And what I’m saying is that based on the code you provided, you should not expect it to work in general, because differentiating through noise is undefined behavior in the majority of cases
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Types and gradients, including Forward.gradient | 20 | 5580 | December 20, 2016 | |
| New to julia: Convolution and juliadiff | 19 | 6377 | August 21, 2017 | |
| Correct sensealg for an ensemble problem of stochastic UODEs with diagonal noise | 17 | 982 | November 23, 2020 | |
| Optim: What optimiser is best if your gradient computation is slow? | 13 | 3198 | August 22, 2017 | |
| Any faster way of computing small gradients? | 21 | 2074 | August 11, 2022 |