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

2025-01-10

AI Summary

In high-energy physics jet identification, deep learning models suffer from inaccurate uncertainty quantification and poor robustness in out-of-distribution (OOD) scenarios. Method: We propose an improved evidential deep learning (EDL) framework that (1) corrects inherent biases in standard EDL to yield more reliable uncertainty estimates, and (2) establishes an interpretable mapping from uncertainty to latent space, enhancing model transparency and generalization. Contribution/Results: Evaluated on public jet datasets, our method significantly outperforms standard EDL and Bayesian ensembles: it reduces uncertainty calibration error by 32%, achieves an OOD detection AUC of 0.94, and substantially lowers computational overhead. This work establishes a new paradigm for physics-informed, trustworthy AI modeling.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• High Energy Physics
• Deep Learning
• Jet Identification

Innovation

• Evidence Deep Learning (EDL)
• Uncertainty Quantification
• Jet Classification