Deep Learning as a Parton Shower

TL;DR

This paper introduces a deep learning model that mimics the behavior of a parton shower in QCD, using a convolutional autoencoder with recursive structure and custom masking to reproduce jet observables.

Contribution

It presents a novel deep learning architecture explicitly connected to the renormalisation group for modeling QCD parton showers, with low parameter count and self-similar structure.

Findings

The model qualitatively reproduces jet-based observables.

The network can be evaluated on unshowered events via shower merging.

It demonstrates a new approach to simulating QCD events with deep learning.

Abstract

We make the connection between certain deep learning architectures and the renormalisation group explicit in the context of QCD by using a deep learning network to construct a toy parton shower model. The model aims to describe proton-proton collisions at the Large Hadron Collider. A convolutional autoencoder learns a set of kernels that efficiently encode the behaviour of fully showered QCD collision events. The network is structured recursively so as to ensure self-similarity, and the number of trained network parameters is low. Randomness is introduced via a novel custom masking layer, which also preserves existing parton splittings by using layer-skipping connections. By applying a shower merging procedure, the network can be evaluated on unshowered events produced by a matrix element calculation. The trained network behaves as a parton shower that qualitatively reproduces jet-based observables.