Speaker
Description
Hadronization, a crucial component of event generation, is traditionally simulated using finely-tuned empirical models. While current phenomenological models have achieved significant success in simulating this process, there remain areas where they fall short of accurately describing the underlying physics. An alternative approach is machine learning-based models.
In this talk, I will present recent developments in MLHAD – a machine learning-based model for hadronization. We introduce a new training method for normalizing flows, which improves the agreement between simulated and experimental distributions of high-level observables by adjusting single-emission dynamics. Our results constitute an important step toward realizing a machine-learning-based model of hadronization that utilizes experimental data during training.
