Tobias Schröder

I am a PhD student in Mathematics at Imperial College London supervised by Andrew Duncan and Greg Pavliotis. My research focuses on probabilistic aspects of generative modeling, including the development of robust and theoretically grounded training methods for energy-based models.

During my PhD, I was incredibly fortunate to work with Lester Mackey on scalable kernel density estimation with applications to large language models during an internship at Microsoft Research New England. I received a Bachelor’s degree in Mathematics and Physics and a Master’s degree in Mathematics from Heidelberg University and spent a wonderful exchange year at the University of Washington. I worked on topics in Optimal Transport, Continuum Random Trees, and spontaneous symmetry breaking in non-relativistic quantum field theories. My academic advisors in this time were Christoph Schnörr, Soumik Pal, Thomas Gasenzer, and Anna Wienhard.

Publications