Post-hoc loss-calibration for Bayesian neural networks

Understand

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available.

• Modern Bayesian models, however, typically involve intractable posteriors that are approximated with, potentially crude, surrogates.
• This difficulty has engendered loss-calibrated techniques that aim to learn posterior approximations that favor high-utility decisions.
• In this paper, focusing on Bayesian neural networks, we develop methods for correcting approximate posterior predictive distributions encouraging them to prefer high-utility decisions.