[ChrisRackauckas]

> namely that gradients are not all that helpful when your optimization landscape is insanely non-linear

Did you try multiple shooting? https://diffeqflux.sciml.ai/dev/examples/multiple_shooting/

I want to restructure the docs because I have come to think that any non-trivial fitting problem requires multiple shooting in order to be stable. Otherwise the loss becomes dominated by "loss values calculated beyond where the simulation has already fallen off". So I'd like to dig into some of the non-fitting examples and see if this or some other tricks are the right answer.