Matthew Griffiths

I'm not reproducing these issues. It looks like there's an issue with the bounds calculation though, if the bounds are infinite this could cause the issue. So perhaps there should...

Is it clearer to represent the Priors as so `GaussianPrior(mean = 50.0, sigma = 30.0)`?

A potential abuse of notation but you could do something like this for the Analysis Factors ``` AnalysisFactor0: gaussian( centre ~ GaussianPrior(mean = 50.0, sigma = 30.0) normalization ~ GaussianPrior(mean...

I presume that there's a tech debt reason behind not using something like TOML or YAML to represent this information?

Hmm, the Hessian here has become indefinite, so its inverse isn't finite. We probably need some code to force the Hessian to be positive-definite. The challenge with that is that...

Could either create a modified `full_diag_update` routine - https://github.com/rhayes777/PyAutoFit/blob/5721dc8585ce2da80f90f7b18ece6dfd6f181f2e/autofit/graphical/laplace/newton.py#L216 - that enforces PD on the updated Hessian or create a `posdef_hessian_direction` function that forces the Hessian to be positive definite.

I had set up some code for visualising `FactorGraph`s - https://github.com/rhayes777/PyAutoFit/blob/ae791e2704cab52bad36d868033fd24512333e1d/autofit/graphical/factor_graphs/graph.py#L344-L485

Yeah, perhaps something like pyvis could be nice - https://towardsdatascience.com/pyvis-visualize-interactive-network-graphs-in-python-77e059791f01