Speaker
Description
Normalizing Flows (NFs) are emerging as a powerful brand of generative models, as they not only allow for efficient sampling, but also deliver density estimations by construction. They are of great potential usage in High Energy Physics (HEP), where we unavoidably deal with complex high dimensional data and probability distributions are everyday’s meal. However, in order to fully leverage the potential of NFs it is crucial to explore their robustness as the dimensionality of our data increases. Thus, in this talk, we discuss the performance of some of the most popular types of NFs on the market, on several example data sets with escalating number of dimensions.
Significance
In recent years, proof of concept publications on Normalizing Flows (NFs) applications in High Energy Physics (HEP) have been on the rise. However, a systematic study of the robustness of NFs as the dimensionality of our data increases is missing. Our work aims to fill that void to provide a better idea of the potential reach of applying NFs in HEP.
| Speaker time zone | Compatible with Europe |
|---|
