Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging

TL;DR

This paper introduces a neural classifier leveraging invariant representations for effective anti-QCD jet tagging, enhancing background rejection and signal significance in jet physics.

Contribution

It demonstrates that a well-calibrated, mass-decorrelated neural classifier can serve as a powerful, generic anti-QCD jet tagger with improved background rejection capabilities.

Findings

Achieved a background rejection rate of 51.

Attained a significance improvement factor of 3.6.

Reaches excellent tagging efficiencies across test signals.

Abstract

We leverage representation learning and the inductive bias in neural-net-based Standard Model jet classification tasks, to detect non-QCD signal jets. In establishing the framework for classification-based anomaly detection in jet physics, we demonstrate that, with a \emph{well-calibrated} and \emph{powerful enough feature extractor}, a well-trained \emph{mass-decorrelated} supervised Standard Model neural jet classifier can serve as a strong generic anti-QCD jet tagger for effectively reducing the QCD background. Imposing \emph{data-augmented} mass-invariance (and thus decoupling the dominant factor) not only facilitates background estimation, but also induces more substructure-aware representation learning. We are able to reach excellent tagging efficiencies for all the test signals considered. In the best case, we reach a background rejection rate of 51 and a significance improvement factor of 3.6 at 50 \% signal acceptance, with the jet mass decorrelated. This study indicates that supervised Standard Model jet classifiers have great potential in general new physics searches.