Thomas Pinder
Thomas Pinder
Good to hear from you @theorashid. This work has definitely not been shelved. I've been snowed the past few weeks finishing up my thesis. Hoping to submit this week and...
Thanks for raising this @adam-hartshorne, this is very much on our radar. We are hoping to sketch out an initial idea of an implementation next week. If you have any...
Hey @adam-hartshorne. In short, things are moving a little slower than I would like as I'm in the process of finishing up my thesis. I'd hope to have this feature...
Comment from Dan's push: - Minimal Kronecker kernel. The inverse is highly inefficient - this can be improved! - Added white noise kernel. - Added diagonal computation abstraction. - Added...
Thanks @patel-zeel for raising this. Supporting heteroscedastic likelihood functions is certainly something I'd like to support. In theory, it should be quite straightforward to do by making the Gaussian likelihood...
Hey @rlouf I've pinned BlackJax version 0.8.2 in GPJax, but we're still getting import errors similar to those in #223. Any ideas how this can be resolved? https://gpjax--79.org.readthedocs.build/en/79/nbs/classification.html
Thanks! That seems to have fixed it. Is there any view to adding `jaxopt` to the dependencies of BlackJax?
Closing in lieu of #270
Hi @patel-zeel and @matthewrhysjones Right now, it would be possible to simply use a `Gaussian` likelihood object and manually set the variance parameter to be a vector (it will default...
Not sure how/if I can be helpful here, but please let me know if there's anything I can help with.