Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of graph-based autoencoders, which operate on jets in their "particle cloud" representations and can leverage the interdependencies among the particles within a jet, for such tasks. Additionally, we develop a differentiable approximation to the energy mover's distance via a graph neural network, which may subsequently be used as a reconstruction loss function for autoencoders.
@article{arxiv.2111.12849,
title = {Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance},
author = {Steven Tsan and Raghav Kansal and Anthony Aportela and Daniel Diaz and Javier Duarte and Sukanya Krishna and Farouk Mokhtar and Jean-Roch Vlimant and Maurizio Pierini},
journal= {arXiv preprint arXiv:2111.12849},
year = {2021}
}
Comments
5 pages, 2 figures. Accepted to the Machine Learning for the Physical Sciences workshop at NeurIPS 2021. arXiv admin note: text overlap with arXiv:2101.08320