Active learning BSM parameter spaces

Abstract

Active learning (AL) has interesting features for parameter scans of new models. We show on a variety of models that AL scans bring large efficiency gains to the traditionally tedious work of finding boundaries for BSM models. In the MSSM, this approach produces more accurate bounds. In light of our prior publication, we further refine the exploration of the parameter space of the SMSQQ model, and update the maximum mass of a dark matter singlet to 48.4 TeV. Finally we show that this technique is especially useful in more complex models like the MDGSSM.

arXiv comment29 pages, 9 figures, 9 tables

References in corpus (63)

• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• SPheno, a program for calculating supersymmetric spectra, SUSY particle decays and SUSY particle production at e+ e- colliders
• SARAH 4: A tool for (not only SUSY) model builders
• SPheno 3.1: extensions including flavour, CP-phases and models beyond the MSSM
• HiggsBounds: Confronting Arbitrary Higgs Sectors with Exclusion Bounds from LEP and the Tevatron
• HiggsSignals: Confronting arbitrary Higgs sectors with measurements at the Tevatron and the LHC
• SUSY Les Houches Accord: Interfacing SUSY Spectrum Calculators, Decay Packages, and Event Generators
• micrOMEGAs5.0 : freeze-in
• SUSY Les Houches Accord 2
• The MSSM Parameter Space with Non-Universal Higgs Masses
• A determination of parton distributions with faithful uncertainty estimation
• HiggsBounds-5: Testing Higgs Sectors in the LHC 13 TeV Era
• Implications of unitarity and gauge invariance for simplified dark matter models
• The Machine Learning Landscape of Top Taggers
• HiggsSignals-2: Probing new physics with precision Higgs measurements in the LHC 13 TeV era
• Bound-state formation for thermal relic dark matter and unitarity
• Revisiting the Higgs Mass and Dark Matter in the CMSSM
• Vevacious: A Tool For Finding The Global Minima Of One-Loop Effective Potentials With Many Scalars
• GAMBIT: The Global and Modular Beyond-the-Standard-Model Inference Tool
• FlexibleSUSY 2.0: Extensions to investigate the phenomenology of SUSY and non-SUSY models
• Machine Learning in the String Landscape
• Recasting direct detection limits within micrOMEGAs and implication for non-standard Dark Matter scenarios
• Higgs-mass predictions in the MSSM and beyond
• Prediction for the Lightest Higgs Boson Mass in the CMSSM using Indirect Experimental Constraints
• Constraining new physics with SModelS version 2
• Understanding Event-Generation Networks via Uncertainties
• Unitarity constraints on general scalar couplings with SARAH
• Asymmetric thermal-relic dark matter: Sommerfeld-enhanced freeze-out, annihilation signals and unitarity bounds
• Comparison of statistical sampling methods with ScannerBit, the GAMBIT scanning module
• Radiative bound-state formation in unbroken perturbative non-Abelian theories and implications for dark matter
• Supersymmetric and non-supersymmetric models without catastrophic Goldstone bosons
• Deep-Learning Jets with Uncertainties and More
• SpecBit, DecayBit and PrecisionBit: GAMBIT modules for computing mass spectra, particle decay rates and precision observables
• Gravitational Wave Signals of Pseudo-Goldstone Dark Matter in the ${\mathbb{Z}}_3$ Complex Singlet Model
• Publishing statistical models: Getting the most out of particle physics experiments
• The SM extension with color-octet scalars: diphoton enhancement and global fit of LHC Higgs data
• Simplified Phenomenology for Colored Dark Sectors
• GANs for generating EFT models
• A deep neural network for simultaneous estimation of b jet energy and resolution
• Improved bounds on ${\mathbb{Z}}_3$ singlet dark matter
• Forbidden frozen-in dark matter
• Constraining the Parameters of High-Dimensional Models with Active Learning
• Pseudo-Goldstone dark matter: gravitational waves and direct-detection blind spots
• Update on the Direct Detection of Dark Matter in MSSM Models with Non-Universal Higgs Masses
• Unitarity and vacuum stability constraints on the couplings of color octet scalars
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• Simple and statistically sound recommendations for analysing physical theories
• LHC limits on gluinos and squarks in the minimal Dirac gaugino model
• The GAMBIT Universal Model Machine: from Lagrangians to Likelihoods
• Has the Origin of the Third-Family Fermion Masses been Determined?
• Constraining Electroweakinos in the Minimal Dirac Gaugino Model
• Bayesian Neural Networks for Fast SUSY Predictions
• Global Analysis of Dark Matter Simplified Models with Leptophobic Spin-One Mediators using MasterCode
• The Higgs Mass in the MSSM at two-loop order beyond minimal flavour violation
• New theoretical constraints on scalar color octet models
• Signal region combination with full and simplified likelihoods in MadAnalysis 5
• Parametrizing the Detector Response with Neural Networks
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• Theoretical Constraints on Supersymmetric Models: Perturbative Unitarity vs. Vacuum Stability
• How heavy can dark matter be? Constraining colourful unitarity with SARAH
• Cornering Colored Coannihilation
• Heavy dark matter through the dilaton portal
• Picking the low-hanging fruit: testing new physics at scale with active learning

Cited by in corpus (6)

• Combining Evolutionary Strategies and Novelty Detection to go Beyond the Alignment Limit of the $Z_3$ 3HDM
• Probing intractable beyond-standard-model parameter spaces armed with Machine Learning
• Bayesian Active Search on Parameter Space: a 95 GeV Spin-0 Resonance in the ($B-L$)SSM
• Exploring Scotogenic Parameter Spaces and Mapping Uncharted Dark Matter Phenomenology with Multi-Objective Search Algorithms
• Exploring the BSM parameter space with Neural Network aided Simulation-Based Inference
• Graph Reinforcement Learning for Exploring BSM Model Spaces