search

LLNL / MuyGPyS

A fast, pure python implementation of the MuyGPs Gaussian process realization and training algorithm.
Other
25 stars 11 forks source link

Update torch documentation and torch tutorial to give caveats #92

Closed alecmdunton closed 1 year ago

alecmdunton commented 1 year ago

Checking to see if docs still build. Torch code mentions that only Matern is support and torch tutorial explains the tradeoff we are making between runtime and performance.

alecmdunton commented 1 year ago

MPI failure was the ongoing issue where the difference between two hyperparameter estimates is 1.3e-7 as opposed to 1e-7.