Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 55: Invited Topical Talks 4

T 55.1: Invited Topical Talk

Wednesday, March 23, 2022, 11:00–11:25, T-H16

Machine Learning for LHC Theory — •Anja Butter — Institut für Theoretische Physik, Heidelberg, Germany

Over the next years, measurements at the LHC and the HL-LHC will provide us with a wealth of data. The best hope of answering fundamental questions like the nature of dark matter, is to adopt machine learning techniques for particle experiment and theory. LHC physics relies at a fundamental level on our ability to simulate events efficiently from first principles. In the coming LHC runs, these simulations will face unprecedented precision requirements to match the experimental accuracy. Neural networks can overcome limitations from the calculation of amplitudes and event generation. Generative networks can achieve high-precision in simulations while maintaining control over training stability and associated uncertainties. Since networks in the form of normalizing flows can be inverted, they also open new avenues in LHC analyses. The access to the density of the generated distribution enables new methods for anomaly detection, while their interpretation in terms of probability densities leads to new methods for multi-dimensional unfolding.