pith. sign in

arxiv: 2006.11695 · v4 · pith:6MBKSAGUnew · submitted 2020-06-21 · 📊 stat.ML · cs.LG

Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks

classification 📊 stat.ML cs.LG
keywords bayesianmodelspredictiveuncertaintiesdeepfeatureslinearregression
0
0 comments X
read the original abstract

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainties by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused on methodically evaluating the predictive uncertainties of these models. In this work, we demonstrate that traditional training procedures for NLMs drastically underestimate uncertainty on out-of-distribution inputs, and that they therefore cannot be naively deployed in risk-sensitive applications. We identify the underlying reasons for this behavior and propose a novel training framework that captures useful predictive uncertainties for downstream tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.