Speaker
Manuel Szewc
Description
A fundamental part of event generation, hadronization is currently simulated with the help of fine-tuned empirical models. Motivated by the difficulties of these models, in this talk I'll present the efforts of the MLHAD collaboration in improving several aspects of hadronization modelling: observable selection via correlation modelling, parameter tuning and uncertainty quantification via autodifferentiation, and a proposed model alternative where the empirical model is replaced by a surrogate Machine Learning-based model to be ultimately data-trainable. I'll detail the current stage of development and discuss challenges and possible ways forward.
| I read the instructions above | Yes |
|---|