Exploration of Parameter Spaces Assisted by Machine Learning

Abstract

We demonstrate two sampling procedures assisted by machine learning models via regression and classification. The main objective is the use of a neural network to suggest points likely inside regions of interest, reducing the number of evaluations of time consuming calculations. We compare results from this approach with results from other sampling methods, namely Markov chain Monte Carlo and MultiNest, obtaining results that range from comparably similar to arguably better. In particular, we augment our classifier method with a boosting technique that rapidly increases the efficiency within a few iterations. We show results from our methods applied to a toy model and the type II 2HDM, using 3 and 7 free parameters, respectively. The code used for this paper and instructions are publicly available on the web.

30 pages, 9 figures. Matches published version. Code and instructions are available on https://github.com/AHamamd150/MLscanner

References in corpus (22)

• SMOTE: Synthetic Minority Over-sampling Technique
• emcee: The MCMC Hammer
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• Theory and phenomenology of two-Higgs-doublet models
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• X-ray spectral modelling of the AGN obscuring region in the CDFS: Bayesian model selection and catalogue
• 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
• HiggsBounds 2.0.0: Confronting Neutral and Charged Higgs Sector Predictions with Exclusion Bounds from LEP and the Tevatron
• The Electroweak Fit of the Standard Model after the Discovery of a New Boson at the LHC
• Averages of $b$-hadron, $c$-hadron, and $\tau$-lepton properties as of 2018
• Constraining Effective Field Theories with Machine Learning
• A Flavor Kit for BSM models
• A Guide to Constraining Effective Field Theories with Machine Learning
• GAMBIT: The Global and Modular Beyond-the-Standard-Model Inference Tool
• Likelihood Analysis of the pMSSM11 in Light of LHC 13-TeV Data
• Fittino, a program for determining MSSM parameters from collider observables using an iterative method
• Status of CMSSM in light of current LHC Run-2 and LUX data
• Sampling using a `bank' of clues
• Constraining the Parameters of High-Dimensional Models with Active Learning
• Picking the low-hanging fruit: testing new physics at scale with active learning

Cited by in corpus (4)

• 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 the BSM parameter space with Neural Network aided Simulation-Based Inference