English
Related papers

Related papers: Parallel Dual-Numbers Reverse AD

200 papers

In the field of high-dimensional data analysis, modeling methods based on quantile loss function are highly regarded due to their ability to provide a comprehensive statistical perspective and effective handling of heterogeneous data. In…

Computation · Statistics 2025-01-14 Xiaofei Wu , Dingzi Guo , Rongmei Liang , Zhimin Zhang

Algorithmic differentiation (AD) tools allow to obtain gradient information of a continuously differentiable objective function in a computationally cheap way using the so-called backward mode. It is common practice to use the same tools…

Optimization and Control · Mathematics 2024-12-02 Lukas Baumgärtner , Franz Bethke

Forward Automatic Differentiation (AD) is a technique for augmenting programs to compute derivatives. The essence of Forward AD is to attach perturbations to each number, and propagate these through the computation. When derivatives are…

Symbolic Computation · Computer Science 2019-09-23 Oleksandr Manzyuk , Barak A. Pearlmutter , Alexey Andreyevich Radul , David R. Rush , Jeffrey Mark Siskind

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD…

Machine Learning · Computer Science 2021-03-16 Deniz Oktay , Nick McGreivy , Joshua Aduol , Alex Beatson , Ryan P. Adams

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

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 forward-mode Automatic Differentiation (AD) for languages with sources of partiality such as partial operations, lazy conditionals on real parameters, iteration, and term and type recursion. We…

Programming Languages · Computer Science 2024-05-28 Matthijs Vákár

Automatic differentiation (AD) aims to compute derivatives of user-defined functions, but in Turing-complete languages, this simple specification does not fully capture AD's behavior: AD sometimes disagrees with the true derivative of a…

Programming Languages · Computer Science 2021-12-07 Alexander K. Lew , Mathieu Huot , Vikash K. Mansinghka

We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm such as stochastic gradient descent. These procedures mirror…

Machine Learning · Statistics 2017-12-13 Luca Franceschi , Michele Donini , Paolo Frasconi , Massimiliano Pontil

Dual numbers are a well-established tool for computing derivatives and constitute the basis of forward-mode automatic differentiation. While the theoretical framework for computing derivatives of arbitrary order is well understood,…

Numerical Analysis · Mathematics 2026-02-06 F. Peñuñuri , K. B. Cantún-Avila , R. Peón-Escalante

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

Automatic differentiation, also known as backpropagation, AD, autodiff, or algorithmic differentiation, is a popular technique for computing derivatives of computer programs accurately and efficiently. Sometimes, however, the derivatives…

Numerical Analysis · Mathematics 2023-05-15 Jan Hückelheim , Harshitha Menon , William Moses , Bruce Christianson , Paul Hovland , Laurent Hascoët

This paper presents our work toward correct and efficient automatic differentiation of OpenMP parallel worksharing loops in forward and reverse mode. Automatic differentiation is a method to obtain gradients of numerical programs, which are…

Mathematical Software · Computer Science 2021-11-04 Jan Hückelheim , Laurent Hascoët

There are several AD tools available, which all implement different strategies for the reverse mode of AD. The major strategies are primal value taping (implemented e.g. by ADOL-c) and Jacobi taping (implemented e.g. by adept and dco/c++).…

Mathematical Software · Computer Science 2017-09-22 Max Sagebaum , Tim Albring , Nicolas R. Gauger

We describe an implementation of the Farfel Fortran AD extensions. These extensions integrate forward and reverse AD directly into the programming model, with attendant benefits to flexibility, modularity, and ease of use. The…

Programming Languages · Computer Science 2016-02-09 Alexey Radul , Barak A. Pearlmutter , Jeffrey Mark Siskind

In arbitrary-order language models, it is an open question how to sample tokens in parallel from the correct joint distribution. With discrete diffusion models, the more tokens they generate in parallel, the less their predicted…

Machine Learning · Computer Science 2025-04-30 Gabe Guo , Stefano Ermon

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

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

We propose both serial and parallel proximal (linearized) alternating direction method of multipliers (ADMM) algorithms for training residual neural networks. In contrast to backpropagation-based approaches, our methods inherently mitigate…

Machine Learning · Computer Science 2025-04-01 Jintao Xu , Yifei Li , Wenxun Xing

Algorithmic differentiation (AD) is a set of techniques that provide partial derivatives of computer-implemented functions. Such a function can be supplied to state-of-the-art AD tools via its source code, or via an intermediate…

Mathematical Software · Computer Science 2023-07-10 Max Aehle , Johannes Blühdorn , Max Sagebaum , Nicolas R. Gauger