Anomaly detection from mass unspecific jet tagging

Abstract

We introduce a novel anomaly search method based on (i) jet tagging to select interesting events, which are less likely to be produced by background processes; (ii) comparison of the untagged and tagged samples to single out features (such as bumps produced by the decay of new particles) in the latter. We demonstrate the usefulness of this method by applying it to a final state with two massive boosted jets: for the new physics benchmarks considered, the signal significance increases an order of magnitude, up to a factor of 40. We compare to other anomaly detection methods in the literature and discuss possible generalisations.

LaTeX 21 pages, 55 plots. Added more comparisons with other methods. Final version in EPJC

References in corpus (4)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• A generic anti-QCD jet tagger
• Search for low mass vector resonances decaying into quark-antiquark pairs in proton-proton collisions at sqrt(s) = 13 TeV
• How good are your fits? Unbinned multivariate goodness-of-fit tests in high energy physics

Cited by in corpus (8)

• Anomaly Detection under Coordinate Transformations
• Neural Embedding: Learning the Embedding of the Manifold of Physics Data
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Meta-learning and data augmentation for mass-generalised jet taggers
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging
• Multiboson signals in the UN2HDM
• Detecting New Physics as Novelty -- Complementarity Matters