search

htjb / margarine

Code to replicate posterior probability distributions with bijectors/KDEs and perform marginal KL/bayesian dimensionality calculations.
MIT License
13 stars 8 forks source link

Master branch assumes uniform prior #4

Closed htjb closed 1 year ago

htjb commented 2 years ago

The code on the master branch currently assumes that the prior is uniform but this is very limiting.

An easy extension is implemented in error_analysis when prior samples can be provided, prior density estimators trained and marginal Bayesian stats subsequently calculated. Needs testing and merging.

htjb commented 1 year ago

Partially solved in master for nuisance-free likelihood calculations but need to merge error_anlaysis branch.

htjb commented 1 year ago

Solved with #6