Howdy folks,

GPyTorch provides Gaussian likelihood objects for fixed noise (FixedNoiseGaussianLikelihood) and for multi-task models (MultitaskGaussianLikelihood). I was wondering if someone could provide me some guidance on how to get a fixed noise multi-task Gaussian likelihood?

Thanks in advance

Galto

I'm trying to have a multi-dimensional lengthscale for my kernel, and cannot find in the documentation how to do this. The closest I've come is specifying input_dim, as described here, but in version 2.0.5 I get an error that input_dim is an unknown keyword argument. How would I get these multidimensional lengthscales in gpfl

There are a variety of interesting optimisations that can be performed on kernels of the form

k(x, z) = w_1 * k_1(x, z) + w_2 * k_2(x, z) + ... + w_L k_L(x, z)

A naive recursive implementation in terms of the current Sum and Scaled kernels hides opportunities for parallelism in the computation of each term, and the summation over terms.

Notable examples of kernels with th

At the moment, looking at the doc page of Variograms, it seems like the only way to analyze Variograms is via the Plots.jl package. But I would much rather obtain the actual values that are plotted. How do I obtain:

1. Values of h axis
2. Values of γ(h)
3. Bin values b(h)

? I don't use Plots.jl and I see no mention in the documentation page on how to obtain these values. The display method