Modeling hadronization using machine learning

Abstract

We present the first steps in the development of a new class of hadronization models utilizing machine learning techniques. We successfully implement, validate, and train a conditional sliced-Wasserstein autoencoder to replicate the Pythia generated kinematic distributions of first-hadron emissions, when the Lund string model of hadronization implemented in Pythia is restricted to the emissions of pions only. The trained models are then used to generate the full hadronization chains, with an IR cutoff energy imposed externally. The hadron multiplicities and cumulative kinematic distributions are shown to match the Pythia generated ones. We also discuss possible future generalizations of our results.

String Interactions as a Source of Collective Behaviour

“…The HadML initiative has demonstrated a proof of principle that the cluster model can be parametrized using GANs [96], and how such models can be tuned to real data [97], providing a path forward for real applications. The MLHad initiative [98] has similarly shown how the string model can be parametrized using normalizing flows [99], as well as how string hadronization can be re-parametrized [100] to allow for more efficient parameter variation and ultimately more robust comparisons to data. While it is still unclear whether such efforts will contribute directly to a deeper physics understanding of hadronization, it is evident that they will aid in making better quantitative comparisons to data, and ultimately in ruling out models that cannot globally describe data.…”

Machine learning and LHC event generation

“…This includes important ingredients to precision predictions such as parton densities and fragmentation functions, where neural network (NN) techniques are routinely used already. First steps towards modeling the hadronization process with ML techniques have been presented in [8]. For the tuning of non-perturbative simulation parameters, including an underlying event model, NN-based approaches have recently shown promise [9].…”

Reweighting Monte Carlo predictions and automated fragmentation variations in Pythia 8

“…It could, for instance, be applied to cluster hadronization-models [25][26][27][28][29][30][31]; various machine-learning based hadronizationmodels, such as those described in refs. [32][33][34]; or the multiparton interaction model within PYTHIA 8 itself [35]. For instance, because the multiparton interaction (MPI) model in PYTHIA 8 produces additional strings in a parton-shower-like fashion, the method presented here is already directly applicable to the variation of MPI parameters.…”