Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging

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.

32 pages, 15 figures. To appear in the Journal of High Energy Physics

References in corpus (7)

• A generic anti-QCD jet tagger
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Autoencoders for unsupervised anomaly detection in high energy physics
• Better Latent Spaces for Better Autoencoders
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Anomaly detection from mass unspecific jet tagging

Cited by in corpus (3)

• Anomalies, Representations, and Self-Supervision
• Unsupervised and lightly supervised learning in particle physics
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning