Ingo Meise
My research focuses on Ensemble Learning, Statistical Learning Theory and Optimization. In particular, my goal is to improve the computational scalability of ensemble learning methods and to characerize its limitations mathematically using methods from discrete optimization. Also, I work on tight lower and upper bounds in the PAC (probably approximately correct) model.
Contact
- office
- Room 3027 at ZIB
- email shown with JavaScript enabled
- languages
- German and English
Curriculum vitae
- since 2024
- Researcher at ZIB
- 2020 to 2024
- Research Assistant at ZIB
- Jul 2024
- M.Sc. in Mathematics at TUB
- Feb 2023
- B.Sc. in Mathematics at TUB
Publications and preprints
Full articles
- Meise, I., Pfetsch, M., and Pokutta, S. (2026). A Tight Approximability Analysis of Boosting. In Theoretical Foundations of Deep Learning. springer.
[BibTeX]
@incollection{2026_MeisePfetschPokutta_BoostingApproximability, year = {2026}, booktitle = {Theoretical Foundations of Deep Learning}, publisher = {springer}, author = {Meise, Ingo and Pfetsch, Marc and Pokutta, Sebastian}, title = {A Tight Approximability Analysis of Boosting} }
Talks and posters
Conference and workshop talks
- Nov 2024
- A Combinatorial Comparison of Boosting and Repeated Boosting by Ingo Meise
Annual Meeting, SPP Theoretical Foundations of Deep Learning, Tutzing
Research seminar talks
- Sep 2024
- A Comparison of Simple and Repeated Weighted Majority Voting by Ingo Meise
IOL Research Seminar (IOL), Berlin