Learning Selection Cuts With Gradients

Abstract

Many analyses in high-energy physics rely on selection thresholds (cuts) applied to detector, particle, or event properties. Initial cut values can often be guessed from physical intuition, but cut optimization, especially for multiple features, is commonly performed by hand, or skipped entirely in favor of multivariate algorithms like BDTs or neural networks. We revisit this problem, and develop a cut optimization approach based on gradient descent. Cut thresholds are learned as parameters of a network with a simple architecture, and can be tuned to achieve a target signal efficiency through the use of custom loss functions. Contractive terms in the loss can be used to ensure a smooth evolution of cuts as functions of efficiency, particle kinematics, or event features. The method is used to classify events in a search for Supersymmetry, and the performance is compared with common classification tools. An implementation of this approach is available in a public code repository and python package.

14 pages, 8 figures

References in corpus (17)

• XGBoost: A Scalable Tree Boosting System
• 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
• TMVA - Toolkit for Multivariate Data Analysis
• Searches for electroweak production of supersymmetric particles with compressed mass spectra in $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Measurement of the photon identification efficiencies with the ATLAS detector using LHC Run 2 data collected in 2015 and 2016
• Search for chargino-neutralino production with mass splittings near the electroweak scale in three-lepton final states in $\sqrt{s}$ = 13 TeV $pp$ collisions with the ATLAS detector
• Search for supersymmetry in final states with two or three soft leptons and missing transverse momentum in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Search for supersymmetry with a compressed mass spectrum in the vector boson fusion topology with 1-lepton and 0-lepton final states in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Electron and photon efficiencies in LHC Run 2 with the ATLAS experiment
• 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
• Searches for direct slepton production in the compressed-mass corridor in $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Reduce, Reuse, Reinterpret: an end-to-end pipeline for recycling particle physics results
• Search for cascade decays of charged sleptons and sneutrinos in final states with three leptons and missing transverse momentum in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Analysis of Hardware Synthesis Strategies for Machine Learning in Collider Trigger and Data Acquisition