Leon Bungert

Leon Bungert is a W2 Professor with Tenure Track to W3 Professorship for Mathematics III (Mathematics of Machine Learning) at the University of Würzburg, appointed since 2023. He leads the Mathematics of Machine Learning group within the Institute of Mathematics. His academic journey includes a Ph.D. (summa cum laude) from the University of Erlangen-Nürnberg in 2020, focusing on nonlinear spectral theory with variational methods, followed by postdoctoral research at TU Berlin, Bonn, and Erlangen-Nürnberg.

Research Interests: Bungert's work bridges applied analysis and machine learning, emphasizing PDEs on graphs, adversarial robustness, inverse problems, optimization, and nonlinear eigenvalue problems. His research often employs variational methods and explores the intersection of geometry, probability, and numerical analysis. Notable areas include adversarial machine learning, Lipschitz learning on graphs, and regularization techniques for inverse problems.

Professional Activities: He serves as a guest editor for the European Journal of Applied Mathematics, associate editor for Advances in Continuous and Discrete Models, and co-organizes major conferences like MIA'25 and SSVM 2025. His work has been published in top journals such as Annals of Applied Probability, Journal de Mathématiques Pures et Appliquées, and SIAM Journal on Imaging Sciences.

Upcoming Engagements: Invited speaker and organizer at events including the IHP Paris conference (January 2025), Osaka workshop on machine learning and numerics (March 2025), and the BIRS workshop on adversarial machine learning (August 2025). His research team collaborates with institutions globally, including MIT, University of Cambridge, and University of Bonn.

Lab/Team: The Mathematics of Machine Learning group at Würzburg focuses on theoretical and applied aspects of machine learning, with active projects in adversarial robustness, PDE-based optimization, and geometric data analysis. Bungert’s team includes researchers like Eloi Martinet and Tim Roith, advancing interdisciplinary work in mathematical foundations of AI.