Balázs Csanád Csáji is a Senior Researcher at SZTAKI (Institute for Computer Science and Control, Budapest, Hungary). He defended his Ph.D. in Computer Science (2008) at the Eötvös Loránd University (ELTE), Budapest, Hungary. Previously, he received Master’s degrees in Computer Science combined with Mathematics (2001) as well as in Philosophy (2006), also from ELTE. During his studies he spent semesters and internships at the Eindhoven University of Technology, Netherlands (2001), British Telecom, UK (2002), and Johannes Kepler University, Austria (2003).
Dr. Csáji was a Postdoctoral Researcher at the Université catholique de Louvain, Belgium (2008-2009), and a Research Fellow at the University of Melbourne, Australia (2009-2012). He has received a number of awards for his achievements including the Discovery Early Career Researcher Award (DECRA) of the Australian Research Council (ARC) and the Béla Gyires Prize of the Section of Mathematics, Hungarian Academy of Sciences.
His main research interests include stochastic models and statistical problems in machine learning and system identification as well as their engineering and industrial applications.
Csáji, B.Cs.; Kis, K.B.: Distribution-free uncertainty quantification for kernel methods by gradient perturbations, Machine Learning, Vol. 108, No. 8-9, 2019, pp. 1677–1699.
Weyer, E.; Campi, M.C.; Csáji, B.Cs.: Asymptotic properties of SPS confidence regions, Automatica, Vol. 82, August 2017, pp. 287-294.
Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Sign-Perturbed Sums: A New System Identification Approach for Constructing Exact Non-Asymptotic Confidence Regions in Linear Regression Models, IEEE Transactions on Signal Processing, IEEE Press, Vol. 69, 2015, pp. 169–181.
Csáji, B. Cs.; Monostori, L.: Adaptive Stochastic Resource Control: A Machine Learning Approach, Journal of Artificial Intelligence Research (JAIR), AAAI Press, Vol. 32, 2008, pp. 453–486.
Csáji, B. Cs.; Monostori, L.: Value Function Based Reinforcement Learning in Changing Markovian Environments, Journal of Machine Learning Research (JMLR), MIT Press and Microtome Publishing, Vol. 9, 2008, pp. 1679–1709.
