Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC

Abstract

We propose a new method to define anomaly scores and apply this to particle physics collider events. Anomalies can be either rare, meaning that these events are a minority in the normal dataset, or different, meaning they have values that are not inside the dataset. We quantify these two properties using an ensemble of One-Class Deep Support Vector Data Description models, which quantifies differentness, and an autoregressive flow model, which quantifies rareness. These two parameters are then combined into a single anomaly score using different combination algorithms. We train the models using a dataset containing only simulated collisions from the Standard Model of particle physics and test it using various hypothetical signals in four different channels and a secret dataset where the signals are unknown to us. The anomaly detection method described here has been evaluated in a summary paper where it performed very well compared to a large number of other methods. The method is simple to implement and is applicable to other datasets in other fields as well.

Deep Set Auto Encoders for Anomaly Detection in Particle Physics

“…In the Dark Machines challenge [49], these deep set VAE models were among the top models, achieving median total improvements greater than 2 in both the hackathon datasets (results from this work) and in the secret dataset. Interestingly, the other set of models which had high median scores for both the hackathon and secret data sets also used as part of their anomaly score a mapping to a fixed representation [50]. The fixed representations were either also a multidimensional Gaussian distribution or a fixed vector.…”

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

“…We also find that the β = 1 D KL score and the β = 0.5 reconstruction score show a similar correlation pattern on signal and background. As a result, we expect that only a limited improvement would be obtained by combining the two, which spares us the cost of introducing a new hyperparameter (the relative weight of the two terms) whose optimal value would be signal-specific, as in the case of Caron et al ( 2021 ).…”

“…This study is an update of our contribution to the DarkMachine challenge (Aarrestad et al, 2021 ), which benefits from the lessons learned by the DarkMachines challenge. Taking inspiration from solutions presented by other groups in the challenge (e.g., Caron et al, 2021 ; Ostdiek, 2021 ), we evaluate the impact of some of their findings on our specific setup. In some cases (but not always), these solutions translate in an improved performance, quantified using the same metrics presented in Aarrestad et al ( 2021 ).…”

The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider

“…Then, the flow model score and combined Deep SVDD model score are combined into a single score using the same method. This method is described in detail in [103]. The results are labelled as Combined-combination-DeepSVDD-Flow in the results.…”