English
Related papers

Related papers: The simple essence of automatic differentiation

200 papers

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

Building on the observation that reverse-mode automatic differentiation (AD) -- a generalisation of backpropagation -- can naturally be expressed as pullbacks of differential 1-forms, we design a simple higher-order programming language…

Programming Languages · Computer Science 2020-02-20 Carol Mak , Luke Ong

Algorithmic differentiation (AD) has become increasingly capable and straightforward to use. However, AD is inefficient when applied directly to solvers, a feature of most engineering analyses. We can leverage implicit differentiation to…

Optimization and Control · Mathematics 2023-06-28 Andrew Ning , Taylor McDonnell

We present a technique for applying (forward and) reverse-mode automatic differentiation (AD) on a non-recursive second-order functional array language that supports nested parallelism and is primarily aimed at efficient GPU execution. The…

Programming Languages · Computer Science 2022-02-22 Robert Schenck , Ola Rønning , Troels Henriksen , Cosmin E. Oancea

In this paper we introduce DiffSharp, an automatic differentiation (AD) library designed with machine learning in mind. AD is a family of techniques that evaluate derivatives at machine precision with only a small constant factor of…

Mathematical Software · Computer Science 2015-11-30 Atilim Gunes Baydin , Barak A. Pearlmutter , Jeffrey Mark Siskind

Clinical diagnosis is a highly specialized discipline requiring both domain expertise and strict adherence to rigorous guidelines. While current AI-driven medical research predominantly focuses on knowledge graphs or natural text…

Machine Learning · Computer Science 2025-12-12 Haolin Li , Tianjie Dai , Zhe Chen , Siyuan Du , Jiangchao Yao , Ya Zhang , Yanfeng Wang

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

Where dual-numbers forward-mode automatic differentiation (AD) pairs each scalar value with its tangent value, dual-numbers reverse-mode AD attempts to achieve reverse AD using a similarly simple idea: by pairing each scalar value with a…

Programming Languages · Computer Science 2025-03-04 Tom Smeding , Matthijs Vákár

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

Backpropagation is a classic automatic differentiation algorithm computing the gradient of functions specified by a certain class of simple, first-order programs, called computational graphs. It is a fundamental tool in several fields, most…

Logic in Computer Science · Computer Science 2019-11-07 Alois Brunel , Damiano Mazza , Michele Pagani

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

Many engineering problems involve learning hidden dynamics from indirect observations, where the physical processes are described by systems of partial differential equations (PDE). Gradient-based optimization methods are considered…

Numerical Analysis · Mathematics 2019-12-17 Kailai Xu , Dongzhuo Li , Eric Darve , Jerry M. Harris

The standard dual-numbers construction works well for forward-mode automatic differentiation (AD) and is attractive due to its simplicity; recently, it also has been adapted to reverse-mode AD, but practical performance, especially on array…

Programming Languages · Computer Science 2025-07-18 Tom Smeding , Mikołaj Konarski , Simon Peyton Jones , Andrew Fitzgibbon

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

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

Where dual-numbers forward-mode automatic differentiation (AD) pairs each scalar value with its tangent derivative, dual-numbers /reverse-mode/ AD attempts to achieve reverse AD using a similarly simple idea: by pairing each scalar value…

Programming Languages · Computer Science 2022-05-24 Tom Smeding , Matthijs Vákár

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 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

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization…

Machine Learning · Computer Science 2024-12-10 Yao Lyu , Xiangteng Zhang , Shengbo Eben Li , Jingliang Duan , Letian Tao , Qing Xu , Lei He , Keqiang Li

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