In our research, we bridge the gap between mathematical theory and machine learning practice. More specifically, we exploit newly discovered deep connections between fundamental results related to the study of large networks — an area to which Hungarian scientists have contributed tremendously — and the more applied domain of machine learning. Our ambition is, on one hand, to connect the country into the network of international research, and on the other hand, to facilitate machine learning applications in the industry.
We are investigating the theoretical foundations of stochastic machine learning methods, with a special emphasis on their confidence, for example data-driven, distribution-free uncertainty quantification.