Gergely Neu is an ICREA research professor at Universitat Pompeu Fabra, Barcelona, Spain. He has previously worked with the SequeL team of INRIA Lille, France and the RLAI group at the University of Alberta, Edmonton, Canada. He obtained his PhD degree in 2013 from the Budapest University of Technology and Economics, where his advisors were András György, Csaba Szepesvári and László Györfi. His main research interests are in machine learning theory, with a strong focus on sequential decision making problems. Dr. Neu was the recipient of a Google Faculty Research award in 2018, the Bosch Young AI Researcher Award in 2019, and an ERC Starting Grant in 2020.

My research is concerned with the mathematical analysis of machine learning algorithms and AI systems, particularly in the context of sequential-decision making where such systems are used to make predictions and take actions in a reactive environment. This work enables a better understanding of existing machine-learning tools and sets the groundwork for the development of new algorithms that are reliable by design. I am especially interested in the following topics:

-Reinforcement learning: design and analysis of large-scale RL algorithms, using tools from linear programming and convex analysis.

-Statistical learning theory: analysis of the generalization ability of machine learning algorithms, using tools from convex analysis and the theory of sequential prediction algorithms.

-Mathematical statistics: development of new statistical tools using connections with the theory of sequential prediction algorithms.