I messed around with your code and found the same thing. I have a feeling that you’re experiencing the same issue that Michael Betancourt talks about in this blog post. See this thread for some advice. Long story short, priors are important (but especially with GPs)!
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| GP regularization effect | 6 | 536 | January 11, 2021 | |
| Latent gaussian process prediction problem | 3 | 1149 | January 25, 2022 | |
| Computer model calibration using a Gaussian Process: From stan to pymc | 10 | 773 | June 22, 2023 | |
| Possible ways to speed up spatio-temporal GP modeling | 16 | 935 | October 22, 2023 | |
| GP Modelling Advice | 1 | 397 | May 5, 2021 |