Add deterministic VI methods

[SamDuffield]

• DADVI (paper) pre-samples the Gaussian noise in the init and then is fully deterministic in update which makes for more stable training. More samples are needed so might need gradient accumulation support Gradient accumulation #52
• Last-layer deterministic VI (paper) provides a handy deterministic objective with linear last layers for regression and classification. Might be worth adding if we can generalise to exponential familiy losses and/or linearise the model.

[ifiaposto]

I am adding SNGP that is also a deterministic/ single-forward pass UQ method. not sure if it will work well on pre-trained models though, i.e., not necessarily regularized with spectral normalization.

[SamDuffield]

My understanding is that SNGP #68 training as in the paper is deterministic because they use a Laplace approximation. I imagine though you could do it with VI and even the deterministic VI methods above!

[SamDuffield]

Adding this which is definitely relevant

• DVI (paper) deterministic VI although it seems to require quite intricate knowledge of the model