Jake Gardner

Hey @stanbiryukov Sorry this took so long to look in to, things are pretty busy right before ICML. Your issue is just batch shaping stuff that only ends up showing...

@stanbiryukov looks like this might have to do with a change we made to how we mark kernels as having lengthscales we didn't think about being breaking. Try adding this:...

@stanbiryukov Could you provide an updated sample of code to run that produces the error?

Not really familiar with the 3 failing `WiskiGP` tests -- maybe something related to the `x1_eq_x2` argument tracking?

@Galto2000 I think we'd just need to implement `FixedNoiseMultitaskGaussianLikelihood`. Basically, you'd specify an `n x t` matrix of noises rather than a length `n` vector of noises, and the interface...

@iprada @lk1983823 I'll take a look at this this week and see if I can get an easy fix out.

Part of the reason we implemented a lot of how we handle W ourselves is because back in like PyTorch 0.2 when we first implemented SKI, the sparse tensor support...

I personally think this would be pretty cool to support. My hunch is that there will be a ton of code reuse at the `LazyTensor` level and lower since they...

Looks like the main failure is just a minor issue in the new unit test checking a return type. `representation` returns a tuple of tensors, so should be a quick...

Hi @mgarort -- Nothing immediately jumps out at me as wrong. Would you possibly be able to provide example data for which this happens, as well as the definition `ExactGPModel`...