Prof. Dr. Josif Grabocka
Automated Machine Learning is the primary focus of the Machine Learning Lab. In particular, the team is interested in developing cutting-edge methods for efficiently tuning the hyperparameters of Deep Learning models, including but not limited to optimizing the settings of Large Language Models, Generative Models, Reinforcement Learning policies, and neural networks for tabular datasets. We tackle the optimization of hyperparameters via meta- and transfer-learning approaches from prior evaluations and gray-box optimization strategies. In addition, we also focus on trustworthy Machine Learning, where we consider robustness, fairness, energy efficiency, and interpretability, as auxiliary optimization criteria for Deep Learning models.
Prof. Dr. Josif Grabocka
Professor of Machine Learning
Current Research Projects
ReScaLe: Responsible And Scalable Learning For Robots Assisting Humans,
Carl-Zeiss Stiftung, 2022 – 2028;
SFB „Small Data“,
DFG, 2023-2027;
Completed Research Projects
Industry Cooperation Grant: Automated AI, Eva Mayr-Stihl Stiftung, 2019-2022
Publications
List of publications of Prof. Dr. Josif Grabocka on Google Scholar
Team
You still have questions?
Then contact our Machine Learning Lab.