As an applied analyst, his research lies at the intersection of PDEs describing mean-field particle models, network dynamics, the mathematics of machine learning, and control theory. Before joining his current position, he worked in Christian Kuehn’s group at TU Munich (via Schrödinger Scholarship) and Enrique Zuazua’s group at FAU Erlangen. In 2020, he completed his PhD at TU Vienna under the supervision of Anton Arnold.

Dr. Wöhrer’s PDE analysis focuses on explicit large-time estimates for mean-field equations using entropy methods and spectral theory. His current research explores models incorporating long-range particle interactions on large networks, with real-world applications such as synchronization phenomena, opinion dynamics, and neural network behavior.

Additionally, he investigates deep learning algorithms, particularly neural ODEs, examining their lack of robustness through the lens of dynamical systems and control theory.