2000 character limit reached
Uncertainty in the Variational Information Bottleneck
Published 2 Jul 2018 in cs.LG and stat.ML | (1807.00906v1)
Abstract: 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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.