QCD or What?

TL;DR

This paper presents an adversarial autoencoder trained on QCD jets that can identify anomalies from heavy resonance decays, offering a general, controllable, and unsupervised approach for new physics searches in jet substructure.

Contribution

It introduces an adversarial autoencoder that de-correlates jet mass, enabling efficient, model-independent anomaly detection in jet data for new physics searches.

Findings

Autoencoders trained on QCD jets can detect arbitrary heavy resonance decays.

Adversarial training reduces background systematics by de-correlating jet mass.

Method is applicable to both image-based and 4-vector-based jet representations.

Abstract

Autoencoder networks, trained only on QCD jets, can be used to search for anomalies in jet-substructure. We show how, based either on images or on 4-vectors, they identify jets from decays of arbitrary heavy resonances. To control the backgrounds and the underlying systematics we can de-correlate the jet mass using an adversarial network. Such an adversarial autoencoder allows for a general and at the same time easily controllable search for new physics. Ideally, it can be trained and applied to data in the same phase space region, allowing us to efficiently search for new physics using un-supervised learning.