Classifier Surrogates: Sharing AI-based Searches with the World

Abstract

In recent years, neural network-based classification has been used to improve data analysis at collider experiments. While this strategy proves to be hugely successful, the underlying models are not commonly shared with the public and rely on experiment-internal data as well as full detector simulations. We show a concrete implementation of a newly proposed strategy, so-called Classifier Surrogates, to be trained inside the experiments, that only utilise publicly accessible features and truth information. These surrogates approximate the original classifier distribution, and can be shared with the public. Subsequently, such a model can be evaluated by sampling the classification output from high-level information without requiring a sophisticated detector simulation. Technically, we show that Continuous Normalizing Flows are a suitable generative architecture that can be efficiently trained to sample classification results using Conditional Flow Matching. We further demonstrate that these models can be easily extended by Bayesian uncertainties to indicate their degree of validity when confronted with unknown inputs by the user. For a concrete example of tagging jets from hadronically decaying top quarks, we demonstrate the application of flows in combination with uncertainty estimation through either inference of a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights.

arXiv comment10 pages, 6 Figures, 1 Table

References in corpus (17)

• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Identifying Boosted Objects with N-subjettiness
• Soft Drop
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Performance of $b$-Jet Identification in the ATLAS Experiment
• Deep Learning and its Application to LHC Physics
• Machine Learning and LHC Event Generation
• Reinterpretation of LHC Results for New Physics: Status and Recommendations after Run 2
• Publishing statistical models: Getting the most out of particle physics experiments
• Searches for New Physics: Les Houches Recommendations for the Presentation of LHC Results
• Measuring QCD Splittings with Invertible Networks
• Anomaly detection search for new resonances decaying into a Higgs boson and a generic new particle $X$ in hadronic final states using $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Search for R-parity violating supersymmetry in a final state containing leptons and many jets with the ATLAS experiment using $\sqrt{s}=13$ TeV proton-proton collision data
• Search for supersymmetry in final states with missing transverse momentum and three or more $b$-jets in 139 fb${}^{-1}$ of proton$-$proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Search for neutral long-lived particles in $pp$ collisions at $\sqrt{s}=13$ TeV that decay into displaced hadronic jets in the ATLAS calorimeter
• Les Houches guide to reusable ML models in LHC analyses

Cited by in corpus (2)

• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification