[longemen3000]

I feel called out on the academic part hahaah. I simply want to code state of the art (thermodynamic) models, and at least julia helps by providing easy testing and publishing infraestructure. but obviously we can't compete with a corporation in code quality (we are trying!)

Unrelated, but for small sizes, i really prefer to use forward mode in julia (Via ForwardDiff.jl) instead of Zygote. the overhead of reverse ADing over an arbitrary function with mutation is not worth it.

[tagrun]

In the context of neural networks with differential equations (which appears to be the original poster's field), the trade-off depends: https://diffeqflux.sciml.ai/dev/ControllingAdjoints/

[longemen3000]

yeah, my systems are really small in comparison (1-20) but with higher order derivatives (up to 4th order), so reverse AD is not the best in that regard