Transforming LHC Physics with Machine Learning

• Tilman Plehn (Universität Heidelberg)

Room: TUM, Physics Department, Garching. Room: PH 3344, (5101.01.344) LHC physics, theory and experiment, offers a perfect link between fundamental physics and modern data science. As modern machine learning is transforming our lives, no aspect of LHC physics is left untouched. This starts with identifying data for classic or optimal analyses and extends to anomaly searches, faster and more precise simulations based on perturbative quantum field theory, and unfolding as a new way to publish LHC data. I will give a few examples for the transformative power of modern machine learning and then show how our understanding of uncertainties adds a new flavor to neural networks. Finally, I will show how generative neural networks help us with LHC simulations and allow us to make LHC data available to a broad scientific community.