James Bowden

icon indicating a website link linkedin.com/in/j-bowden icon indicating an email [email protected]

icon company Caltech icon location Los Angeles, CA icon location Machine Learning PhD student @ Berkeley. Caltech '23. CS, Data Science, Biology.

Results 3 comments of James Bowden

ARD kernel behavior

Maybe related to [this earlier issue](https://github.com/JaxGaussianProcesses/GPJax/issues/108), which behavior still seems to occur. Does this mean that when setting `active_dims`, just have to manually make your lengthscale the correct dimensionality?

ARD kernel behavior

Okay, that makes sense. I think fixing the documentation will at least make it clear what needs to be done--issue is mainly that I thought I had an ARD kernel...

ARD kernel behavior

In the case you proposed, why wouldn't you just select the dimensions of your covariates that you want to apply the kernel to, e.g., `D_active = D[0:2,:]` and apply a...