Uncovering Hidden Systematics in Neural Network Models for High Energy Physics

• URL: http://arxiv.org/abs/2605.07470v1
• Date: Fri, 08 May 2026 09:17:58 GMT
• Title: Uncovering Hidden Systematics in Neural Network Models for High Energy Physics
• Abstract summary: We show how subtle perturbations, fully consistent with the experimental uncertainties on the input observables, can lead to substantial changes in NN outputs.<n>We introduce a framework to probe and measure the hidden sensitivity of neural networks to realistic experimental variations.
• Score: 38.26828627410069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flexibility enables unprecedented performance in high-energy physics (HEP) analyses, it also makes them sensitive to small variations in their inputs. Consequently, the propagation and estimation of systematic uncertainties in NN-based models remain an open challenge. There are indications that uncertainties derived in control regions or from nominal variations of input features can underestimate the true model uncertainty, potentially leaving biases unaccounted for. Inspired by insights from adversarial-attack studies in machine learning, we explore how subtle perturbations, fully consistent with the experimental uncertainties on the input observables, can lead to substantial changes in NN outputs, while keeping the one-dimensional and correlated input distributions nearly unchanged. Using a set of representative HEP tasks, including event classification and object identification, and testing across a variety of network architectures, we demonstrate that networks can be systematically "fooled" at significant rates within the allowed uncertainty envelopes. Building on this observation, we introduce a quantitative framework to probe and measure the hidden sensitivity of neural networks to realistic experimental variations, providing a practical path to evaluate and control their systematic uncertainty in physics analyses.

Related papers

• Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter [31.377504700683374]
  This paper presents a novel online distributed sensing framework, where agents collaborate and exchange information to perform latent state estimation.<n>The proposed estimator combines available partial domain knowledge with the representation capabilities of deep neural networks.<n>Experiments on linear, chaotic (z), and practical wireless tracking environments reveal that the proposed CoLoren-Agnostic Neural Kalman Consensus Filter (CA-NKCF) outperforms traditional distributed Kalman and particle filters.
  arXiv  Detail & Related papers  (2026-06-26T08:07:31Z)
• Bayesian Neural Networks vs. Mixture Density Networks: Theoretical and Empirical Insights for Uncertainty-Aware Nonlinear Modeling [2.0797819204842036]
  We compare the approaches of Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression.<n>On the theoretical side, we derive convergence rates and error bounds under H"older smoothness conditions, showing that MDNs achieve faster Kullback-Leibler (KL) divergence convergence.<n>Our findings clarify the complementary strengths of posterior-based and likelihood-based probabilistic learning, offering guidance for uncertainty-aware modeling in nonlinear systems.
  arXiv  Detail & Related papers  (2025-10-28T22:00:30Z)
• Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer [55.66973223528494]
  We develop a Bayesian Non-negative Decision Layer (BNDL), which reformulates deep neural networks as a conditional Bayesian non-negative factor analysis.<n>BNDL can model complex dependencies and provide robust uncertainty estimation.<n>We also offer theoretical guarantees that BNDL can achieve effective disentangled learning.
  arXiv  Detail & Related papers  (2025-05-28T10:23:34Z)
• Response Estimation and System Identification of Dynamical Systems via Physics-Informed Neural Networks [0.0]
  This paper explores the use of Physics-Informed Neural Networks (PINNs) for the identification and estimation of dynamical systems. PINNs offer a unique advantage by embedding known physical laws directly into the neural network's loss function, allowing for simple embedding of complex phenomena. The results demonstrate that PINNs deliver an efficient tool across all aforementioned tasks, even in presence of modelling errors.
  arXiv  Detail & Related papers  (2024-10-02T08:58:30Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Variational Neural Networks [88.24021148516319]
  We propose a method for uncertainty estimation in neural networks called Variational Neural Network (VNN) VNN generates parameters for the output distribution of a layer by transforming its inputs with learnable sub-layers. In uncertainty quality estimation experiments, we show that VNNs achieve better uncertainty quality than Monte Carlo Dropout or Bayes By Backpropagation methods.
  arXiv  Detail & Related papers  (2022-07-04T15:41:02Z)
• Asymptotic-Preserving Neural Networks for multiscale hyperbolic models of epidemic spread [0.0]
  In many circumstances, the spatial propagation of an infectious disease is characterized by movements of individuals at different scales governed by multiscale PDEs. In presence of multiple scales, a direct application of PINNs generally leads to poor results due to the multiscale nature of the differential model in the loss function of the neural network. We consider a new class of AP Neural Networks (APNNs) for multiscale hyperbolic transport models of epidemic spread.
  arXiv  Detail & Related papers  (2022-06-25T11:25:47Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Multidimensional Uncertainty-Aware Evidential Neural Networks [21.716045815385268]
  We propose a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-versa (OOD) detection problem. We took a hybrid approach that combines Wasserstein Generative Adrial Network (WGAN) with ENNs to jointly train a model with prior knowledge of a certain class. We demonstrated that the estimation of uncertainty by WENN can significantly help distinguish OOD samples from boundary samples.
  arXiv  Detail & Related papers  (2020-12-26T04:28:56Z)
• Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings [7.476901945542385]
  We show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks. Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions.
  arXiv  Detail & Related papers  (2020-09-03T16:58:15Z)
• Phase Detection with Neural Networks: Interpreting the Black Box [58.720142291102135]
  Neural networks (NNs) usually hinder any insight into the reasoning behind their predictions. We demonstrate how influence functions can unravel the black box of NN when trained to predict the phases of the one-dimensional extended spinless Fermi-Hubbard model at half-filling.
  arXiv  Detail & Related papers  (2020-04-09T17:45:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.