Max Balandat comments

Results 476 comments of


                                            Max Balandat

Pairwise comparison with fantasies

Hi @fraiori0, glad you're interested in using the pairwise GP model. I am not sure to what extent we have tested the pairwise GP model for fantasizing and using it...

Pairwise comparison with fantasies

Hi @fraiori0, sorry this fell off the radar somehow. I am not particularly familiar with this part of the code, but it looks like the issue here is that the...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

@mc-robinson, thanks for the comprehensive issue. We have designed the `posterior` API in a way to also support getting the posterior predictive, by using the `observation_noise` kwarg. So you can...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

The "Most Likely Heteroscedastic Gaussian Process Regression:" seems to be pretty much exactly what you're doing, just adding an EM-style fitting process where you iteratively re-estimate the mean and the...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

The issue with the `observation_noise` kwarg not being honored in for `BatchedMultiOutputGPyTorchModel` models is addressed in #182

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

> I think your method would also work well I think this would work for small models, but we will quickly run into scalability issues if we have a latent...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

Thanks @mc-robinson, I will take a look later today.

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

> However, for the heteroskedastic model, I am getting a slightly different result from when I did it by hand. Can you take a look at the differences and let...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

Thanks a lot for expanding on the nb. > However, this could be due to their method of estimating noise, which is different than mine (I'm not sure I totally...

[Feature Request] Implement most likely heteroskedastic GP and write a tutorial notebook

Thanks for the update, this looks great! > From my reading of the paper the samples they draw $t_i^{j}$ are indeed from the predictive distribution I must have misread that...