DifferentiationInterface

Package	Docs
DifferentiationInterface
DifferentiationInterfaceTest

An interface to various automatic differentiation (AD) backends in Julia.

Goal

This package provides a backend-agnostic syntax to differentiate functions of the following types:

one-argument functions (allocating): f(x) = y
two-argument functions (mutating): f!(y, x) = nothing

Features

First- and second-order operators
In-place and out-of-place differentiation
Preparation mechanism (e.g. to create a config or tape)
Thorough validation on standard inputs and outputs (numbers, vectors, matrices)
Testing and benchmarking utilities accessible to users with DifferentiationInterfaceTest

Compatibility

We support most of the backends defined by ADTypes.jl:

Backend	Object
ChainRulesCore.jl	`AutoChainRules(; ruleconfig)`
Diffractor.jl	`AutoDiffractor()`
Enzyme.jl	`AutoEnzyme(; mode=Enzyme.Forward)`, `AutoEnzyme(; mode=Enzyme.Reverse)`
FiniteDiff.jl	`AutoFiniteDiff()`
FiniteDifferences.jl	`AutoFiniteDifferences(; fdm)`
ForwardDiff.jl	`AutoForwardDiff()`
PolyesterForwardDiff.jl	`AutoPolyesterForwardDiff(; chunksize)`
ReverseDiff.jl	`AutoReverseDiff()`
SparseDiffTools.jl	`AutoSparseForwardDiff()`, `AutoSparseFiniteDiff()`
Tracker.jl	`AutoTracker()`
Zygote.jl	`AutoZygote()`

We also provide some experimental backends ourselves:

Backend	Object
FastDifferentiation.jl	`AutoFastDifferentiation()`, `AutoSparseFastDifferentiation()`
Symbolics.jl	`AutoSymbolics()`, `AutoSparseSymbolics()`
Tapir.jl	`AutoTapir()`

Installation

To install the stable version of the package, run the following code in a Julia REPL:

julia> using Pkg

julia> Pkg.add("DifferentiationInterface")

To install the development version, run this instead:

julia> using Pkg

julia> Pkg.add(
        url="https://github.com/gdalle/DifferentiationInterface.jl",
        subdir="DifferentiationInterface"
    )

Example

julia> import ForwardDiff

julia> using DifferentiationInterface

julia> backend = AutoForwardDiff();

julia> f(x) = sum(abs2, x);

julia> value_and_gradient(f, backend, [1., 2., 3.])
(14.0, [2.0, 4.0, 6.0])