The experiments at the LHC deliver large amounts of data, which are being used to test the Standard Model of particle physics in detail. While many theoretical and experimental motivations for physics beyond the Standard Model exist, it is impossible to perform a dedicated search for every such scenario. Recent developments in modern machine learning opened up the possibilities for model-agnostic anomaly detection algorithms. One of these, called CATHODE (Classifying Anomalies THrough Outer Density Estimation - https://arxiv.org/abs/2109.00546), has shown a particularly good performance in enhancing searches based on bump hunts.

The codes are based on python and we will be using git for version control. Existing experience in these will be helpful, but motivation to learn them is sufficient.

For more details, please contact Claudius.Krause(at)oeaw.ac.at.