A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks

The continuous growth in model complexity in high-energy physics (HEP) collider experiments demands increasingly time-consuming model fits. As parameter inference with conditional invertible neural networks (cINNs) is very fast, the application of these versatile networks in a VH-Analysis at CMS is demonstrated. In the VH-Analysis workflow the signal strength modifier parameters $\mu = \sigma/\sigma_\text{SM}$ are inferred. Hereby, the performance indicators of such a setup including the treatment of systematic and statistic uncertainties are presented, highlighting the features of cINNs estimating the signal strength.