Anomaly Detection

Equivariant Neural Networks
Developed graph-based and Lorentz-equivariant models to better suit our high energy physics data. Our Lorentz-group autoencoder (LGAE) outperforms graph and convolutional networks on jet compression and anomaly detection tasks. Latest work published at EPJC.
Review
Equivariant Neural Networks
Anomaly Detection
Developed several approaches for finding rare particle collisions, including GNNs, Lorentz-equivariant networks, and multi-variate goodness-of-fit tests.
Generative transformers and how to evaluate them (+ Lorentz-equivariant networks)
With the increase in luminosity and detector granularity, simulation will be a significant computational challenge in the HL-LHC. To …
Jun 27, 2023 UC Irvine
Project Project Project Slides
Generative transformers and how to evaluate them (+ Lorentz-equivariant networks)
Lorentz group equivariant autoencoders
Developed an auto-encoder model equivariant to Lorentz transformations of the input. We find it outperforms graph and convolutional neural networks on jet reconstruction and anomaly detection tasks.
Zichun Hao, Raghav Kansal, Javier Duarte, Nadezda Chernyavskaya
PDF arXiv Cite Code Project Project DOI
Lorentz group equivariant autoencoders
Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of …
Steven Tsan, Raghav Kansal, Anthony Aportela, Daniel Diaz, Javier Duarte, Sukanya Krishna, Farouk Mokhtar, Jean-Roch Vlimant, Maurizio Pierini
PDF arXiv Cite Project Project Poster
Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance