Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference

TL;DR

This paper introduces a novel Bayesian learning framework that combines calibration regularization, confidence minimization, and selective calibration to improve AI reliability in both in-distribution and out-of-distribution scenarios.

Contribution

It extends variational inference-based Bayesian learning with a new scheme integrating calibration and confidence techniques for better AI decision reliability.

Findings

SCBNN-OCM achieves superior ID and OOD calibration and accuracy.

Selective calibration effectively rejects uncertain inputs.

Trade-offs exist between accuracy, calibration, and rejection rate.

Abstract

The application of artificial intelligence (AI) models in fields such as engineering is limited by the known difficulty of quantifying the reliability of an AI's decision. A well-calibrated AI model must correctly report its accuracy on in-distribution (ID) inputs, while also enabling the detection of out-of-distribution (OOD) inputs. A conventional approach to improve calibration is the application of Bayesian ensembling. However, owing to computational limitations and model misspecification, practical ensembling strategies do not necessarily enhance calibration. This paper proposes an extension of variational inference (VI)-based Bayesian learning that integrates calibration regularization for improved ID performance, confidence minimization for OOD detection, and selective calibration to ensure a synergistic use of calibration regularization and confidence minimization. The scheme is constructed successively by first introducing calibration-regularized Bayesian learning (CBNN), then incorporating out-of-distribution confidence minimization (OCM) to yield CBNN-OCM, and finally integrating also selective calibration to produce selective CBNN-OCM (SCBNN-OCM). Selective calibration rejects inputs for which the calibration performance is expected to be insufficient. Numerical results illustrate the trade-offs between ID accuracy, ID calibration, and OOD calibration attained by both frequentist and Bayesian learning methods. Among the main conclusions, SCBNN-OCM is seen to achieve best ID and OOD performance as compared to existing state-of-the-art approaches at the cost of rejecting a sufficiently large number of inputs.