Probabilistic Energy-Based Neural Networks for Uncertainty-Aware Collider Data Analyses
Abstract
We introduce a probabilistic energy-based Neural Network (NN) for uncertainty-aware classification in collider analyses. Standard discriminative classifiers can give highly confident predictions even for events that are different from the data used during training. Energy-Based Models provide an alternative by assigning an energy score to each event, which measures how well the event agrees with the learned data distribution. In this framework, a NN maps the input features into a latent space, where the energy is defined with respect to class-specific embeddings. This allows the model to identify noisy, anomalous or shifted events while maintaining good classification performance. We first study the method using controlled synthetic examples and then test it in a realistic collider analysis based on the h → τ+ τ- process at the Large Hadron Collider, where h is the discovered Standard Model Higgs boson. We show that the associated energy score can help identify events affected by mismodelling and/or systematic variations and can thus be used to define uncertainty-aware event selections. Although we use this specific Higgs process as a testbed, the method is general and can be applied to other collider classification problems where robustness against systematic and distributional uncertainties is important.
Related
- Generalised Dynamic Radius Jets for Robust Collider Analyses
- Conditional validity of quantum event classifiers under collider systematics and quantum estimation uncertainty
- FCC-μe: High Energy, High Luminosity Muon-Electron Collider & Neutrino Factory at CERN
- Precision luminosity measurement in proton-proton collisions at a center-of-mass energy of 13 TeV with the CMS detector at the Large Hadron Collider
- Bottom quark electroweak dipole moments at a high-energy μ−collider
BibTeX
@misc{ramos2026probabilistic,
title = {{Probabilistic Energy-Based Neural Networks for Uncertainty-Aware Collider Data Analyses}},
author = {Raymundo Ramos and Ahmed Hammad and Amit Chakraborty and Pyungwon Ko and Stefano Moretti},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40268},
eprint = {2610.40268},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40268},
}
RIS
TY - UNPB
TI - Probabilistic Energy-Based Neural Networks for Uncertainty-Aware Collider Data Analyses
AU - Raymundo Ramos
AU - Ahmed Hammad
AU - Amit Chakraborty
AU - Pyungwon Ko
AU - Stefano Moretti
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40268
UR - https://arxiv.org/abs/2610.40268
AB - We introduce a probabilistic energy-based Neural Network (NN) for uncertainty-aware classification in collider analyses. Standard discriminative classifiers can give highly confident predictions even for events that are different from the data used during training. Energy-Based Models provide an alternative by assigning an energy score to each event, which measures how well the event agrees with the learned data distribution. In this framework, a NN maps the input features into a latent space, where the energy is defined with respect to class-specific embeddings. This allows the model to identify noisy, anomalous or shifted events while maintaining good classification performance. We first study the method using controlled synthetic examples and then test it in a realistic collider analysis based on the h → τ^+ τ^- process at the Large Hadron Collider, where h is the discovered Standard Model Higgs boson. We show that the associated energy score can help identify events affected by mismodelling and/or systematic variations and can thus be used to define uncertainty-aware event selections. Although we use this specific Higgs process as a testbed, the method is general and can be applied to other collider classification problems where robustness against systematic and distributional uncertainties is important.
ER -