Teaching Profile
My teaching focuses on machine learning fundamentals and statistical learning theory, with an emphasis on bridging theoretical foundations and practical ML system design. I highlight reliability, generalization, and real-world deployment throughout my courses. My main BSc course is Machine Learning: Basic Techniques, with over 500 students. At the MSc level, I regularly teach Statistical Learning Theory and Applications, a course I designed in 2023 that connects mathematical foundations with current research challenges.
Core courses
Statistical Learning Theory and Applications, ~100 students, SS23, SS25, SS26
Machine Learning: Basic Techniques, ~500 students, WS25
Advanced Seminars & Series
Lecture Series in AI, WS24
International Seminar on Learning Theory, JKU–TU Braunschweig–UNI Genova–UNI LUT, 2023-Now [link]
Industrial Research Seminar S3AI, 2020-2022 [link]
Examination & Academic Service
AI Master Exams, examiner, WS24 - Now
PhD Pre-defensios, examiner, WS24 - Now
Supervision
I supervise and co-supervise PhD and MSc students in machine learning, domain adaptation, and robustness, often in close collaboration with academic and industrial partners.
PhD Students
Stephanie Holly, Generative models for design optimization (ongoing)
Lukas Gruber, Density ratio estimation and robustness (ongoing, co-supervised with S. Hochreiter)
Marius-Constantin Dinu, Parameter choice and neuro-symbolic approaches for domain-invariant learning, 2024
Hoan Duc Nguyen, Regularization in RKHSs for covariate shift adaptation, 2023
MSc Theses (selected)
Andrea Huber, Parameter choice methods for unsupervised domain adaptation, 2023
Johannes Zigsch, Domain generalization by deep learning-based domain encoding, 2023