So we started a new huge project for which we aim to use Optimization.jl with Enzyme.jl as AD backend. We came up with some early prototypes and plugged that into Optimization.jl, unfortunately not very succesful (It seems to be the case that the closures we need to provide to Optimization.jl intro…

For arrays in reverse mode, you should not use Active(x), but rather create a zero shadow of memory for it to store the derivatives into. In other words, something like: dx = zeros(4) autodiff(Reverse,vec_input_target,Active,Duplicated(x, dx)) # result is in dx

Autodiff of vector inputs with Enzyme.jl (and possibly Optimization.jl)

Specific Domains Optimization (Mathematical)

wsmoses August 16, 2023, 8:54am 10

Yeah post a bug report with a MWE if you can

Topic		Replies	Views
Reliability of Enzyme.jl General Usage question , diffeq , autodiff	11	2114	October 23, 2022
Error using Enzyme to autodiff wrt Flux neural net parameters General Usage question	10	264	January 15, 2025
AD with Enzyme.jl: "task switch not allowed from inside staged nor pure functions" Optimization (Mathematical)	3	295	November 30, 2023
What's the state of Automatic Differentiation in Julia January 2023? General Usage autodiff	41	12431	June 21, 2024
Enzyme with Const() on a vector throws an error Optimization (Mathematical) autodiff , enzyme	20	537	April 10, 2025

Autodiff of vector inputs with Enzyme.jl (and possibly Optimization.jl)

Related topics