Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

Abstract

We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic way. The execution of existing simulators as probabilistic programs enables highly interpretable posterior inference in the structured model defined by the simulator code base. We demonstrate the technique in particle physics, on a scientifically accurate simulation of the tau lepton decay, which is a key ingredient in establishing the properties of the Higgs boson. Inference efficiency is achieved via inference compilation where a deep recurrent neural network is trained to parameterize proposal distributions and control the stochastic simulator in a sequential importance sampling scheme, at a fraction of the computational cost of a Markov chain Monte Carlo baseline.

arXiv comment20 pages, 9 figures

References in corpus (39)

• Auto-Encoding Variational Bayes
• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• MCMC using Hamiltonian dynamics
• Event generation with SHERPA 1.1
• Herwig++ Physics and Manual
• Variational Inference with Normalizing Flows
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Church: a language for generative models
• Spin determination of single-produced resonances at hadron colliders
• Jet Substructure at the Large Hadron Collider: Experimental Review
• On the spin and parity of a single-produced resonance at the LHC
• A Precision Measurement of the Mass of the Top Quark
• Matrix Elements and Parton Showers in Hadronic Interactions
• A Convolutional Neural Network Neutrino Event Classifier
• Edward: A library for probabilistic modeling, inference, and criticism
• Constraining anomalous Higgs boson couplings to the heavy flavor fermions using matrix element techniques
• A Guide to Constraining Effective Field Theories with Machine Learning
• Finding physics signals with shower deconstruction
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• Measuring CP Violation in $h\to {\tau }^{+}{\tau }^{-}$ at Colliders
• Reconstruction of hadronic decay products of tau leptons with the ATLAS experiment
• The Matrix Element Method and QCD Radiation
• Unravelling $t\bar{t}h$ via the matrix element method
• Precision studies of the Higgs boson decay channel H -> ZZ -> 4l with MEKD
• Extending the Matrix Element Method beyond the Born approximation: Calculating event weights at next-to-leading order accuracy
• Polishing a shiny Higgs with matrix elements
• Simple, Distributed, and Accelerated Probabilistic Programming
• On Nesting Monte Carlo Estimators
• Finding the Higgs boson in decays to Z gamma using the matrix element method at Next-to-Leading Order
• Inference Compilation and Universal Probabilistic Programming
• The Matrix Element Method at next-to-leading order QCD for hadronic collisions: Single top-quark production at the LHC as an example application
• Accelerated Matrix Element Method with Parallel Computing
• Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators
• Boosted Top Tagging Method Overview
• Amortized Rejection Sampling in Universal Probabilistic Programming