Fast multilabel classification of HEP constraints with deep learning
arXiv:2409.05453 · doi:10.1103/PhysRevD.111.075010
Abstract
The shortcomings of the Standard Model (SM) motivate its extension to accommodate new expected phenomena, such as dark matter and neutrino masses. However, such extensions are generally more complex due to the presence of a large number of free parameters and additional phenomenology. Understanding how theoretical and experimental limits affect the parameter spaces of new models, individually and collectively, is of utmost importance for conducting model status analysis, motivating precise computations, or model-building aimed at solving certain issues. However, checking the constraints usually require a large amount of time using a chain of physics tools. We demonstrate, for the first time, the application of deep learning (DL) for the multilabel classification (MLC) of a group of theoretical and experimental constraints in the dark doublet phase of the next-to-two-Higgs-doublet model (DDP-N2HDM), as a representative 9-dimensional parameter space. We analyze the issue of class imbalance and the ability of the classifier to learn joint class distributions. We demonstrate the time advantage compared to physics tools, with the classifier achieving orders of magnitude faster checks on groups of constraints and strong performance. The classifier performed strongly in terms of identifying regions where all constraints are valid or invalid, as well as regions where one or more of the constraints are valid or invalid simultaneously. This approach can be applied to any extension beyond the SM with the potential to aid HEP tools or act as a surrogate for fast model status checks. To that end, we provide a python tool \texttt{HEPMLC} for generating and investigating multilabel classifiers for SM extensions.
Changed the title and improved the manuscript throughout. Accepted in Physical Review D
References in corpus (68)
- Theory and phenomenology of two-Higgs-doublet models
- Machine learning and the physical sciences
- SARAH 4: A tool for (not only SUSY) model builders
- Improved Naturalness with a Heavy Higgs: An Alternative Road to LHC Physics
- The Inert Doublet Model: an Archetype for Dark Matter
- ParticleNet: Jet Tagging via Particle Clouds
- A portrait of the Higgs boson by the CMS experiment ten years after the discovery
- A detailed map of Higgs boson interactions by the ATLAS experiment ten years after the discovery
- Deep Learning and its Application to LHC Physics
- The oblique parameters in multi-Higgs-doublet models
- Update of the global electroweak fit and constraints on two-Higgs-doublet models
- The MSSM Parameter Space with Non-Universal Higgs Masses
- A precision constraint on multi-Higgs-doublet models
- HiggsBounds-5: Testing Higgs Sectors in the LHC 13 TeV Era
- NMSSM Higgs Benchmarks Near 125 GeV
- HiggsSignals-2: Probing new physics with precision Higgs measurements in the LHC 13 TeV era
- Exploring new models in all detail with SARAH
- Anatomy of the Inert Two Higgs Doublet Model in the light of the LHC and non-LHC Dark Matter Searches
- An Updated Analysis of Inert Higgs Doublet Model in light of the Recent Results from LUX, PLANCK, AMS-02 and LHC
- Status of the scalar singlet dark matter model
- Natural Dark Matter from an Unnatural Higgs Boson and New Colored Particles at the TeV Scale
- The CMSSM and NUHM1 in Light of 7 TeV LHC, B_s to mu+mu- and XENON100 Data
- Building and testing models with extended Higgs sectors
- Updated Constraints on the Minimal Supergravity Model
- Updated Constraints on the Minimal Supergravity Model
- Status of the two-Higgs-doublet model of type II
- The N2HDM under Theoretical and Experimental Scrutiny
- A new viable region of the inert doublet model
- Machine and Deep Learning Applications in Particle Physics
- LHC constraints on two-Higgs doublet models
- Tree-unitarity bounds for THDM Higgs masses revisited
- Benchmark scenarios for the NMSSM
- Recasting direct detection limits within micrOMEGAs and implication for non-standard Dark Matter scenarios
- Updated Constraints from B Physics on the MSSM and the NMSSM
- Extending two-Higgs-doublet models by a singlet scalar field - the Case for Dark Matter
- The Next-to-Minimal Two Higgs Doublet Model
- The pMSSM10 after LHC Run 1
- Unitarity constraints on general scalar couplings with SARAH
- The BSM-AI project: SUSY-AI - Generalizing LHC limits on Supersymmetry with Machine Learning
- Interaction networks for the identification of boosted decays
- Midi-review: Status of weak scale supersymmetry after LHC Run 2 and ton-scale noble liquid WIMP searches
- Impact of Vacuum Stability Constraints on the Phenomenology of Supersymmetric Models
- Fate of electroweak symmetry in the early Universe: Non-restoration and trapped vacua in the N2HDM
- Supervised deep learning in high energy phenomenology: a mini review
- N2HDECAY: Higgs Boson Decays in the Different Phases of the N2HDM
- The constrained next-to-minimal supersymmetric standard model
- Vacuum Instabilities in the N2HDM
- Constraining the Parameters of High-Dimensional Models with Active Learning
- Reopen parameter regions in Two-Higgs Doublet Models
- Efficient sampling of constrained high-dimensional theoretical spaces with machine learning
- Perturbativity Constraints in BSM Models
- Improved unitarity constraints in Two-Higgs-Doublet-Models
- Deep learning for the R-parity violating supersymmetry searches at the LHC
- The CMSSM Survives Planck, the LHC, LUX-ZEPLIN, Fermi-LAT, H.E.S.S. and IceCube
- Exploring Parameter Spaces with Artificial Intelligence and Machine Learning Black-Box Optimisation Algorithms
- Unitarity constraints in triplet extensions beyond the large s limit
- Deep Learning Jet Image as a Probe of Light Higgsino Dark Matter at the LHC
- A Novel Scenario in the Semi-constrained NMSSM
- Theoretical Constraints on Supersymmetric Models: Perturbative Unitarity vs. Vacuum Stability
- Deep learnig analysis of the inverse seesaw in a 3-3-1 model at the LHC
- Search for Mono-Higgs Signals in Final States Using Deep Neural Networks
- Phenomenology of extension of inert-doublet model with exotic scalars and leptons
- Dark matter in Inert Doublet Model with one scalar singlet and gauge symmetry
- Electroweak Corrections to Dark Matter Direct Detection in the Dark Singlet Phase of the N2HDM
- Probing intractable beyond-standard-model parameter spaces armed with Machine Learning
- Using Machine Learning techniques in phenomenological studies in flavour physics
- Invisible dark matter decays of a non-Standard Model like CP-even scalar boson
- Upper limit on dark matter mass in the inert doublet model