# How to GAN LHC Events

## TL;DR

This paper explores the use of generative adversarial networks to efficiently generate LHC physics events, capturing complex features like phase space boundaries and distribution tails, with potential extensions for more detailed simulations.

## Contribution

It introduces a GAN-based method for LHC event generation that accurately models physical features and incorporates the maximum mean discrepancy for sharp local features.

## Key findings

- Successfully models intermediate on-shell particles
- Captures phase space boundaries and distribution tails
- Can be extended to include off-shell effects and detector simulations

## Abstract

Event generation for the LHC can be supplemented by generative adversarial networks, which generate physical events and avoid highly inefficient event unweighting. For top pair production we show how such a network describes intermediate on-shell particles, phase space boundaries, and tails of distributions. In particular, we introduce the maximum mean discrepancy to resolve sharp local features. It can be extended in a straightforward manner to include for instance off-shell contributions, higher orders, or approximate detector effects.