Two Invertible Networks for the Matrix Element Method

Abstract

The matrix element method is widely considered the ultimate LHC inference tool for small event numbers. We show how a combination of two conditional generative neural networks encodes the QCD radiation and detector effects without any simplifying assumptions, while keeping the computation of likelihoods for individual events numerically efficient. We illustrate our approach for the CP-violating phase of the top Yukawa coupling in associated Higgs and single-top production. Currently, the limiting factor for the precision of our approach is jet combinatorics.

25 pages, 13 figures

References in corpus (13)

• An Introduction to PYTHIA 8.2
• Guided Image Generation with Conditional Invertible Neural Networks
• Machine Learning and LHC Event Generation
• Automation of the matrix element reweighting method
• Search for a standard model Higgs boson produced in association with a top-quark pair and decaying to bottom quarks using a matrix element method
• The Matrix Element Method and its Application to Measurements of the Top Quark Mass
• Targeting Multi-Loop Integrals with Neural Networks
• Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
• Inference of cosmic-ray source properties by conditional invertible neural networks
• Modern Machine Learning for LHC Physicists
• ν-Flows: Conditional Neutrino Regression
• Finding the Higgs boson in decays to Z gamma using the matrix element method at Next-to-Leading Order
• The matrix element method at next-to-leading order for arbitrary jet algorithms

Cited by in corpus (24)

• MadNIS -- Neural Multi-Channel Importance Sampling
• How to Understand Limitations of Generative Networks
• The MadNIS Reloaded
• Returning CP-Observables to The Frames They Belong
• CaloFlow for CaloChallenge Dataset 1
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Precision-Machine Learning for the Matrix Element Method
• A Lorentz-Equivariant Transformer for All of the LHC
• Normalizing Flows for High-Dimensional Detector Simulations
• Differentiable MadNIS-Lite
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Anomaly detection with flow-based fast calorimeter simulators
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• Advancing Tools for Simulation-Based Inference
• PIPPIN: Generating variable length full events from partons
• Interpretable deep learning models for the inference and classification of LHC data
• Unifying Simulation and Inference with Normalizing Flows
• Generative Unfolding with Distribution Mapping
• Application-driven Validation of Posteriors in Inverse Problems
• Sensitivity to $\mathcal{C}\mathcal{P}$-violating effective couplings in the top-Higgs sector
• Extrapolating Jet Radiation with Autoregressive Transformers
• BitHEP -- The Limits of Low-Precision ML in HEP
• Reconstructing Sparticle masses at the LHC using Generative Machine Learning
• A Novel Implementation of the Matrix Element Method at Next-to-Leading Order for the Measurement of the Higgs Self-Coupling ${\lambda }_{3H}$