Related papers: Stable and Interpretable Jet Physics with IRC-Safe…
Adversarial examples reveal critical vulnerabilities in deep neural networks by exploiting their sensitivity to imperceptible input perturbations. While adversarial training remains the predominant defense strategy, it often incurs…
Deep neural networks provide flexible frameworks for learning data representations and functions relating data to other properties and are often claimed to achieve 'super-human' performance in inferring relationships between input data and…
The radiation pattern within high energy quark- and gluon-initiated jets (jet substructure) is used extensively as a precision probe of the strong force as well as an environment for optimizing event generators with numerous applications in…
Charged track multiplicity is among the most powerful observables for discriminating quark- from gluon-initiated jets. Despite its utility, it is not infrared and collinear (IRC) safe, so perturbative calculations are limited to studying…
Energy correlators have recently been proposed as a class of jet substructure observables that directly link experimental measurements of the asymptotic energy flux with the field theoretic description of the underlying microscopic…
Distinguishing quark-initiated jets from gluon-initiated jets has the potential to significantly improve the reach of many beyond-the-standard model searches at the Large Hadron Collider and to provide additional tests of QCD. To explore…
Embedding symmetries in the architectures of deep neural networks can improve classification and network convergence in the context of jet substructure. These results hint at the existence of symmetries in jet energy depositions, such as…
The reliable discrimination of tectonic earthquakes from anthropogenic quarry blasts and transient noise remains a critical challenge in single station seismic monitoring. In this study, we introduce a novel Physics Informed Convolutional…
Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such models remains impractical on resource-constrained devices with…
Jet point cloud images are high dimensional data structures that needs to be transformed to a separable feature space for machine learning algorithms to distinguish them with simple decision boundaries. In this article, the authors focus on…
Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning…
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…
The jet quenching phenomenon in heavy ion collisions provides a strong evidence of the modification of parton shower in the quark-gluon plasma (QGP). Jet substructure observables can probe various aspects of the jet formation mechanism.…
We study the fragmentation function of jets propagating through a dense quark-gluon plasma within perturbative QCD. Our results for its nuclear modification factor are in qualitative agreement with the experimental data in Pb+Pb collisions…
An interpretable, physics-consistent turbulence model correction framework, termed FISR-Equation Learner (EQL), is proposed by embedding equation learning directly into a Partial Differential Equations (PDE)-constrained field inversion…
Efficient and accurate algorithms are necessary to reconstruct particles in the highly granular detectors anticipated at the High-Luminosity Large Hadron Collider and the Future Circular Collider. We study scalable machine learning models…
Jets, as collections of multi-scale objects, allow for insight into perturbative (high-momentum) processes, but gaining an understanding of the non-perturbative structure within jets such as hadronization effects and the underlying event…
Many real-world interactions are group-based rather than pairwise such as papers with multiple co-authors and users jointly engaging with items. Hypergraph neural networks have shown great promise at modeling higher-order relations, but…
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…
We develop a neural network model, based on the processes of high-energy heavy-ion collisions, to study and predict several experimental observables in Au+Au collisions. We present a data-driven deep learning framework for predicting…