[Past Member] Postdoctoral Researcher | Seminars coordinator at FAU DCN-AvH 2021 – 2022
tobias.woehrer@math.fau.de
Room 03.315 | DDS – Department of Data Science. FAU DCN-AvH Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship
+49 9131 85-67138
I am a postdoc researcher with research ambitions at the at the intersection of mean-field particle models, control theory and mathematics of machine learning. I am at the Chair for Dynamics, Control
and Numerics headed by Enrique Zuazua. Before, I was a postdoc at TU Vienna at the Institute of Analysis and Scientific Computing in the group of Anton Arnold, where I also finished my PhD in 2020. In 2019, I was an invited guest of Prof. Shi Jin at Shanghai Jiao Tong University.
Large-time behaviour of mean-field equations
During my PhD, I focused on obtaining explicit and for application meaningful large-time estimates for mean-field equations by means of spectral theory and entropy methods. I am currently interested in including long-range particle interactions on large networks, which have many fascinating real-world applications, such as synchronisation and opinion formations.
Mathematics of machine learning
The achievements of machine learning algorithms are beyond impressive, but still surprisingly little is understood about why they work so well. The mathematician’s job is now to look behind the curtain and extend the vocabulary to describe what at this point seems like magic. I am currently investigating supervised learning procedures of neural networks and their lack of robustness from an optimal control perspective.
“The writers who embellish a language, who treat it as an object of art, make of it at the same time a more supple instrument, more apt for rendering shades of thought.” -Henri Poincaré
PhD Thesis: On Decay Rates in Linear Kinetic Equations with Defects (2020)
My posters
Sharp Estimates in Defective Evolution Equations: From ODEs to Kinetic Equations with Uncertainties
My posts on Math and Research
Training of neural ODEs using pyTorch
