I am interested in quantifying model uncertainty in dynamical systems. This is useful for generating reliable predictions and building robust control systems. By sampling a variety of scenarios from our model - not just those contained in the data - we can expose our controller to a wider variety of settings, leading to better performance in new ones. I am also interested in the problem of inference from noisy or incomplete data and in variational inference methods.
In Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 2931-2940, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (inproceedings)
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems