CWoLa Hunting: Extending the Bump Hunt with Machine Learning

The oldest and most robust technique to search for new particles is to look for `bumps' in invariant mass spectra over smoothly falling backgrounds. This is a powerful technique, but only uses one-dimensional information. One can restrict the phase space to enhance a potential signal, but such tagging techniques require a signal hypothesis and training a classifier in simulation and applying it on data. We present a new method for using all of the available information (with machine learning) without using any prior knowledge about potential signals. Given the lack of new physics signals at the Large Hadron Collider (LHC), such model independent approaches are critical for ensuring full coverage to fully exploit the rich datasets from the LHC experiments. In addition to illustrating how the new method works in simple test cases, we demonstrate the power of the extended bump hunt on a realistic all-hadronic resonance search in a channel that would not be covered with existing techniques.

[1]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[2]  P. Harris,et al.  Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure , 2016, 1603.00027.

[3]  Quark versus Gluon Jet Tagging Using Charged-Particle Constituent Multiplicity with the ATLAS Detector The ATLAS , 2017 .

[4]  E. Dawe,et al.  Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks , 2016, 1609.00607.

[5]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[6]  J. A. Aguilar-Saavedra Stealth multiboson signals , 2017, 1705.07885.

[7]  Patrick T. Komiske,et al.  Deep learning in color: towards automated quark/gluon jet discrimination , 2016, Journal of High Energy Physics.

[8]  M. Cacciari,et al.  The anti-$k_t$ jet clustering algorithm , 2008, 0802.1189.

[9]  Pierre Baldi,et al.  Decorrelated jet substructure tagging using adversarial neural networks , 2017, Physical Review D.

[10]  Atlas Collaboration,et al.  Performance of top-quark and $$\varvec{W}$$ W -boson tagging with ATLAS in Run 2 , 2018, The European Physical Journal C.

[11]  Atlas Collaboration Light-quark and gluon jet discrimination in pp collisions at $\sqrt{s}$ = 7 TeV with the ATLAS detector , 2014, 1405.6583.

[12]  R. Frederix,et al.  The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations , 2014, 1405.0301.

[13]  A General search for new phenomena in ep scattering at HERA , 2004 .

[14]  R. Sundrum,et al.  Flavor universal resonances and warped gravity , 2016, 1608.00526.

[15]  J. Sculli,et al.  Search for new physics in aμX data at DØ using SLEUTH: A quasi-model-independent search strategy for new physics , 2000 .

[16]  J. Favereau,et al.  DELPHES 3: a modular framework for fast simulation of a generic collider experiment , 2013, Journal of High Energy Physics.

[17]  K. Cranmer,et al.  Asymptotic formulae for likelihood-based tests of new physics , 2010, 1007.1727.

[18]  J. A. Aguilar-Saavedra,et al.  A generic anti-QCD jet tagger , 2017, 1709.01087.

[19]  J. A. Aguilar-Saavedra Running bumps from stealth bosons , 2018, 1801.08129.

[20]  G. Soyez,et al.  Soft drop , 2014, 1402.2657.

[21]  Tatsumi Nitta,et al.  Identification of Hadronically-Decaying W Boson Top Quarks Using High-Level Features as Input to Boosted Decision Trees and Deep Neural Networks in ATLAS at #sqrt{s} = 13 TeV , 2017 .

[22]  Leandro Giordano Almeida,et al.  Playing tag with ANN: boosted top identification with pattern recognition , 2015, 1501.05968.

[23]  P. Baldi,et al.  Jet Substructure Classification in High-Energy Physics with Deep Neural Networks , 2016, 1603.09349.

[24]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[25]  M. Cacciari,et al.  FastJet user manual , 2011, 1111.6097.

[26]  J. Cogan,et al.  Jet-images: computer vision inspired techniques for jet tagging , 2014, 1407.5675.

[27]  B. Nachman,et al.  Classification without labels: learning from mixed samples in high energy physics , 2017, Journal of High Energy Physics.

[28]  T. Hebbeker,et al.  Model unspecific search for new physics in pp collision at $\sqrt{ s} {=} {7}$ TeV , 2012 .

[29]  Vm Joint Nucl Res Inst Dubna Russia. Abazov,et al.  Quasi-model-independent search for new physics at large transverse momentum , 2001 .

[30]  G. Kasieczka,et al.  Deep-learning top taggers or the end of QCD? , 2017, 1701.08784.

[31]  A. Larkoski,et al.  Novel jet observables from machine learning , 2017, 1710.01305.

[32]  Georgios Choudalakis,et al.  On hypothesis testing, trials factor, hypertests and the BumpHunter , 2011, 1101.0390.

[33]  J. Thaler,et al.  Maximizing boosted top identification by minimizing N-subjettiness , 2011, 1108.2701.

[34]  Peter Skands,et al.  A brief introduction to PYTHIA 8.1 , 2007, Comput. Phys. Commun..

[35]  Heavy flavor identification at CMS with deep neural networks , 2017 .

[36]  Zihao Jiang,et al.  Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment , 2017 .

[37]  Boosted Higgs ( → bb̄ ) Boson Identification with the ATLAS Detector at √ s = 13 TeV , 2016 .

[38]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[39]  A. Larkoski,et al.  How much information is in a jet? , 2017, Journal of High Energy Physics.

[40]  Gilles Louppe,et al.  Learning to Pivot with Adversarial Networks , 2016, NIPS.

[41]  M. L. Stevenson,et al.  Pion-Pion Interaction in the Reaction p ¯ + p → 2 π + + 2 π − + n π 0 , 1962 .

[42]  L. Dery,et al.  Weakly supervised classification in high energy physics , 2017, Journal of High Energy Physics.