New Physics Searches at the LHC through Event-based Anomaly Detection and Development of ADFilter Web-tool

TL;DR

This paper introduces ADFilter, a web-based anomaly detection tool using deep unsupervised neural networks for model-agnostic new physics searches at the LHC, demonstrating its effectiveness in reinterpretation of results and comparison with supervised methods.

Contribution

The paper develops ADFilter, a novel web-tool employing autoencoders for event-based anomaly detection, enhancing model-agnostic searches for new physics at the LHC.

Findings

ADFilter effectively identifies anomalous events in LHC data.

Anomaly detection can improve exclusion limits compared to traditional methods.

Comparison shows advantages of unsupervised over supervised techniques in certain scenarios.

Abstract

This work presents advancements in model-agnostic searches for new physics at the Large Hadron Collider (LHC) through the application of event-based anomaly detection techniques utilizing unsupervised machine learning. We discuss the advantages of the anomaly detection approach, as demonstrated in a recent ATLAS analysis, and introduce ADFilter, a web-based tool designed to process collision events using autoencoders based on deep unsupervised neural networks. ADFilter calculates loss distributions for input events, aiding in determining the degree to which events can be considered anomalous. Real-life examples are provided to demonstrate how the tool can be used to reinterpret existing LHC results, with the goal of significantly improving exclusion limits. Furthermore, we present a comparative study between anomaly detection and supervised machine learning techniques, using the search for heavy resonances decaying into two or more Higgs bosons as a representative case to demonstrate the application and effectiveness of these methods.