Picking the low-hanging fruit: testing new physics at scale with active learning

TL;DR

This paper introduces a machine learning-based method for efficiently testing new physics theories against collider data, enabling large-scale exploration with significantly reduced computational resources.

Contribution

It presents a novel machine learning approach that predicts model compatibility with experimental data, reducing resource requirements and expanding testing capabilities.

Findings

Achieved over 90% precision and recall in predictions.

Reduced computational resources to less than 10% of previous methods.

Enabled testing of models previously infeasible due to resource constraints.

Abstract

Since the discovery of the Higgs boson, testing the many possible extensions to the Standard Model has become a key challenge in particle physics. This paper discusses a new method for predicting the compatibility of new physics theories with existing experimental data from particle colliders. Using machine learning, the technique obtained comparable results to previous methods (>90% precision and recall) with only a fraction of their computing resources (<10%). This makes it possible to test models that were impossible to probe before, and allows for large-scale testing of new physics theories.