JetFlow: Generating Jets with Conditioned and Mass Constrained Normalising Flows

Fast data generation based on Machine Learning has become a major research topic in particle physics. This is mainly because the Monte Carlo simulation approach is computationally challenging for future colliders, which will have a significantly higher luminosity. The generation of collider data is similar to point cloud generation with complex correlations between the points. In this study, the generation of jets with up to 30 constituents with Normalising Flows using Rational Quadratic Spline coupling layers is investigated. Without conditioning on the jet mass, our Normalising Flows are unable to model all correlations in data correctly, which is evident when comparing the invariant jet mass distributions between ground truth and generated data. Using the invariant mass as a condition for the coupling transformation enhances the performance on all tracked metrics. In addition, we demonstrate how to sample the original mass distribution by interpolating the empirical cumulative distribution function. Similarly, the variable number of constituents is taken care of by introducing an additional condition on the number of constituents in the jet. Furthermore, we study the usefulness of including an additional mass constraint in the loss term. On the \texttt{JetNet} dataset, our model shows state-of-the-art performance combined with fast and stable training.

[1]  D. Shih,et al.  CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows , 2021, ArXiv.

[2]  Javier Mauricio Duarte,et al.  Particle Cloud Generation with Message Passing Generative Adversarial Networks , 2021, NeurIPS.

[3]  D. Shih,et al.  CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows , 2021, Physical Review D.

[4]  Benjamin Nachman,et al.  A Living Review of Machine Learning for Particle Physics , 2021, ArXiv.

[5]  G. Papamakarios,et al.  nflows: normalizing flows in PyTorch , 2020 .

[6]  G. Kasieczka,et al.  GANplifying event samples , 2020, SciPost Physics.

[7]  Ivan Kobyzev,et al.  Normalizing Flows: An Introduction and Review of Current Methods , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  K. Matchev,et al.  Uncertainties associated with GAN-generated datasets in high energy physics , 2020, SciPost Physics.

[9]  Eric Nalisnick,et al.  Normalizing Flows for Probabilistic Modeling and Inference , 2019, J. Mach. Learn. Res..

[10]  Iain Murray,et al.  Neural Spline Flows , 2019, NeurIPS.

[11]  Huilin Qu,et al.  ParticleNet: Jet Tagging via Particle Clouds , 2019, Physical Review D.

[12]  Damian Podareanu,et al.  Event generation and statistical sampling for physics with deep generative models and a density information buffer , 2019, Nature Communications.

[13]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[14]  Patrick T. Komiske,et al.  Energy flow polynomials: a complete linear basis for jet substructure , 2017, 1712.07124.

[15]  Leonidas J. Guibas,et al.  Learning Representations and Generative Models for 3D Point Clouds , 2017, ICML.

[16]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[17]  Iain Murray,et al.  Masked Autoregressive Flow for Density Estimation , 2017, NIPS.

[18]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[19]  Lucio Rossi,et al.  High-Luminosity Large Hadron Collider (HL-LHC) : Preliminary Design Report , 2015 .

[20]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  E. Tabak,et al.  A Family of Nonparametric Density Estimation Algorithms , 2013 .

[23]  F. Fritsch,et al.  A Method for Constructing Local Monotone Piecewise Cubic Interpolants , 1984 .