Office: S.2018

Max-Planck-Ring 4

72076 Tübingen

Germany

Max-Planck-Ring 4

72076 Tübingen

Germany

+49 7071 601 1714

Advisor(s):

Philipp Hennig

I am a PhD student in the Max Planck Research Group on Probabilistic Numerics. Together with my supervisor Philipp Hennig and my colleagues, I try to develop algorithms which return information about the uncertainty of the result. This uncertainty is mathematically captured by probability measures. I am especially interested in solving ordinary differential equations (ODEs). My main goal for my PhD is to bridge the trade-off between computational cost and probabilistic calibration of the estimated uncertainty. Therefore I aim at developing solvers that return meaningful probabilistic information while staying fast. Additionally, I would like to learn as much as possible about algorithms based on Gaussian processes or Bayesian statistics. In machine learning these algorithms are often connected in a series and I believe that there are still many open questions about the interplay between the different computational steps (e.g. about the propagation of error estimates). I hope to add insights about these overarching questions from my ODE perspective. Before joining this group, I studied mathematics at LMU Munich with a focus on stochastic calculus.

3 results
(View BibTeX file of all listed publications)

**Probabilistic Solutions To Ordinary Differential Equations As Non-Linear Bayesian Filtering: A New Perspective**
*ArXiv preprint 2018*, arXiv:1810.03440 [stat.ME], October 2018 (article)

**Convergence Rates of Gaussian ODE Filters**
*arXiv preprint 2018*, arXiv:1807.09737 [math.NA], July 2018 (article)

**Active Uncertainty Calibration in Bayesian ODE Solvers**
*Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence (UAI)*, pages: 309-318, (Editors: Ihler, A. and Janzing, D.), AUAI Press, June 2016 (conference)