No article text was recorded for this version.
higher-order automatic differentiation
Version 1 of 173 papers141 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming
- Blog: Automatic differentiation in ML: Where we are and where we should be going
- Blog: AD in Fortran, Part 1: Design
- Blog: Collapsing Taylor Mode Automatic Differentiation
- Blog: Generalized Physics-Informed Learning through Language-Wide Differentiable Programming
- Blog: Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients
- Blog: Efficient Implementation of a Higher-Order Language with Built-In AD
- Blog: DLVM: A modern compiler infrastructure for deep learning systems
- Blog: Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming
- Blog: Tangent: Automatic Differentiation Using Source Code Transformation in Python
- Blog: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
- Blog: Efficient Differentiable Programming in a Functional Array-Processing Language
- Blog: ad-trait: A Fast and Flexible Automatic Differentiation Library in Rust
- Blog: Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming
- Blog: DiffSharp: Automatic Differentiation Library
- Blog: A Language and Compiler View on Differentiable Programming
- Blog: BACKpropagation through BACK substitution with a BACKslash
- Blog: Coarsening Optimization for Differentiable Programming
- Blog: An Introduction to Using Software Tools for Automatic Differentiation
- Blog: DiffTaichi: Differentiable Programming for Physical Simulation
- Blog: DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing
- Blog: Automatic differentiation in ML: Where we are and where we should be going
- Blog: Getting Started with ADOL-C
- Blog: 𝜆ₛ: computable semantics for differentiable programming with higher-order functions and datatypes
- Blog: Recursive SQL and GPU-support for in-database machine learning
- Blog: Efficient Differentiable Programming in a Functional Array-Processing Language
- Blog: DiffSharp: An AD Library for .NET Languages
- Blog: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
- Blog: A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning
- Blog: Bridging HPC Communities through the Julia Programming Language
- Blog: Automatic Differentiation of Algorithms for Machine Learning
- Blog: Fashionable Modelling with Flux
- Blog: Mini-symposium on automatic differentiation and its applications in the financial industry
- Blog: Part 2: Implementation via Prepreprocessor
- Blog: Relay: A New IR for Machine Learning Frameworks
- Blog: DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing
- Blog: Forward-Mode Automatic Differentiation in Julia
- Blog: Towards Adjoint and Directional Derivatives in FMI utilizing ADOL-C within OpenModelica
- Blog: JAX-XC: Exchange Correlation Functionals Library in Jax
- Blog: Probabilistic Programming with Programmable Variational Inference
- Blog: Automatic Differentiation of Algorithms for Machine Learning
- Blog: A mathematical model for automatic differentiation in machine learning
- Blog: The Stan Math Library: Reverse-Mode Automatic Differentiation in C++
- Blog: Divide-and-Conquer Checkpointing for Arbitrary Programs with No User Annotation
- Blog: DiffTaichi: Differentiable Programming for Physical Simulation
- Blog: Automatic Differentiation and Ubiquitous Adaptive Computing
- Blog: A Differential-form Pullback Programming Language for Higher-order Reverse-mode Automatic Differentiation
- Blog: On Correctness of Automatic Differentiation for Non-Differentiable Functions
- Blog: Automatic Differentiation in Machine Learning: a Survey
- Blog: Differential geometry and stochastic dynamics with deep learning numerics
- Blog: Computing Derivatives for PETSc Adjoint Solvers using Algorithmic Differentiation
- Blog: The automatic solution of partial differential equations using a global spectral method
- Blog: Automatic Functional Differentiation in JAX
- Blog: MOLPIPx: An end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
- Blog: Automatic differentiation in machine learning: a survey
- Blog: ωPAP Spaces: Reasoning Denotationally About Higher-Order, Recursive Probabilistic and Differentiable Programs
- Blog: On the Equivalence of Forward Mode Automatic Differentiation and Symbolic Differentiation
- Blog: Sparsity-Specific Code Optimization using Expression Trees
- Blog: Automatic Differentiation of Algorithmsfor Machine Learning
- Blog: PETSc TSAdjoint: A Discrete Adjoint ODE Solver for First-Order and Second-Order Sensitivity Analysis
Showing 60 of 73 papers.
History & citation
Current · Permanent link
- Correctness of Automatic Differentiation for Non-Differentiable Programs merged into this direction (83% overlap)
- This direction split from Compiler Integrated Automatic Differentiation and Differentiable Programming (90% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_higher_order_automatic_differentiation_7bec8c8c,
title = {higher-order automatic differentiation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/higher-order-automatic-differentiation/rdr_7bec8c8c544343e08bf4bbdad24e3068},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_higher_order_automatic_differentiation_7bec8c8c_v1,
title = {higher-order automatic differentiation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/higher-order-automatic-differentiation/rdr_7bec8c8c544343e08bf4bbdad24e3068/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}