Speaker
Description
In this study, jets with up to 30 particles are modelled using Normalizing Flows with Rational Quadratic Spline coupling layers. The invariant mass of the jet is a powerful global feature to control whether the flow-generated data contains the same high-level correlations as the training data. The use of normalizing flows without conditioning shows that they lack the expressive power to do this. Using the mass as a condition for the coupling transformation enhances the model's performance on all tracked metrics. In addition, we demonstrate how to sample the original mass distribution with the use of the empirical cumulative distribution function and we
study the usefulness of including an additional mass constraint in the loss term. On the JetNet dataset, our model shows state-of-the-art performance combined with a general model and stable training.
References
Reference: The study uses the public JetNet dataset: https://zenodo.org/record/4834876 and arXiv:2106.11535
Significance
Significance: The contribution demonstrates that Normalising Flows with Rational Quadratic Splines can model high-dimensional data efficiently (i.e. stable training and state-of-the-art performance) when global features (mass) are used for conditioning the transformation.
| Experiment context, if any | None |
|---|
