IRC-safe Graph Autoencoder for unsupervised anomaly detection
High Energy Physics - Phenomenology
2022-08-02 v2 Machine Learning
High Energy Physics - Experiment
Abstract
Anomaly detection through employing machine learning techniques has emerged as a novel powerful tool in the search for new physics beyond the Standard Model. Historically similar to the development of jet observables, theoretical consistency has not always assumed a central role in the fast development of algorithms and neural network architectures. In this work, we construct an infrared and collinear safe autoencoder based on graph neural networks by employing energy-weighted message passing. We demonstrate that whilst this approach has theoretically favourable properties, it also exhibits formidable sensitivity to non-QCD structures.
Cite
@article{arxiv.2204.12231,
title = {IRC-safe Graph Autoencoder for unsupervised anomaly detection},
author = {Oliver Atkinson and Akanksha Bhardwaj and Christoph Englert and Partha Konar and Vishal S. Ngairangbam and Michael Spannowsky},
journal= {arXiv preprint arXiv:2204.12231},
year = {2022}
}
Comments
16 pages, 5 figures, Matched with the published version