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 (gradients, Jacobians, Hessians and more)
• In-place and out-of-place differentiation
• Preparation mechanism (e.g. to create a config or tape)
• Built-in sparsity handling
• Thorough validation on standard inputs and outputs (numbers, vectors, matrices)
• Testing and benchmarking utilities accessible to users with DifferentiationInterfaceTest

Compatibility

We support all of the backends defined by ADTypes.jl v1.0:

• ChainRulesCore.jl
• Diffractor.jl
• Enzyme.jl
• FastDifferentiation.jl
• FiniteDiff.jl
• FiniteDifferences.jl
• ForwardDiff.jl
• PolyesterForwardDiff.jl
• ReverseDiff.jl
• Symbolics.jl
• Tapir.jl
• Tracker.jl
• Zygote.jl

Installation

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

using Pkg

Pkg.add("DifferentiationInterface")

To install the development version, run this instead:

using Pkg

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

Example

using DifferentiationInterface
import ForwardDiff, Enzyme, Zygote  # AD backends you want to use 

f(x) = sum(abs2, x)

x = [1.0, 2.0]

value_and_gradient(f, AutoForwardDiff(), x) # returns (5.0, [2.0, 4.0]) with ForwardDiff.jl
value_and_gradient(f, AutoEnzyme(),      x) # returns (5.0, [2.0, 4.0]) with Enzyme.jl
value_and_gradient(f, AutoZygote(),      x) # returns (5.0, [2.0, 4.0]) with Zygote.jl

To improve your performance by up to several orders of magnitude compared to this example, take a look at the DifferentiationInterface tutorial and its section on operator preparation.

Related packages

• AbstractDifferentiation.jl is the original inspiration for DifferentiationInterface.jl.
• AutoDiffOperators.jl is an attempt to bridge ADTypes.jl with AbstractDifferentiation.jl.