Automating and Accelerating Scientific Discovery in HEP with Generative Models

12.05.2023 11:15 – 12:15

RESEARCH CENTER FOR STATISTICS SEMINAR / ABSTRACT

This talk focuses on automating and accelerating scientific discovery in High Energy Physics (HEP) using generative models. With the vast amounts of data produced by modern experiments, it is challenging to identify rare events and extract meaningful information. The proposed framework leverages generative models to learn the underlying distribution of the data and generate synthetic samples, reducing computational costs and improving statistical power. This approach can potentially lead to the discovery of new physical phenomena beyond human intuition. Real-world datasets from the ATLAS experiment at CERN demonstrate the effectiveness of this approach in identifying rare signals, improving background estimation accuracy, and optimizing event classification. The talk discusses the challenges and limitations of the approach and outlines future research directions in automated scientific discovery.

Lieu

Bâtiment: Uni Mail

Online & in Uni Mail

Boulevard du Pont-d'Arve 40
1205 Geneva

Room M 3393, 3rd floor

entrée libre