Bayesian Neural Networks for Fast SUSY Predictions

One of the goals of current particle physics research is to obtain evidence for new physics, that is, physics beyond the Standard Model (BSM), at accelerators such as the Large Hadron Collider (LHC) at CERN. The searches for new physics are often guided by BSM theories that depend on many unknown parameters, which, in some cases, makes testing their predictions difficult. In this paper, machine learning is used to model the mapping from the parameter space of the phenomenological Minimal Supersymmetric Standard Model (pMSSM), a BSM theory with 19 free parameters, to some of its predictions. Bayesian neural networks are used to predict cross sections for arbitrary pMSSM parameter points, the mass of the associated lightest neutral Higgs boson, and the theoretical viability of the parameter points. All three quantities are modeled with average percent errors of 3.34% or less and in a time significantly shorter than is possible with the supersymmetry codes from which the results are derived. These results are a further demonstration of the potential for machine learning to model accurately the mapping from the high dimensional spaces of BSM theories to their predictions.

[1]  W. Fawcett.  pMSSM studies with ATLAS and CMS , 2016 .

[2]  P. Bhat.  Multivariate Analysis Methods in Particle Physics , 2011 .

[3]  R. E. Hall,et al.  Observation of single top-quark production. , 2009, Physical review letters.

[4]  Federico Ambrogi,et al.  On the coverage of the pMSSM by simplified model results , 2017, The European Physical Journal C.

[5]  Philip Bechtle,et al.  SCYNet: testing supersymmetric models at the LHC with neural networks , 2017, The European Physical Journal C.

[6]  P. Alam.  ‘T’ , 2021, Composites Engineering: An A–Z Guide.

[7]  James O. Berger,et al.  Overall Objective Priors , 2015, 1504.02689.

[8]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[9]  James O. Berger,et al.  The interplay of Bayesian and frequentist analysis , 2004 .

[10]  B. C. Allanach,et al.  SOFTSUSY: A program for calculating supersymmetric spectra☆ , 2001, hep-ph/0104145.

[11]  Tom Heskes,et al.  Constraining the parameters of high-dimensional models with active learning , 2019, The European Physical Journal C.

[12]  Tilman Plehn,et al.  Production of Charginos, Neutralinos, and Sleptons at Hadron Colliders , 1999 .

[13]  K. Griest,et al.  Supersymmetric dark matter , 1992 .

[14]  S. M. Etesami,et al.  Phenomenological MSSM interpretation of CMS searches in pp collisions at s=7$$ \sqrt{s}=7 $$ and 8 TeV , 2016, 1606.03577.

[15]  The Minimal Supersymmetric Standard Model: Group Summary Report , 1999, hep-ph/9901246.

[16]  Naftali Tishby,et al.  Machine learning and the physical sciences , 2019, Reviews of Modern Physics.

[17]  M. P. Casado,et al.  Summary of the ATLAS experiment’s sensitivity to supersymmetry after LHC Run 1 — interpreted in the phenomenological MSSM , 2015, 1508.06608.

[18]  Éric Gaussier,et al.  A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation , 2005, ECIR.

[19]  Scoap.  The BSM-AI project: SUSY-AI–generalizing LHC limits on supersymmetry with machine learning , 2017 .

[20]  Ryszard S. Romaniuk,et al.  Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC , 2012 .

[21]  C. Quigg.  Electroweak Symmetry Breaking in Historical Perspective , 2015, 1503.01756.

[22]  J. Hewett,et al.  Lessons and prospects from the pMSSM after LHC Run I , 2014, 1407.4130.

[23]  J. Hewett,et al.  Supersymmetry Without Prejudice , 2008, 0812.0980.

[24]  K. Cranmer,et al.  MadMiner: Machine Learning-Based Inference for Particle Physics , 2019, Computing and Software for Big Science.

[25]  R. Siezen,et al.  others , 1999, Microbial Biotechnology.

[26]  T. Severini.  Likelihood Methods in Statistics , 2001 .

[27]  C. Englert,et al.  Higgs physics: It ain’t over till it is over , 2018, Physics Reports.

[28]  P. Alam,et al.  R , 1823, The Herodotus Encyclopedia.

[29]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[30]  Sascha Caron,et al.  The BSM-AI project: SUSY-AI–generalizing LHC limits on supersymmetry with machine learning , 2016, The European Physical Journal C.

[31]  J. Hewett,et al.  Constraints on Higgs Properties and SUSY Partners in the pMSSM , 2013, 1308.0297.

[32]  Y. Meng,et al.  Applying Bayesian neural networks to separate neutrino events from backgrounds in reactor neutrino experiments , 2008, 0808.0240.

[33]  Roderick Little,et al.  Calibrated Bayes, for Statistics in General, and Missing Data in Particular , 2011, 1108.1917.

[34]  G De Lorenzo,et al.  Observation of electroweak single top-quark production. , 2009, Physical review letters.

[35]  P. Barria,et al.  First Observation of Elec-troweak Single Top Quark Production , 2009 .

[36]  Jaehoon Lee,et al.  Deep Neural Networks as Gaussian Processes , 2017, ICLR.

[37]  B. Schmidt.  The High-Luminosity upgrade of the LHC: Physics and Technology Challenges for the Accelerator and the Experiments , 2016 .

[38]  J. Lykken,et al.  Interpreting LHC SUSY searches in the phenomenological MSSM , 2011, 1109.5119.

[39]  Gorjan Alagic,et al.  #p , 2019, Quantum information & computation.

[40]  Gilles Louppe,et al.  A guide to constraining effective field theories with machine learning , 2018, Physical Review D.