ARI Guest Talk: 17 January 2024
The Standard Model (SM) of particle physics is one of the most successful descriptions of Nature we have, explaining fundamental particles and their interactions over more than 10 orders of magnitude in energy scale. However, observations like neutrino oscillations or Dark Matter are not explained by the SM. The research program in high-energy physics is crucially defined by first-principle simulations, which link fundamental theory predictions and interpretation with the vast data output of multi-purpose detectors. This link offers a wide range of applications of modern machine learning, ranging from generative networks for simulations and simulation-based inference; to classifiers for particle identification; to regression networks for calibration and inference; and to new ideas for anomaly detection.
In my talk on "Machine learning & Particle physics", I will show how these new ideas and tools developed at the interface of particle physics and machine learning transform the way we do particle physics, handle the complexity of collision data, and ultimately improve our understanding of nature.
Dr. Claudius Krause studied physics in Cottbus, Munich, and Lausanne. He obtained his doctorate from LMU Munich in 2016, working on "Higgs Effective Field Theories --- Systematics and Applications" and continued to investigate the theory of the Higgs particle in his first postdoctoral positions at IFIC Valencia and at Fermilab in the US. At Fermilab, he started to work on the application of machine learning techniques to particle physics. After two machine-learning-for-particle-physics focused postdocs at Rutgers University and the University of Heidelberg, he joint the Institute for High-Energy-Physics (HEPHY) in Vienna in 2023 as Group Leader for Machine Learning in HEP.