Deep Set Auto Encoders for Anomaly Detection in Particle Physics

Journal Article · 30 January 2022 · SciPost Physics

DOI: https://doi.org/10.21468/SciPostPhys.12.1.045 · OSTI ID:1842863

Ostdiek, Bryan ^[1]

---

1. Harvard University, The NSF AI Institute for Artificial Intelligence and Fundamental Interactions

There is an increased interest in model agnostic search strategies for physics beyond the standard model at the Large Hadron Collider. We introduce a Deep Set Variational Autoencoder and present results on the Dark Machines Anomaly Score Challenge. We find that the method attains the best anomaly detection ability when there is no decoding step for the network, and the anomaly score is based solely on the representation within the encoded latent space. This method was one of the top-performing models in the Dark Machines Challenge, both for the open data sets as well as the blinded data sets.

• Research Organization: Harvard Univ., Cambridge, MA (United States)
• Sponsoring Organization: National Science Foundation (NSF); USDOE; USDOE Office of Science (SC)
• Grant/Contract Number: SC0013607; SC0020223
• OSTI ID: 1842863
• Journal Information: SciPost Physics, Journal Name: SciPost Physics Journal Issue: 1 Vol. 12; ISSN 2542-4653
• Publisher: Stichting SciPostCopyright Statement
• Country of Publication: Netherlands
• Language: English