Event Generation and Density Estimation with Surjective Normalizing Flows
arXiv:2205.01697 · doi:10.21468/SciPostPhys.13.3.047
Abstract
Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the peripheral features of collision events. Using the framework of Nielsen et al. (2020), we introduce several surjective and stochastic transform layers to a baseline normalizing flow to improve modelling of permutation symmetry, varying dimensionality and discrete features, which are all commonly encountered in particle physics events. We assess their efficacy in the context of the generation of a matrix element-level process, and in the context of anomaly detection in detector-level LHC events.
29 pages, 15 figures
References in corpus (13)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
- Understanding Event-Generation Networks via Uncertainties
- Better Latent Spaces for Better Autoencoders
- Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
- Targeting Multi-Loop Integrals with Neural Networks
- Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
- Deep Set Auto Encoders for Anomaly Detection in Particle Physics
- Equivariant Energy Flow Networks for Jet Tagging
- DCTRGAN: Improving the Precision of Generative Models with Reweighting
- Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
- Measuring QCD Splittings with Invertible Networks
- Efficient sampling of constrained high-dimensional theoretical spaces with machine learning