Hi, I hope you’re having a wonderful day! I’m a PhD student in machine learning jointly supervised by Niki Kilbertus (TUM) and Andreas Krause (ETH), and funded by Helmholtz AI. My research interests are currently rather broad and include reinforcement learning, world models, causal inference, and AI4Science.
One of my favourite formulae is the bias-variance decomposition in least-squares regression with risk \(r(a) = \mathbb{E}[(a(X) - Y)^2]\), computed (randomised) algorithm \(A\), and optimal algorithm \(a^*\):
\[\underbrace{\mathbb{E}[r(A)] - r(a^*)}_{\text{expected excess risk}} = \underbrace{\mathbb{E}\left[(\mathbb{E}[A(X) \mid X] - a^*(X))^2\right]}_{\text{expected square bias}} + \underbrace{\mathbb{E}[\mathrm{Var}[A(X) \mid X]]}_{\text{expected variance}}\]Education
I agree with Dijkstra that calling informatics “computer science” would be like calling astrophysics “telescope science” 😉
- MSc Informatics, TUM, 2026
- exchange stay at UNSW Sydney, 2024
- MSc Mathematical Sciences, Oxford University, 2023
- BSc Informatics, University of Passau, 2022
- BSc Mathematics, University of Passau, 2022
Work Experience
- since 2026: Doctoral Student, Helmholtz AI (with TUM & ETH), Munich, Germany
- 2025-2026: Research Assistant, TUM, Munich, Germany
- Summer 2023: AI Engineering Intern, Google, California & New York
- Summer 2022: Software Engineering Intern, Google, San Francisco
- 2018-2022: Self-employed Web Developer, Remote, Germany
Publications
The Merit of River Network Topology for Neural Flood Forecasting
Kirschstein, N., Sun, Y. (2024). The Merit of River Network Topology for Neural Flood Forecasting. In: Proceedings of the 41st International Conference on Machine Learning (ICML'24), Vol. 235. JMLR.org, Article 990, 24713–24725.
Deep Active Learning for Detection of Mercury’s Bow Shock and Magnetopause Crossings
Julka, S., Kirschstein, N., Granitzer, M., Lavrukhin, A., Amerstorfer, U. (2023). Deep Active Learning for Detection of Mercury’s Bow Shock and Magnetopause Crossings. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13716. Springer, Cham.
Research Projects
Teaching
Mathematics Tutor
Taught two 2-hour weekly tutorial sessions for IN0018 Discrete Probability Theory
Teaching Assistant
Undergraduate courses 5200 Algorithms and Data Structures, 5306 Theoretical Computer Science
Scholarships
- 2020-2026: Studienstiftung scholarship of Germany
- 2018-2026: Max Weber Programme of Bavaria
- 2022-2023: Joan Protheroe Scholarship from Lincoln College, University of Oxford
- 2022-2023: DAAD fellowship by the German Academic Exchange Service
Service and Leadership
- 2025-2026: Regional Representative of the Studienstiftung scholarship holders in Munich, Germany
- 2023-2024: Board Member of UniversitätsChor Munich, Germany
- 2021: Conference Co-organiser, University of Passau, Germany
- 2020: Student Representative in professorship appointments, University of Passau, Germany
- 2020: On-call Social Worker, Bavarian Red Cross, Germany