English
Related papers

Related papers: A tutorial on automatic differentiation with compl…

200 papers

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

Diffusive representations of fractional derivatives have proven to be useful tools in the construction of fast and memory efficient numerical methods for solving fractional differential equations. A common challenge in many of the known…

Numerical Analysis · Mathematics 2022-04-11 Kai Diethelm

The Cheap Gradient Principle (Griewank 2008) --- the computational cost of computing the gradient of a scalar-valued function is nearly the same (often within a factor of $5$) as that of simply computing the function itself --- is of…

Optimization and Control · Mathematics 2019-01-15 Sham Kakade , Jason D. Lee

Differentiation is a cornerstone of computing and data analysis in every discipline of science and engineering. Indeed, most fundamental physics laws are expressed as relationships between derivatives in space and time. However, derivatives…

Numerical Analysis · Mathematics 2026-03-10 Pavel Komarov , Floris van Breugel , J. Nathan Kutz

We show that a particular form of target propagation, i.e., relying on learned inverses of each layer, which is differential, i.e., where the target is a small perturbation of the forward propagation, gives rise to an update rule which…

Machine Learning · Computer Science 2020-08-19 Yoshua Bengio

We present a simple yet powerful framework for solving inverse problems by leveraging automatic differentiation. Our method is broadly applicable whenever a smooth cost function can be defined near the true solution, and a numerical…

Disordered Systems and Neural Networks · Physics 2025-06-17 Koji Kobayashi , Tomi Ohtsuki

In the context of the optimization of Deep Neural Networks, we propose to rescale the learning rate using a new technique of automatic differentiation. This technique relies on the computation of the {\em curvature}, a second order…

Neural and Evolutionary Computing · Computer Science 2022-10-27 Frédéric de Gournay , Alban Gossard

We discuss the functional lazy techniques in generation and handling of arbitrarily long sequences of derivatives of numerical expressions in one ``variable''; the domain to which the paper belongs is usually nicknamed ``Automatic…

Programming Languages · Computer Science 2025-01-24 Jerzy Karczmarczuk

Leibniz's rule for the $n$-th derivative of a product is a very well known and extremely useful formula. In this article, we introduce an analogous explicit formula for the $n$-th derivative of a quotient of two functions. Later, we use…

Classical Analysis and ODEs · Mathematics 2023-04-18 Roudy El Haddad

Performant numerical solving of differential equations is required for large-scale scientific modeling. In this manuscript we focus on two questions: (1) how can researchers empirically verify theoretical advances and consistently compare…

Software Engineering · Computer Science 2018-07-18 Christopher Rackauckas , Qing Nie

One of the great triumphs in the history of numerical methods was the discovery of the Conjugate Gradient (CG) algorithm. It could solve a symmetric positive-definite system of linear equations of dimension N in exactly N steps. As many…

Data Structures and Algorithms · Computer Science 2016-09-01 Muhammad Ali Raza Anjum

As more and more multiphysics effects are entering the field of CFD simulations, this raises the question how they can be accurately captured in gradient computations for shape optimization. The latter has been successfully enriched over…

Computational Physics · Physics 2018-11-02 Ole Burghardt , Nicolas R. Gauger

The auto differentiable simulation is a type of simulation that outputs of the simulation include not only the simulation result itself, but also their derivatives with respect to various input parameters. It provides an efficient method to…

Computational Physics · Physics 2025-12-01 Ji Qianga , Yue Hao , Allen Qiang , Jinyu Wan

There are many approaches for training decision trees. This work introduces a novel gradient-based method for constructing decision trees that optimize arbitrary differentiable loss functions, overcoming the limitations of heuristic…

Machine Learning · Computer Science 2025-03-25 Andrei V. Konstantinov , Lev V. Utkin

Differential calculus on discrete spaces is studied in the manner of non-commutative geometry by representing the differential calculus by an operator algebra on a suitable Krein space. The discrete analogue of a (pseudo-)Riemannian metric…

Mathematical Physics · Physics 2007-05-23 Eric Forgy , Urs Schreiber

We investigate the automatic differentiation of dominant eigensolver where only a small proportion of eigenvalues and corresponding eigenvectors are obtained. Backpropagation through the dominant eigensolver involves solving certain…

Strongly Correlated Electrons · Physics 2020-06-15 Hao Xie , Jin-Guo Liu , Lei Wang

The reverse derivative is a fundamental operation in machine learning and automatic differentiation. This paper gives a direct axiomatization of a category with a reverse derivative operation, in a similar style to that given by Cartesian…

Logic in Computer Science · Computer Science 2019-10-17 Robin Cockett , Geoffrey Cruttwell , Jonathan Gallagher , Jean-Simon Pacaud Lemay , Benjamin MacAdam , Gordon Plotkin , Dorette Pronk

The categorical models of the differential lambda-calculus are additive categories because of the Leibniz rule which requires the summation of two expressions. This means that, as far as the differential lambda-calculus and differential…

Logic in Computer Science · Computer Science 2021-11-30 Thomas Ehrhard

Modelers use automatic differentiation (AD) of computation graphs to implement complex Deep Learning models without defining gradient computations. Stochastic AD extends AD to stochastic computation graphs with sampling steps, which arise…

Machine Learning · Statistics 2021-10-27 Emile van Krieken , Jakub M. Tomczak , Annette ten Teije

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