andrschl

I would have a first implementation of an interpolating adjoint method for DDEs with constant delays. The code can be found here: [https://github.com/andrschl/dde_adjoint_method](https://github.com/andrschl/dde_adjoint_method) However, I am sure the structure and...

@ChrisRackauckas, @devmotion Apparently, performance and memory usage of my approach become terrible for increasing number of sample times. I assume this is because of the adjoint state history which I...

Ok, great. This should simplify things a lot and then we can also add discontinuities coming from non-smoothness at the initial point.

Adding the callbacks improved things a lot :D The code looks much simpler and runtime and memory usage are better than for ReverseDiffAdjoint() in my example. I pushed the code...

Thanks for the reference to the code and sorry for my late reply. I am currently adding some things such as a continuous loss with delays. I will give it...

Ok, yeah makes sense. However, I am still not sure whether the DDE adjoint is actually correct. In my tests, there is an average mismatch compared to the ReverseDiffAdjoint of...

Thanks for your answer and sorry for my late one. Well, for the gradients I just defined the functions, ``` # we need the functions fi: xi->f(x0,...,xi,...,xk) ndelays=length(lags) fs =...

Ok, I see. Thanks. Yes, as I am working with neural networks I did not really need that, but it shouldn't be a problem to add it. I am currently...

> It's not a good idea to do that, even on ODEs. It's numerically unstable to not have the error control on the integral term. That doesn't mean there aren't...

OK, great. Thanks for the link to the issue. But in this case it might be better to go with the QuadratureAdjoint until this is solved. i.e. calculating a dense...