[nextfx]

MCMC is AFAIU overly prohibitive for neural networks. If you are interested in incorporating uncertainty awareness and improving calibration of your neural net classifiers in a somewhat scalable manner, I think linearized Laplace is a good place to look. I'd suggest you look at `laplace-torch` [1], it's an easy way of doing that.

[1]: https://aleximmer.github.io/Laplace/

[radarsat1]

Never heard of that, I'll take a look thanks. What do you mean by overly prohibitive? I'm not talking about big networks here so running them many times for inference is not a big deal, although I admit I'm not sure what numbers we are talking about. 100s to 1000s of times is feasible though.

[nextfx]

I'm not an expert on MCMC for BNNs by any means, but even with small networks I think it's a little tricky to get right. If my memory serves me right, this paper[1] focuses on small networks and goes over the issues and how to get around them.

[1]: https://arxiv.org/abs/2402.01484