Fast Perfekt: Regression-based refinement of fast simulation

TL;DR

Fast Perfekt is a machine learning approach that refines fast simulation outputs to achieve accuracy comparable to more resource-intensive methods, using residual neural networks and domain knowledge.

Contribution

It introduces a regression-based refinement method employing residual neural networks and a novel training schedule with ensemble loss functions for simulation enhancement.

Findings

Improved accuracy of fast simulations in particle physics.

Minimal additional computational overhead.

Effective use of domain knowledge in refinement process.

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.