Daniel VandenHeuvel

Thanks very much for the input @TorkelE! I'll try to keep it in mind once I eventually get into the rework. Regarding Plots.jl: I've never used Plots.jl, so I probably...

@sebapersson: > But also agree it would also be nice to in addition to have the interface where people themselves can provide likelihood, gradient of the likelihood (autodiff directly on...

Sorry for the lack of progress here @sebapersson and @TorkelE. Still not sure I'll ever be able to find much time to get to these changes. I don't really have...

I'd never heard of DensityInterface before, but I'd be happy to look at any PR that includes support for it - that'd be great if you want to do that.

Hi @Moelf, thanks for your interest! I'm a bit confused on what you are suggesting here - probably because I'm too tired currently - but these links are quite interesting....

I see. I agree that being able to re-use other's code where possible would be a good idea. Regarding these features, as I mentioned I've not heard of them previously...

That shouldn't be too hard to implement. It might even be possible already if you set `param_ranges` appropriately with `threshold=-Inf`? Maybe you can check if that works. If it doesn't...

I have a working version of Farin's $C^1$ interpolant in https://github.com/DanielVandH/NaturalNeighbours.jl/tree/farin. Just needs to be properly tested.

Good references for Farin and Hiyoshi's smooth coordinates: https://link.springer.com/chapter/10.1007/978-3-540-24767-8_8 https://theses.hal.science/tel-00832487/PDF/these-flototto.pdf Also, for Hiyoshi's $C^k$ interpolant, https://www.sciencedirect.com/science/article/pii/S0925772101000529 is the initial reference (but Bobach's discussion of the implementation in his thesis and...

https://dl.acm.org/doi/abs/10.1504/IJCSE.2007.014460 another reference for Hiyoshi's $C^2$