When reading the SciMLSensitivity docs I am somewhat surprised that Enzyme.jl is only mentioned as an option for JVPs. Why is doing e.g. end to end gradient computations with Enzyme (e.g. much like ForwardDiff.jl does) not a more prominent option? I suspect that this might not be very user friendl…

[image] nrontsis: Why is doing e.g. end to end gradient computations with Enzyme (e.g. much like ForwardDiff.jl does) not a more prominent option? It only supports a subset of Julia which doesn’t include the ODE solvers at this time. But it’s growing, and that’s one our goals.

End-to-end gradients with Enzyme when training ODE parameters

General Usage

ChrisRackauckas October 21, 2022, 5:19pm 2

It only supports a subset of Julia which doesn’t include the ODE solvers at this time. But it’s growing, and that’s one our goals.

1 Like

Topic		Replies	Views
Reliability of Enzyme.jl General Usage question , diffeq , autodiff	11	2121	October 23, 2022
Using Enzyme with DE.jl General Usage ad , differentialequation , enzyme	3	757	March 10, 2023
Any faster way of computing small gradients? Performance zygote , forwarddiff , symbolics , autodiff	21	2084	August 11, 2022
Open discussion on the state of differentiable physics in Julia Community sciml , ad , dp	9	6940	August 15, 2022
Optim: What optimiser is best if your gradient computation is slow? Optimization (Mathematical) optim	13	3211	August 22, 2017

End-to-end gradients with Enzyme when training ODE parameters

Related topics