Observable Optimization for Precision Theory: Machine Learning Energy Correlators

Abstract

The practice of collider physics typically involves the marginalization of multi-dimensional collider data to uni-dimensional observables relevant for some physics task. In any cases, such as classification or anomaly detection, the observable can be arbitrarily complicated, such as the output of a neural network. However, for precision measurements, the observable must correspond to something computable systematically beyond the level of current simulation tools. In this work, we demonstrate that precision-theory-compatible observable space exploration can be systematized by using neural simulation-based inference techniques from machine learning. We illustrate this approach by exploring the space of marginalizations of the energy 3-point correlator to optimize sensitivity to the the top quark mass. We first learn the energy-weighted probability density from simulation, then search in the space of marginalizations for an optimal triangle shape. Although simulations and machine learning are used in the process of observable optimization, the output is an observable definition which can be then computed to high precision and compared directly to data without any memory of the computations which produced it. We find that the optimal marginalization is isosceles triangles on the sphere with a side ratio approximately $1:1:\sqrt{2}$ (i.e. right triangles) within the set of marginalizations we consider.

32 pages, 11 figures, 1 appendix; Published version uploaded with additional acknowledgements

References in corpus (81)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Herwig++ Physics and Manual
• Dispelling the N^3 myth for the Kt jet-finder
• Conformal collider physics: Energy and charge correlations
• General-purpose event generators for LHC physics
• Energy Correlation Functions for Jet Substructure
• SHERPA 1.alpha, a proof-of-concept version
• Anomaly Detection with Density Estimation
• Medium-Induced Gluon Radiation off Massive Quarks Fills the Dead Cone
• Real-time gravitational-wave science with neural posterior estimation
• Light-ray operators in conformal field theory
• Event Shape/Energy Flow Correlations
• Event Generation with Normalizing Flows
• New Angles on Energy Correlation Functions
• Factorization of e+e- Event Shape Distributions with Hadronic Final States in Soft Collinear Effective Theory
• The Collinear Limit of the Energy-Energy Correlator
• Rethinking Jets with Energy Correlators: Tracks, Resummation and Analytic Continuation
• From correlation functions to event shapes
• QCD-Aware Recursive Neural Networks for Jet Physics
• Event shapes in N=4 super-Yang-Mills theory
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Analyzing N-point Energy Correlators Inside Jets with CMS Open Data
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Score-based Generative Models for Calorimeter Shower Simulation
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• Resolving the Scales of the Quark-Gluon Plasma with Energy Correlators
• Understanding Event-Generation Networks via Uncertainties
• The Transverse Energy-Energy Correlator in the Back-to-Back Limit
• Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Nucleon Energy Correlators for the Color Glass Condensate
• Deep-Learning Jets with Uncertainties and More
• Uncertainty Aware Learning for High Energy Physics
• A New Paradigm for Precision Top Physics: Weighing the Top with Energy Correlators
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Spinning Gluons from the QCD Light-Ray OPE
• Resonant anomaly detection without background sculpting
• Celestial Blocks and Transverse Spin in the Three-Point Energy Correlator
• MadNIS -- Neural Multi-Channel Importance Sampling
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• FETA: Flow-Enhanced Transportation for Anomaly Detection
• Precise determination of ${\alpha }_S(M_Z)$ from a global fit of energy-energy correlation to NNLO+NNLL predictions
• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• Conformal Colliders Meet the LHC
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• ν-Flows: Conditional Neutrino Regression
• Inductive Simulation of Calorimeter Showers with Normalizing Flows
• Nonperturbative Effects in Energy Correlators: From Characterizing Confinement Transition to Improving ${\alpha }_s$ Extraction
• The MadNIS Reloaded
• Analytic Computation of Three-point Energy Correlator in QCD
• CaloFlow for CaloChallenge Dataset 1
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• ${\nu }^2$-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
• Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
• Energy Correlators of Hadronically Decaying Electroweak Bosons
• One never walks alone: the effect of the perturber population on subhalo measurements in strong gravitational lenses
• Prospect of measuring the top quark mass through energy correlators
• Using the $W$ as a Standard Candle to Reach the Top: Calibrating Energy Correlator Based Top Mass Measurements
• Normalizing Flows for High-Dimensional Detector Simulations
• Scalable inference with Autoregressive Neural Ratio Estimation
• Calorimeter shower superresolution
• Energy-Energy Correlator for jet production in $pp$ and $pA$ collisions
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Unbinned Profiled Unfolding
• An implementation of neural simulation-based inference for parameter estimation in ATLAS
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Simulation-Based Inference Benchmark for Weak Lensing Cosmology
• Flows for Flows: Morphing one Dataset into another with Maximum Likelihood Estimation
• Probing cold nuclear matter with energy correlators
• Advancing Tools for Simulation-Based Inference
• Anomaly detection with flow-based fast calorimeter simulators
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• Unbinned inclusive cross-section measurements with machine-learned systematic uncertainties
• Unifying Simulation and Inference with Normalizing Flows
• Generative Unfolding with Distribution Mapping
• Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysis
• Designing Observables for Measurements with Deep Learning

Cited by in corpus (1)

• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction