Accurate Surrogate Amplitudes with Calibrated Uncertainties

Abstract

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with Kolmogorov-Arnold Networks. Then, we train neural surrogates to simultaneously predict the target amplitude and an uncertainty for the prediction. We disentangle systematic uncertainties, learned by a well-defined likelihood loss, from statistical uncertainties, which require the introduction of Bayesian neural networks or repulsive ensembles. We test the coverage of the learned uncertainties using pull distributions to quantify the calibration of cutting-edge neural surrogates.

33 pages, 15 figures

References in corpus (74)

• Variational Inference: A Review for Statisticians
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Event Generation with Sherpa 2.2
• KAN: Kolmogorov-Arnold Networks
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Energy Flow Networks: Deep Sets for Particle Jets
• Event Generation with Normalizing Flows
• How to GAN LHC Events
• Numerical evaluation of virtual corrections to multi-jet production in massless QCD
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• AtlFast3: the next generation of fast simulation in ATLAS
• Machine Learning and LHC Event Generation
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Score-based Generative Models for Calorimeter Shower Simulation
• Exploring phase space with Neural Importance Sampling
• Invertible Networks or Partons to Detector and Back Again
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• How to GAN away Detector Effects
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
• Understanding Event-Generation Networks via Uncertainties
• Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates
• Generative Networks for Precision Enthusiasts
• GANplifying Event Samples
• A factorisation-aware Matrix element emulator
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Optimising simulations for diphoton production at hadron colliders using amplitude neural networks
• Targeting Multi-Loop Integrals with Neural Networks
• Deep-Learning Jets with Uncertainties and More
• KAN 2.0: Kolmogorov-Arnold Networks Meet Science
• Calomplification -- The Power of Generative Calorimeter Models
• MadNIS -- Neural Multi-Channel Importance Sampling
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Per-Object Systematics using Deep-Learned Calibration
• Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
• How to Understand Limitations of Generative Networks
• Two Invertible Networks for the Matrix Element Method
• Measuring QCD Splittings with Invertible Networks
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Modern Machine Learning for LHC Physicists
• ν-Flows: Conditional Neutrino Regression
• Inductive Simulation of Calorimeter Showers with Normalizing Flows
• The MadNIS Reloaded
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Efficient phase-space generation for hadron collider event simulation
• Improving Generative Model-based Unfolding with Schrödinger Bridges
• One-loop matrix element emulation with factorisation awareness
• End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
• The Landscape of Unfolding with Machine Learning
• 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
• Precision-Machine Learning for the Matrix Element Method
• ELSA -- Enhanced latent spaces for improved collider simulations
• Kolmogorov-Arnold Transformer
• Normalizing Flows for High-Dimensional Detector Simulations
• Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable MadNIS-Lite
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• Loop Amplitudes from Precision Networks
• Generative Machine Learning for Detector Response Modeling with a Conditional Normalizing Flow
• Advancing Tools for Simulation-Based Inference
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• PIPPIN: Generating variable length full events from partons
• Accelerating HEP simulations with Neural Importance Sampling
• Interpolating amplitudes
• Optimal Equivariant Architectures from the Symmetries of Matrix-Element Likelihoods
• Unifying Simulation and Inference with Normalizing Flows
• PINNferring the Hubble Function with Uncertainties
• KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics example

Cited by in corpus (5)

• Accelerating multijet-merged event generation with neural network matrix element surrogates
• Amplitude Uncertainties Everywhere All at Once
• BitHEP -- The Limits of Low-Precision ML in HEP
• Amplitude Surrogates for Multi-Jet Processes
• Observable Optimization for Precision Theory: Machine Learning Energy Correlators