[tMcGrath]

I'd like to flag up this paper on HMC and minibatch inference: https://arxiv.org/abs/1502.01510v1. It seems that SGHMC might not always behave as well as you might like.

I should say this isn't to pour cold water on the idea of Bayesian deep learning - I think it's an extremely sensible idea and undoubtedly a good direction for research, but just wanted to caution that this particular MCMC method might have subtle flaws.

[eref]

I wished more academic papers would have a "Limitations" section. Often it is so hard to tell what these are, e.g.: Does it scale well? How much faster/slower is it than other methods? Does it converge reliably?

[pishpash]

No incentive for such a thing.

[eref]

Neither is there for reproducible code, but now there are artificial incentives such as the Reproduction Challenge.