Fast Perfekt: Regression-based refinement of fast simulation

Abstract

The availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with a relative advantage in accuracy or speed. The quality of insights extracted from the data stands to increase if the accuracy of faster, more economical simulation could be improved to parity or near parity with more resource-intensive but accurate simulation. We present Fast Perfekt, a machine-learned regression that employs residual neural networks to refine the output of fast simulations. A deterministic morphing model is trained using a unique schedule that makes use of the ensemble loss function MMD, with the option of an additional pair-based loss function such as the MSE. We explore this methodology in the context of an abstract analytical model and in terms of a realistic particle physics application featuring jet properties in hadron collisions at the CERN Large Hadron Collider. The refinement makes maximum use of domain knowledge, and introduces minimal computational overhead to production.

References in corpus (17)

• A Brief Introduction to PYTHIA 8.1
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Jet substructure as a new Higgs search channel at the LHC
• Identifying Boosted Objects with N-subjettiness
• Performance of electron reconstruction and selection with the CMS detector in proton-proton collisions at sqrt(s) = 8 TeV
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Energy calibration and resolution of the CMS electromagnetic calorimeter in pp collisions at sqrt(s) = 7 TeV
• Summary of the ATLAS experiment's sensitivity to supersymmetry after LHC Run 1 - interpreted in the phenomenological MSSM
• AtlFast3: the next generation of fast simulation in ATLAS
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• Data Unfolding Methods in High Energy Physics
• Phenomenological MSSM interpretation of CMS searches in pp collisions at sqrt(s) = 7 and 8 TeV
• Refining Fast Calorimeter Simulations with a Schrödinger Bridge
• Combination and summary of ATLAS dark matter searches interpreted in a 2HDM with a pseudo-scalar mediator using 139 fb${}^{-1}$ of $\sqrt{s}=13$ TeV $pp$ collision data
• Refining fast simulation using machine learning
• Chained Quantile Morphing with Normalizing Flows
• Computationally-Efficient Climate Predictions using Multi-Fidelity Surrogate Modelling