Uncertainty in the Variational Information Bottleneck
Alexander A. Alemi, Ian S. Fischer, Joshua V. Dillon · arXiv (Cornell University) · 2018
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.