On Calibrated Model Uncertainty in Deep Learning. (arXiv:2206.07795v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07795

Estimated uncertainty by approximate posteriors in Bayesian neural networks
are prone to miscalibration, which leads to overconfident predictions in
critical tasks that have a clear asymmetric cost or significant losses. Here,
we extend the approximate inference for the loss-calibrated Bayesian framework
to dropweights based Bayesian neural networks by maximising expected utility
over a model posterior to calibrate uncertainty in deep learning. Furthermore,
we show that decisions informed by loss-calibrated uncertainty can improve
diagnostic performance to a greater extent than straightforward …

arxiv deep deep learning learning lg model on uncertainty