Event generator tuning using Bayesian optimization

TL;DR

This paper demonstrates that Bayesian optimization can efficiently tune Monte Carlo event generator parameters, significantly reducing computational time and requiring minimal physics expertise, thus improving the tuning process.

Contribution

It introduces a Bayesian optimization method for tuning event generators, achieving accurate parameter determination with minimal expert input and reduced computational resources.

Findings

Bayesian optimization accurately tunes PYTHIA 8 parameters.

Tuning 20 parameters takes only two days on a laptop.

Method reduces need for extensive CPU resources and expert knowledge.

Abstract

Monte Carlo event generators contain a large number of parameters that must be determined by comparing the output of the generator with experimental data. Generating enough events with a fixed set of parameter values to enable making such a comparison is extremely CPU intensive, which prohibits performing a simple brute-force grid-based tuning of the parameters. Bayesian optimization is a powerful method designed for such black-box tuning applications. In this article, we show that Monte Carlo event generator parameters can be accurately obtained using Bayesian optimization and minimal expert-level physics knowledge. A tune of the PYTHIA 8 event generator using $e^+e^-$ events, where 20 parameters are optimized, can be run on a modern laptop in just two days. Combining the Bayesian optimization approach with expert knowledge should enable producing better tunes in the future, by making it faster and easier to study discrepancies between Monte Carlo and experimental data.