Creating simple, interpretable anomaly detectors for new physics in jet substructure

Anomaly detection with convolutional autoencoders is a popular method to search for new physics in a model-agnostic manner. These techniques are powerful, but they are still a "black box," since we do not know what high-level physical observables determine how anomalous an event is. To address this, we adapt a recently proposed technique by Faucett et al. [Phys. Rev. D 103, 036020 (2021)., 10.1103/PhysRevD.103.036020], which maps out the physical observables learned by a neural network classifier, to the case of anomaly detection. We propose two different strategies that use a small number of high-level observables to mimic the decisions made by the autoencoder on background events, one designed to directly learn the output of the autoencoder, and the other designed to learn the difference between the autoencoder's outputs on a pair of events. Despite the underlying differences in their approach, we find that both strategies have similar ordering performance as the autoencoder and independently use the same six high-level observables. From there, we compare the performance of these networks as anomaly detectors. We find that both strategies perform similarly to the autoencoder across a variety of signals, giving a nontrivial demonstration that learning to order background events transfers to ordering a variety of signal events.