Florian Kalinke

Florian Kalinke is a Researcher at the Information Management Systems group under the IPD Böhm team at the Karlsruhe Institute of Technology (KIT). His work focuses on advanced machine learning methodologies for data streams, statistical testing, and kernel-based approaches.

• Research Interests: Machine Learning, Data Mining, Time Series Analysis, Statistical Learning, Artificial Intelligence, and Computer Science.
• Key Contributions: Development of novel techniques for partial-label learning with reject options, Nyström kernel approximations, online change detection using Maximum Mean Discrepancy, and multi-kernel outlier detection in streaming data.
• Collaborations: Works with researchers like Tobias Fuchs, Karsten Böhm, Zoltán Szabó, and others, leveraging theoretical and applied machine learning frameworks.
• Publications: Active in top venues like Transactions on Machine Learning Research, NeurIPS, AISTATS, and Discovery Science, with a focus on scalable and interpretable models.