Bayesian Neural Network Versus Ex-Post Calibration For Prediction Uncertainty

Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings. However, in practice most datasets are trained on non-probabilistic neural networks which by default do not capture th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-09
Main Authors: Borgohain, Satya, Ackermann, Klaus, Loaiza-Maya, Ruben
Format: Article
Language:English
Subjects:
Bayesian analysis
Calibration
Datasets
Decision making
Neural networks
Predictions
Tables (data)
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings. However, in practice most datasets are trained on non-probabilistic neural networks which by default do not capture this inherent uncertainty. This well-known problem has led to the development of post-hoc calibration procedures, such as Platt scaling (logistic), isotonic and beta calibration, which transforms the scores into well calibrated empirical probabilities. A plausible alternative to the calibration approach is to use Bayesian neural networks, which directly models a predictive distribution. Although they have been applied to images and text datasets, they have seen limited adoption in the tabular and small data regime. In this paper, we demonstrate that Bayesian neural networks yields competitive performance when compared to calibrated neural networks and conduct experiments across a wide array of datasets.
ISSN:2331-8422