Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
This method addresses the challenge of detecting rare new physics phenomena within high-density regions of particle collision data, which is a critical problem for high-energy physicists.
The paper introduces an unsupervised in-distribution anomaly detection method using a conditional density estimator to find unique, unknown sets of samples within high probability density regions. Applied to simulated LHC particle collisions, it successfully detected a new particle appearing in only 0.08% of 1 million events.
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.