Hi! I think that you will have problems using the absolute value too. The main issue is related to the fact that no internal variable inside the function can be complex.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Fitting a complex model with a large dataset: chain contains only diverging samples | 5 | 1276 | December 12, 2019 | |
| Theano.scan and pm.Model() are strangely incompatible | 9 | 1843 | May 21, 2019 | |
| Complex model samples very slowly - wondering about possible improvements | 5 | 752 | July 31, 2020 | |
| Trouble with Initilization and Posterior Sampling | 13 | 2225 | June 15, 2018 | |
| Sampling crashes with "The derivative of RV [whatever] is zero" when using a custom likelihood defined with pm.Potential | 4 | 4028 | February 23, 2019 |