Computing · Computer Science 2025-01-22 Jamie Lohoff , Anil Kaya , Florian Assmuth , Emre Neftci

This paper presents a new functionality of the Automatic Differentiation (AD) tool Tapenade. Tapenade generates adjoint codes which are widely used for optimization or inverse problems. Unfortunately, for large applications the adjoint code…

Data Structures and Algorithms · Computer Science 2007-05-23 Laurent Hascoet , Mauricio Araya-Polo

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