A survey of machine learning-based physics event generation

TL;DR

This survey reviews current machine learning techniques for physics event generation, highlighting models, challenges, and integration of physics principles to improve accuracy and extrapolation in high-energy physics simulations.

Contribution

It provides a comprehensive overview of ML-based event generators, discusses challenges, and explores methods of incorporating physics into ML models for improved performance.

Findings

ML generative models are increasingly used in physics event generation

Incorporating physics into ML models improves fidelity and extrapolation

Open questions remain in super-resolution and model fidelity

Abstract

Event generators in high-energy nuclear and particle physics play an important role in facilitating studies of particle reactions. We survey the state-of-the-art of machine learning (ML) efforts at building physics event generators. We review ML generative models used in ML-based event generators and their specific challenges, and discuss various approaches of incorporating physics into the ML model designs to overcome these challenges. Finally, we explore some open questions related to super-resolution, fidelity, and extrapolation for physics event generation based on ML technology.