Probing intractable beyond-standard-model parameter spaces armed with Machine Learning

Abstract

This article attempts to summarize the effort by the particle physics community in addressing the tedious work of determining the parameter spaces of beyond-the-standard-model (BSM) scenarios, allowed by data. These spaces, typically associated with a large number of dimensions, especially in the presence of nuisance parameters, suffer from the curse of dimensionality and thus render naive sampling of any kind -- even the computationally inexpensive ones -- ineffective. Over the years, various new sampling (from variations of Markov Chain Monte Carlo (MCMC) to dynamic nested sampling) and machine learning (ML) algorithms have been adopted by the community to alleviate this issue. If not all, we discuss potentially the most important among them and the significance of their results, in detail.

arXiv commentThis is an invited review on ML in HEP which is to appear in EPJST

References in corpus (46)

• SMOTE: Synthetic Minority Over-sampling Technique
• emcee: The MCMC Hammer
• MCMC using Hamiltonian dynamics
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• SPheno, a program for calculating supersymmetric spectra, SUSY particle decays and SUSY particle production at e+ e- colliders
• SPheno 3.1: extensions including flavour, CP-phases and models beyond the MSSM
• 2020 Global reassessment of the neutrino oscillation picture
• Automatic Calculation of supersymmetric Renormalization Group Equations and Self Energies
• Averages of $b$-hadron, $c$-hadron, and $\tau$-lepton properties as of 2018
• A Nested Sampling Algorithm for Cosmological Model Selection
• Dynamic temperature selection for parallel-tempering in Markov chain Monte Carlo simulations
• Exploring new models in all detail with SARAH
• Search for CP violation in Neutrino and Antineutrino Oscillations by the T2K experiment with $2.2\times 10^{21}$ protons on target
• Sneutrino Mixing Phenomena
• Nested sampling for physical scientists
• GAMBIT: The Global and Modular Beyond-the-Standard-Model Inference Tool
• A Bayesian model selection analysis of WMAP3
• $\text{HEPfit}$: a Code for the Combination of Indirect and Direct Constraints on High Energy Physics Models
• Analysis of neutral $B$-meson decays into two muons
• Electroweak Precision Fit and New Physics in light of $W$ Boson Mass
• A frequentist analysis of three right-handed neutrinos with GAMBIT
• Neutrino masses in R-parity violating supersymmetric models
• Atmospheric Neutrino Oscillation Analysis With Improved Event Reconstruction in Super-Kamiokande IV
• Global analysis of electroweak data in the Standard Model
• The electro-weak couplings of the top and bottom quarks -- global fit and future prospects
• Machine Learning for Anomaly Detection in Particle Physics
• $b\to c\tau {\nu }_{\tau }$ Decays: A Catalogue to Compare, Constrain, and Correlate New Physics Effects
• Deep learning in the heterotic orbifold landscape
• Cosmological constraints on decaying axion-like particles: a global analysis
• A Step Toward Model Comparison: Connecting Electroweak-Scale Observables to BSM through EFT and Bayesian Statistics
• Constraining the Parameters of High-Dimensional Models with Active Learning
• Electron and muon magnetic moments and implications for dark matter and model characterisation in non-universal $U(1{)}^{\prime }$ supersymmetric models
• Efficient sampling of constrained high-dimensional theoretical spaces with machine learning
• Neutrino masses and R-parity violation
• The GAMBIT Universal Model Machine: from Lagrangians to Likelihoods
• Updated global fit of the aligned two-Higgs-doublet model with heavy scalars
• Exploration of Parameter Spaces Assisted by Machine Learning
• Global fits of simplified models for dark matter with GAMBIT I. Scalar and fermionic models with s-channel vector mediators
• Active learning BSM parameter spaces
• Bilinear R-parity violating supersymmetry under the light of neutrino oscillation, higgs and flavor data
• Global fits of simplified models for dark matter with GAMBIT II. Vector dark matter with an $s$-channel vector mediator
• A detailed study of the ${\Lambda }_b\to \Lambda {\ell }^{+}{\ell }^{-}$ decays in the Standard Model
• Complete analysis of all $B\to \pi K$ decays
• Machine-Learning the Classification of Spacetimes

Cited by in corpus (3)

• Bayesian Active Search on Parameter Space: a 95 GeV Spin-0 Resonance in the ($B-L$)SSM
• Fast multilabel classification of HEP constraints with deep learning
• Universal New Physics Latent Space