Invisible Higgs search through Vector Boson Fusion: A deep learning approach

Abstract

Vector boson fusion proposed initially as an alternative channel for finding heavy Higgs has now established itself as a crucial search scheme to probe different properties of the Higgs boson or for new physics. We explore the merit of deep-learning entirely from the low-level calorimeter data in the search for invisibly decaying Higgs. Such an effort supersedes decades-old faith in the remarkable event kinematics and radiation pattern as a signature to the absence of any color exchange between incoming partons in the vector boson fusion mechanism. We investigate among different neural network architectures, considering both low-level and high-level input variables as a detailed comparative analysis. To have a consistent comparison with existing techniques, we closely follow a recent experimental study of CMS search on invisible Higgs with 36 fb${}^{-1}$ data. We find that sophisticated deep-learning techniques have the impressive capability to improve the bound on invisible branching ratio by a factor of three, utilizing the same amount of data. Without relying on any exclusive event reconstruction, this novel technique can provide the most stringent bounds on the invisible branching ratio of the SM-like Higgs boson. Such an outcome has the ability to constraint many different BSM models severely.

arXiv commentIncluded estimation of pixelwise energy uncertainty, minor changes in text and updated references. Accepted for publication in EPJC

References in corpus (104)

• The NumPy array: a structure for efficient numerical computation
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Geometric deep learning: going beyond Euclidean data
• Asymptotic formulae for likelihood-based tests of new physics
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• FeynRules 2.0 - A complete toolbox for tree-level phenomenology
• Confidence Level Computation for Combining Searches with Small Statistics
• Jet substructure as a new Higgs search channel at the LHC
• Pileup subtraction using jet areas
• Jet energy scale and resolution in the CMS experiment in pp collisions at 8 TeV
• Implications of LHC searches for Higgs--portal dark matter
• Towards Jetography
• N-Jettiness: An Inclusive Event Shape to Veto Jets
• Deep Learning and its Application to LHC Physics
• Strong and electroweak corrections to the production of Higgs+2jets via weak interactions at the LHC
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Techniques for improved heavy particle searches with jet substructure
• Fully differential VBF Higgs production at NNLO
• Determining the Structure of Higgs Couplings at the LHC
• Jet Substructure at the Large Hadron Collider: Experimental Review
• Classification without labels: Learning from mixed samples in high energy physics
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Graviscalars from higher-dimensional metrics and curvature-Higgs mixing
• Search for invisible decays of a Higgs boson produced through vector boson fusion in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Deep-learning Top Taggers or The End of QCD?
• Direct detection of Higgs-portal dark matter at the LHC
• Structure Function Approach to Vector-Boson Scattering in pp Collisions
• Observing an invisible Higgs boson
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• A Convolutional Neural Network Neutrino Event Classifier
• Next-to-leading order jet distributions for Higgs boson production via weak-boson fusion
• Dark Matter through the Higgs portal
• Anomalous Higgs boson couplings in vector boson fusion at the CERN LHC
• Searching for H --> tau tau in weak boson fusion at the LHC
• Deep-learned Top Tagging with a Lorentz Layer
• Vector-boson fusion Higgs production at N${}^3$LO in QCD
• Jet p_T Resummation in Higgs Production at NNLL'+NNLO
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Graph Neural Networks in Particle Physics
• Observing H -> W*W* -> e mu pT(miss) in weak boson fusion with dual forward jet tagging at the LHC
• Higgs Portal Vector Dark Matter : Revisited
• Precise predictions for V+jets dark matter backgrounds
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Searching for H -> gamma gamma in weak boson fusion at the LHC
• Machine and Deep Learning Applications in Particle Physics
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Guiding New Physics Searches with Unsupervised Learning
• The Metric Space of Collider Events
• QCD-Aware Recursive Neural Networks for Jet Physics
• Pileup Mitigation with Machine Learning (PUMML)
• Higgs plus two jet production via gluon fusion as a signal at the CERN LHC
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Boosting $H\to b\bar{b}$ with Machine Learning
• Invisible Higgs Boson Decay into Massive Neutrinos of 4th Generation
• The MSSM invisible Higgs in the light of dark matter and g-2
• How Much Information is in a Jet?
• Particle-level pileup subtraction for jets and jet shapes
• Probing Dark Matter at the LHC using Vector Boson Fusion Processes
• QCD corrections to electroweak l nu_l jj and l^+ l^- jj production
• Search for the standard model Higgs boson produced through vector boson fusion and decaying to b bbar
• Probing stop pair production at the LHC with graph neural networks
• Search for invisible Higgs boson decays in vector boson fusion at $\sqrt{s}=13$ TeV with the ATLAS detector
• Probing Electroweak Precision Physics via boosted Higgs-strahlung at the LHC
• Collider Signatures of Higgs-portal Scalar Dark Matter
• Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
• Supervised deep learning in high energy phenomenology: a mini review
• The Hidden Geometry of Particle Collisions
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Nonfactorizable QCD Effects in Higgs Boson Production via Vector Boson Fusion
• Jet substructure shedding light on heavy Majorana neutrinos at the LHC
• Spying an invisible Higgs
• Rapidity gap signals in Higgs production at the SSC
• Portraying Double Higgs at the Large Hadron Collider
• Invisible charginos and neutralinos from gauge boson fusion : a way to explore anomaly mediation ?
• Looking for Minimal Inverse Seesaw scenarios at the LHC with Jet Substructure Techniques
• Search for electroweak production of a vector-like quark decaying to a top quark and a Higgs boson using boosted topologies in fully hadronic final states
• Probing the inert doublet model using jet substructure with a multivariate analysis
• Graviton production with 2 jets at the LHC in large extra dimensions
• Neutralinos in Vector Boson Fusion at High Energy Colliders
• Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
• Higgs self-coupling measurements using deep learning in the $b\bar{b}b\bar{b}$ final state
• Deep learning for the R-parity violating supersymmetry searches at the LHC
• Looking for hints of a reconstructible seesaw model at the Large Hadron Collider
• CapsNets Continuing the Convolutional Quest
• New Physics Opportunities in the Boosted Di-Higgs plus \ET Signature
• Production of a Higgs pseudoscalar plus two jets in hadronic collisions
• Signals of neutralinos and charginos from gauge boson fusion at the CERN Large Hadron Collider
• Slepton production from gauge boson fusion
• Measuring the CP property of Higgs coupling to tau leptons in the VBF channel at the LHC
• Next-to-leading order QCD corrections to slepton pair production via vector-boson fusion
• Exploring a heavy charged Higgs using jet substructure in a fully hadronic channel
• Tagging Jets in Invisible Higgs Searches
• Beyond $M_{t\bar{t}}$: learning to search for a broad $t\bar{t}$ resonance at the LHC
• Preserving physically important variables in optimal event selections: A case study in Higgs physics
• New Higgs signals from vector boson fusion in R-parity violating supersymmetry
• Boosted jet techniques for a supersymmetric scenario with gravitino LSP
• Gauge boson fusion as a probe of inverted hierarchies in supersymmetry
• Probing Exotic Triple Higgs Couplings at the LHC

Cited by in corpus (9)

• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Higgs boson tagging with the Lund jet plane
• Disentangling Boosted Higgs Boson Production Modes with Machine Learning
• Exotic Higgs decays into displaced jets at the LHeC
• Role of polarizations and spin-spin correlations of $W^{\prime }s$ in $e^{-}{e}^{+}\to W^{-}{W}^{+}$ at $\sqrt{s}=250$ GeV to probe anomalous $W^{-}{W}^{+}Z/\gamma$ couplings
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Influence of QCD parton shower in deep learning invisible Higgs through vector boson fusion
• One-loop contributions to the decay $H\to {\nu }_l{\bar{\nu }}_l\gamma$ in standard model revisited
• Indian Contributions to LHC Theory