Cargando…
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...
| Autor principal: | |
|---|---|
| Lenguaje: | eng |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | http://cds.cern.ch/record/2875710 |
| _version_ | 1780978906638057472 |
|---|---|
| author | CMS Collaboration |
| author_facet | CMS Collaboration |
| author_sort | CMS Collaboration |
| collection | CERN |
| description | 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. |
| id | cern-2875710 |
| institution | Organización Europea para la Investigación Nuclear |
| language | eng |
| publishDate | 2023 |
| record_format | invenio |
| spelling | cern-28757102023-10-16T18:55:07Zhttp://cds.cern.ch/record/2875710engCMS CollaborationA Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural NetworksDetectors and Experimental TechniquesThe 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.CMS-DP-2023-077CERN-CMS-DP-2023-077oai:cds.cern.ch:28757102023-08-29 |
| spellingShingle | Detectors and Experimental Techniques CMS Collaboration A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title | A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title_full | A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title_fullStr | A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title_full_unstemmed | A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title_short | A Method for Inferring Signal Strength Modifiers by Conditional Invertible Neural Networks |
| title_sort | method for inferring signal strength modifiers by conditional invertible neural networks |
| topic | Detectors and Experimental Techniques |
| url | http://cds.cern.ch/record/2875710 |
| work_keys_str_mv | AT cmscollaboration amethodforinferringsignalstrengthmodifiersbyconditionalinvertibleneuralnetworks AT cmscollaboration methodforinferringsignalstrengthmodifiersbyconditionalinvertibleneuralnetworks |