Parametrized classifiers for optimal EFT sensitivity

Abstract

We study unbinned multivariate analysis techniques, based on Statistical Learning, for indirect new physics searches at the LHC in the Effective Field Theory framework. We focus in particular on high-energy $ZW$ production with fully leptonic decays, modeled at different degrees of refinement up to NLO in QCD. We show that a considerable gain in sensitivity is possible compared with current projections based on binned analyses. As expected, the gain is particularly significant for those operators that display a complex pattern of interference with the Standard Model amplitude. The most effective method is found to be the "Quadratic Classifier" approach, an improvement of the standard Statistical Learning classifier where the quadratic dependence of the differential cross section on the EFT Wilson coefficients is built-in and incorporated in the loss function. We argue that the Quadratic Classifier performances are nearly statistically optimal, based on a rigorous notion of optimality that we can establish for an approximate analytic description of the $ZW$ process.

34 pages, 9 figures

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• PYTHIA 6.4 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• MadAnalysis 5, a user-friendly framework for collider phenomenology
• Automation of the matrix element reweighting method
• Novel measurements of anomalous triple gauge couplings for the LHC
• The Matrix Element Method and its Application to Measurements of the Top Quark Mass
• Precision diboson measurements at hadron colliders

Cited by in corpus (16)

• Publishing statistical models: Getting the most out of particle physics experiments
• Presenting Unbinned Differential Cross Section Results
• High-energy EFT probes with fully differential Drell-Yan measurements
• Higgs boson tagging with the Lund jet plane
• Unbinned multivariate observables for global SMEFT analyses from machine learning
• Searching for anomalous quartic gauge couplings at muon colliders using principle component analysis
• Energy Correlators of Hadronically Decaying Electroweak Bosons
• A fully differential SMEFT analysis of the golden channel using the method of moments
• Precision from the diphoton Zh channel at FCC-hh
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Diboson production in the SMEFT from gluon fusion
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• Refinable modeling for unbinned SMEFT analyses
• Constraints on standard model effective field theory for a Higgs boson produced in association with W or Z bosons in the H $\to \mathrm{b}\bar{\mathrm{b}}$ decay channel in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Equivariant neural networks for robust $\text{CP}$ observables
• Learning New Physics from an Imperfect Machine