ELUQuant: Event-Level Uncertainty Quantification in Deep Inelastic Scattering

TL;DR

ELUQuant introduces a physics-informed Bayesian Neural Network with flow-based posteriors for detailed event-level uncertainty quantification in deep inelastic scattering, enhancing physical insights and decision-making capabilities.

Contribution

The paper presents a novel Bayesian neural network with flow-approximated posteriors for granular event-level uncertainty quantification in DIS, combining deep learning with physics-informed modeling.

Findings

Effective extraction of kinematic variables with uncertainty estimates

Matching performance of recent deep learning regression methods

Potential applications in data quality monitoring and anomaly detection

Abstract

We introduce a physics-informed Bayesian Neural Network (BNN) with flow approximated posteriors using multiplicative normalizing flows (MNF) for detailed uncertainty quantification (UQ) at the physics event-level. Our method is capable of identifying both heteroskedastic aleatoric and epistemic uncertainties, providing granular physical insights. Applied to Deep Inelastic Scattering (DIS) events, our model effectively extracts the kinematic variables $x$, $Q^2$, and $y$, matching the performance of recent deep learning regression techniques but with the critical enhancement of event-level UQ. This detailed description of the underlying uncertainty proves invaluable for decision-making, especially in tasks like event filtering. It also allows for the reduction of true inaccuracies without directly accessing the ground truth. A thorough DIS simulation using the H1 detector at HERA indicates possible applications for the future EIC. Additionally, this paves the way for related tasks such as data quality monitoring and anomaly detection. Remarkably, our approach effectively processes large samples at high rates.