Transferability of Deep Learning Models in Searches for New Physics at Colliders

Abstract

In this work we assess the transferability of deep learning models to detect beyond the standard model signals. For this we trained Deep Neural Networks on three different signal models: $tZ$ production via a flavour changing neutral current, pair-production of vector-like $T$-quarks via standard model gluon fusion and via a heavy gluon decay in a grid of 3 mass points: 1, 1.2 and 1.4 TeV. These networks were trained with $t\bar{t}$, $Z$+jets and dibosons as the main backgrounds. Limits were derived for each signal benchmark using the inference of networks trained on each signal independently, so that we can quantify the degradation of their discriminative power across different signal processes. We determine that the limits are compatible within uncertainties for all networks trained on signals with vector-like $T$-quarks, whether they are produced via heavy gluon decay or standard model gluon fusion. The network trained on flavour changing neutral current signal, while struggling the most on the other signals, still produce reasonable limits. These results indicate that deep learning models are capable of providing sensitivity in the search for new physics even if it manifests itself in models not assumed during training.

arXiv comment7 pages, 7 figures, accepted for publication in PRD

References in corpus (18)

• Scikit-learn: Machine Learning in Python
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• An Introduction to PYTHIA 8.2
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Parton distributions with LHC data
• Event generator tunes obtained from underlying event and multiparton scattering measurements
• Deep Learning and its Application to LHC Physics
• Identifying top partners at LHC
• Model Independent Framework for Searches of Top Partners
• A global approach to top-quark flavor-changing interactions
• Automatic computations at next-to-leading order in QCD for top-quark flavor-changing neutral processes
• Search for flavor-changing neutral currents in top-quark decays t to Zq in pp collisions at sqrt(s) = 8 TeV
• Search for pair production of vector-like top quarks in events with one lepton, jets, and missing transverse momentum in $\sqrt{s}=13$ TeV pp collisions with the ATLAS detector
• Search for vector-like quarks in events with two oppositely charged leptons and jets in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Search for associated production of a Z boson with a single top quark and for tZ flavour-changing interactions in pp collisions at sqrt(s) = 8 TeV
• Search for flavour-changing neutral current top-quark decays $t\to qZ$ in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Interpretation of Vector-like Quark Searches: Heavy Gluons in Composite Higgs Models
• OpTHyLiC: an Optimised Tool for Hybrid Limits Computation

Cited by in corpus (18)

• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• Better Latent Spaces for Better Autoencoders
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• What's Anomalous in LHC Jets?
• Hunting for top partner with a new signature at the LHC
• Anomaly Detection under Coordinate Transformations
• Collider signatures of vector-like fermions from a flavor symmetric model
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Non-resonant Anomaly Detection with Background Extrapolation
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Preserving New Physics while Simultaneously Unfolding All Observables
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure