Current Members

Office Hours: upon request via e-mail

Stefan received his B.Sc. and M.Sc. degrees in Electrical Engineering and Information Technology with a major in Automation Systems from Technische Universität Darmstadt in 2021 and 2023, respectively. His bachelor thesis was titled “Influence of System Parameters on the Robust Coupling Capacity of Linear Multivariable Systems,” and his master thesis focused on cost function learning for model predictive control using Bayesian optimization.

After previously gaining experience as a teaching assistant at the Signal Processing Group at TU Darmstadt, Stefan joined SPG in October 2024 to begin working on his PhD.

His research focuses on the intersection of conformal prediction and signal processing, specifically aimed at providing rigorous, distribution-free uncertainty quantification. While traditional point-forecasting methods often lack reliability guarantees under model misspecification, conformal prediction allows for the construction of prediction intervals that remain valid even in finite-sample regimes. Stefan is particularly interested in adapting these frameworks to time series analysis, with an emphasis on robustness against outliers and distribution shifts. Furthermore, he is investigating applications in the frequency domain, exploring how spectral characteristics can be leveraged to refine uncertainty bounds for periodic and non-stationary signals.

Digital Signal Processing

Fundamentals of Signal Processing