Unveiling the secrets of new physics through top quark tagging

R Sahu, S Ashanujjaman, K Ghosh - The European Physical Journal …, 2024 - Springer
The ubiquity of top-rich final states in the context of beyond the Standard Model (BSM)
searches has led to their status as extensively studied signatures at the LHC. Over the past …

Foundations of automatic feature extraction at LHC–point clouds and graphs

A Bhardwaj, P Konar, V Ngairangbam - The European Physical Journal …, 2024 - Springer
Deep learning algorithms will play a key role in the upcoming runs of the Large Hadron
Collider (LHC), hel** bolster various fronts ranging from fast and accurate detector …

Streamlined jet tagging network assisted by jet prong structure

A Hammad, MM Nojiri - Journal of High Energy Physics, 2024 - Springer
A bstract Attention-based transformer models have become increasingly prevalent in collider
analysis, offering enhanced performance for tasks such as jet tagging. However, they are …

A Lorentz-Equivariant Transformer for All of the LHC

J Brehmer, V Bresó, P de Haan, T Plehn, H Qu… - arxiv preprint arxiv …, 2024 - arxiv.org
We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-
of-the-art performance for a wide range of machine learning tasks at the Large Hadron …

Equivariant, safe and sensitive—graph networks for new physics

A Bhardwaj, C Englert, W Naskar… - Journal of High Energy …, 2024 - Springer
A bstract This study introduces a novel Graph Neural Network (GNN) architecture that
leverages infrared and collinear (IRC) safety and equivariance to enhance the analysis of …

A detailed study of interpretability of deep neural network based top taggers

A Khot, MS Neubauer, A Roy - Machine Learning: Science and …, 2023 - iopscience.iop.org
Recent developments in the methods of explainable artificial intelligence (XAI) allow
researchers to explore the inner workings of deep neural networks (DNNs), revealing crucial …

Feature selection with distance correlation

R Das, G Kasieczka, D Shih - Physical Review D, 2024 - APS
Choosing which properties of the data to use as input to multivariate decision algorithms—
also known as feature selection—is an important step in solving any problem with machine …

Streamlining latent spaces in machine learning using moment pooling

R Gambhir, A Osathapan, J Thaler - Physical Review D, 2024 - APS
Many machine learning applications involve learning a latent representation of data, which
is often high-dimensional and difficult to directly interpret. In this work, we propose “moment …

Enforcing exact permutation and rotational symmetries in the application of quantum neural networks on point cloud datasets

Z Li, L Nagano, K Terashi - Physical Review Research, 2024 - APS
Recent developments in the field of quantum machine learning have promoted the idea of
incorporating physical symmetries in the structure of quantum circuits. A crucial milestone in …

Accuracy versus precision in boosted top tagging with the ATLAS detector

G Aad, E Aakvaag, B Abbott… - Journal of …, 2024 - iopscience.iop.org
The identification of top quark decays where the top quark has a large momentum
transverse to the beam axis, known as top tagging, is a crucial component in many …