Michael Betancourt
Michael Betancourt
I don't describe the HPD at all because it's not a well-defined probabilistic object, i.e. it can't be defined as expectation values (or differences of expectation values in the case...
To be honest 2.5% and 97.5% require way too many effective samples to be reasonable defaults. If you need 100 effective samples below the 2.5% quantile to estimate it with...
Given how obscure these functions will be for most users, in particular those who wouldn’t be common users of Boost, I would prefer to err on the side of redundancy...
I guess the question is whether you are implementing the Gram matrix or all of the efficient Cholesky/inner products/determinants calculations. If it’s just the Gram matrix then the pure dot...
Just for context this was the original spec for adding new covariance functions, https://github.com/stan-dev/stan/wiki/Adding-a-Gaussian-Process-Covariance-Function The idea was to have optimized Cholesky factorizations and all that good stuff for everything. That...