Implicit Quantile Networks For Emulation in Jet Physics

Abstract

The ability to model and sample from conditional densities is important in many physics applications. Implicit quantile networks (IQN) have been successfully applied to this task in domains outside physics. In this work, we illustrate the potential of IQNs as components of emulators using the simulation of jets as an example. Specifically, we use an IQN to map jets described by their 4-momenta at the generation level to jets at the event reconstruction level. The conditional densities emulated by our model closely match those generated by $\text{Delphes}$, while also enabling faster jet simulation.

References in corpus (24)

• XGBoost: A Scalable Tree Boosting System
• The anti-k_t jet clustering algorithm
• Empirical Evaluation of Rectified Activations in Convolutional Network
• The ATLAS Simulation Infrastructure
• On the Convergence of Adam and Beyond
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Parameterized Machine Learning for High-Energy Physics
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Event Generation with Normalizing Flows
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• How to GAN away Detector Effects
• Publishing statistical models: Getting the most out of particle physics experiments
• Measurement and QCD analysis of double-differential inclusive jet cross sections in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• How to Understand Limitations of Generative Networks
• Measuring QCD Splittings with Invertible Networks
• A deep neural network for simultaneous estimation of b jet energy and resolution
• Measurement of hadronic event shapes in high-$p_{\text{T}}$ multijet final states at $\sqrt{s}=13$ TeV with the ATLAS detector
• Parametrizing the Detector Response with Neural Networks
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• End-to-end simulation of particle physics events with Flow Matching and generator Oversampling
• Towards Instance-Wise Calibration: Local Amortized Diagnostics and Reshaping of Conditional Densities (LADaR)
• Implicit Quantile Neural Networks for Jet Simulation and Correction