Semi-Supervised Anomaly Detection - Towards Model-Independent Searches of New Physics

TL;DR

This paper introduces a semi-supervised anomaly detection algorithm for high energy physics that models background with Gaussian mixtures and identifies deviations, offering robustness against signal model inaccuracies compared to supervised neural networks.

Contribution

The paper presents a novel semi-supervised anomaly detection method that does not rely on signal training data, improving robustness over traditional supervised classifiers in physics searches.

Findings

More robust against signal model misspecification than neural networks

Performs comparably to neural networks when training data is accurate

Effective in identifying unexpected signals without prior training on them

Abstract

Most classification algorithms used in high energy physics fall under the category of supervised machine learning. Such methods require a training set containing both signal and background events and are prone to classification errors should this training data be systematically inaccurate for example due to the assumed MC model. To complement such model-dependent searches, we propose an algorithm based on semi-supervised anomaly detection techniques, which does not require a MC training sample for the signal data. We first model the background using a multivariate Gaussian mixture model. We then search for deviations from this model by fitting to the observations a mixture of the background model and a number of additional Gaussians. This allows us to perform pattern recognition of any anomalous excess over the background. We show by a comparison to neural network classifiers that such an approach is a lot more robust against misspecification of the signal MC than supervised classification. In cases where there is an unexpected signal, a neural network might fail to correctly identify it, while anomaly detection does not suffer from such a limitation. On the other hand, when there are no systematic errors in the training data, both methods perform comparably.