Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
Abstract
Anomaly detection is a key application of machine learning, but is generally focused on the detection of outlying samples in the low probability density regions of data. Here we instead present and motivate a method for unsupervised in-distribution anomaly detection using a conditional density estimator, designed to find unique, yet completely unknown, sets of samples residing in high probability density regions. We apply this method towards the detection of new physics in simulated Large Hadron Collider (LHC) particle collisions as part of the 2020 LHC Olympics blind challenge, and show how we detected a new particle appearing in only 0.08% of 1 million collision events. The results we present are our original blind submission to the 2020 LHC Olympics, where it achieved the state-of-the-art performance.
Cite
@article{arxiv.2012.11638,
title = {Unsupervised in-distribution anomaly detection of new physics through conditional density estimation},
author = {George Stein and Uros Seljak and Biwei Dai},
journal= {arXiv preprint arXiv:2012.11638},
year = {2020}
}
Comments
Accepted to NeurIPS Machine Learning and the Physical Sciences workshop. See arXiv:2007.00674 for further methods