Rens Holmer

Thanks for the comment. I am on a fresh machine and haven't used meteor on this machine before (so no rosetta terminal etc.). I have tried both the 'old' way...

Indeed probably not a frequent issue, but OTOH might also not be very uncommon (I think gnu core-utils is used frequently on mac: [75K installs in the last 30days](https://formulae.brew.sh/formula/coreutils)). I'll...

I just realized that I'm getting this exact same error in #1041 with the variational stuff. [Potentially offending line](https://github.com/cornellius-gp/gpytorch/blob/master/gpytorch/variational/variational_strategy.py#L91) in the source code. Not 100% sure of the issue, but...

I think my main confusion is that the API now does not clearly distinguish between closed form vs sampling. In addition, the underlying code execution is a bit opaque. Both...

A very relevant use of this feature would be the use of the aggregation functionality, especially since MongoDB 3.4. For this option #2 of @steph643's original post would be a...

This still happens

Having the same issue! ``` Reading BLAST file and pre-processing Generating BLAST list 0 matches imported (645901 discarded) 0 pairwise comparisons 0 alignments generated Pairwise collinear blocks written to test/dt.collinearity...

@brkldj It did, took me a while to figure it out. The readme says input files should be in bed format, which has the name of the feature as 4th...

Chiming in here, I'm pretty sure the implementation that @vr308 contributed _can_ learn a distribution over X through a variational approximation: https://github.com/cornellius-gp/gpytorch/blob/master/gpytorch/models/gplvm/latent_variable.py#L65

Awesome, thanks for clarifying! Am I wrong when I think that the testing idea could be implemented with backconstraints a la [Lawrence and Quinonero-Candela 2006](https://inverseprobability.com/publications/files/backConstraints.pdf)?