SciPost Submission Page
Event Generation and Density Estimation with Surjective Normalizing Flows
by Rob Verheyen
Submission summary
| Authors (as registered SciPost users): | Rob Verheyen |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2205.01697v2 (pdf) |
| Code repository: | https://github.com/rbvh/surflows |
| Date accepted: | July 5, 2022 |
| Date submitted: | June 17, 2022, 8:23 a.m. |
| Submitted by: | Rob Verheyen |
| Submitted to: | SciPost Physics |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approaches: | Computational, Phenomenological |
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.
List of changes
Published as SciPost Phys. 13, 047 (2022)