Jan
Jan
I think you need to sum the log probs over the second dimension: your prior has four independent dimensions, but the final log prob should be the joint over all...
That's great, thanks a lot @plcrodrigues for sharing this example. I think it is ideal to have such a simple and general example! We have been thinking about adding more...
idea: when doing the entire SBI in transformed space, then outside posterior sampling will not be an issue anymore. we would do this by default, and when the user sets...
Hi @flo-schu let's call your input $Y$. If $Y$ is fixed for all parameters, it should be no problem. You would learn an emulator for `simulator(theta, input=Y)`, i.e., train NLE...
I see, your `Y`s are like experimental conditions, deterministic but different for different trials? I would then train the emulator to emulate `Y` as well, e.g., the emulator takes inputs...
addition: would be great to add log transforms for bounded data, e.g., for reaction time data in NLE.
this seems to be solved. Feel free to re-open if needed.
yes, it could used in an extended version the SBC tutorial. Inge (@lehcni) is working on the implementation of the local coverage tests.
thanks! No, I don't think we have this option. Have you tried increasing sampling speed using the `slice_np_vectorized` option, or `slice_np` with `num_workers>1`?
Actually, I think we cannot handle multi-dimensional parameters yet, e.g., no matrices. If a user wants to define a prior over a matrix she has to implement a prior wrapper...