A Sober Look at Bayesian Neural Networks
Proponents of Bayesian neural networks often claim that trained BNNs output distributions which capture epistemic uncertainty. Epistemic uncertainty is incredibly valuable for a wide variety of applications, and we agree with the Bayesian approach in general. However, we argue that BNNs require highly informative priors to handle uncertainty. We show that if the prior does not distinguish between functions that generalize and functions that don’t, Bayesian inference cannot provide useful uncertainties. This puts into question the standard argument that “uninformative priors” are appropriate when the true prior distribution is unknown.
Source: A Sober Look at Bayesian Neural Networks, an article by Jacob Buckman.