Simulation Assisted Likelihood-free Anomaly Detection
This addresses the need for broader, model-independent searches in high-energy physics, but it is incremental as it builds on existing approaches by hybridizing them.
The paper tackled the problem of detecting new particles at the Large Hadron Collider by introducing a hybrid method that combines simulation and data-based approaches, resulting in a technique that allows for background estimation with non-trivial correlations in features, as illustrated in a dijet search with jet substructure.
Given the lack of evidence for new particle discoveries at the Large Hadron Collider (LHC), it is critical to broaden the search program. A variety of model-independent searches have been proposed, adding sensitivity to unexpected signals. There are generally two types of such searches: those that rely heavily on simulations and those that are entirely based on (unlabeled) data. This paper introduces a hybrid method that makes the best of both approaches. For potential signals that are resonant in one known feature, this new method first learns a parameterized reweighting function to morph a given simulation to match the data in sidebands. This function is then interpolated into the signal region and then the reweighted background-only simulation can be used for supervised learning as well as for background estimation. The background estimation from the reweighted simulation allows for non-trivial correlations between features used for classification and the resonant feature. A dijet search with jet substructure is used to illustrate the new method. Future applications of Simulation Assisted Likelihood-free Anomaly Detection (SALAD) include a variety of final states and potential combinations with other model-independent approaches.