Enhancing the hunt for new phenomena in dijet final-states using anomaly detection filters at the High-Luminosity Large Hadron Collider

TL;DR

This paper proposes an anomaly detection method using unsupervised machine learning to improve the search for new physics phenomena in dijet events at the High-Luminosity Large Hadron Collider, overcoming limitations of traditional background modeling.

Contribution

It introduces an anomaly detection approach that enhances the sensitivity of dijet searches by effectively filtering background events without relying on analytic background functions.

Findings

Demonstrates improved detection sensitivity in simulated HL-LHC conditions.

Shows the method effectively filters background events in large data volumes.

Validates the approach's potential for uncovering new physics signals.

Abstract

In the realm of dijet searches in high-energy physics, a significant challenge has emerged: with experiments producing more and more data, the traditional methods of using analytic functions to describe dijet mass spectra start to fail. To address this, we suggest the application of an anomaly detection approach to eliminate less interesting background events based on event final states. This method not only bypasses the limitations of conventional background models but also significantly enhances our ability to detect potential signals of new physics. Through simulations that mimic the conditions of the upcoming High-Luminosity Large Hadron Collider, we demonstrate the strength and efficiency of this approach in dealing with large data volumes. The integration of unsupervised machine learning into our experimental framework paves the way for a promising avenue to unveil hidden physics discoveries within the overwhelming influx of data.