Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

TL;DR

This paper investigates evidential deep learning (EDL) for uncertainty quantification and out-of-distribution detection in jet classification at the LHC, comparing it with Bayesian methods and exploring its interpretability.

Contribution

It provides a comprehensive analysis of EDL's effectiveness in jet identification, including hyperparameter optimization, uncertainty distribution, and anomaly detection, with insights into its advantages and pitfalls.

Findings

EDL offers a computationally efficient alternative to Bayesian methods for UQ.

Uncertainty distributions vary across jet classes and can indicate anomalies.

Identified limitations of EDL in out-of-distribution detection and proposed improvements.

Abstract

Current methods commonly used for uncertainty quantification (UQ) in deep learning (DL) models utilize Bayesian methods which are computationally expensive and time-consuming. In this paper, we provide a detailed study of UQ based on evidential deep learning (EDL) for deep neural network models designed to identify jets in high energy proton-proton collisions at the Large Hadron Collider and explore its utility in anomaly detection. EDL is a DL approach that treats learning as an evidence acquisition process designed to provide confidence (or epistemic uncertainty) about test data. Using publicly available datasets for jet classification benchmarking, we explore hyperparameter optimizations for EDL applied to the challenge of UQ for jet identification. We also investigate how the uncertainty is distributed for each jet class, how this method can be implemented for the detection of anomalies, how the uncertainty compares with Bayesian ensemble methods, and how the uncertainty maps onto latent spaces for the models. Our studies uncover some pitfalls of EDL applied to anomaly detection and a more effective way to quantify uncertainty from EDL as compared with the foundational EDL setup. These studies illustrate a methodological approach to interpreting EDL in jet classification models, providing new insights on how EDL quantifies uncertainty and detects out-of-distribution data which may lead to improved EDL methods for DL models applied to classification tasks.