Open kazewong opened 9 months ago
@kazewong will you use vanilla JAX to write a Hierarchical Bayesian model likelihood or any other ppl like NumPyro?
I think I am more inclined to use vanilla JAX and existing interfaces defined in Jim and flowMC instead of ppl like NumPyro, as users do not need to learn the specific ppl interface in order to understand the code. Also, vanilla Jax integrate with flowMC better.
The main focus of jim has been on individual event parameter estimation. One obvious extension that can leverage the infrastructure in jim and flowMC is the addition of population analysis, at least in the way that is commonly done with hierarchical Bayesian analysis.
This would require the following steps: