Short-CV

Tobias Sutter is tenure-track-professor for Computer Science with focus on Machine Learning at the University of Konstanz since 2021. Since 2022 he is a member of the Centre for Human | Data | Society. He received his bachelor’s degree in 2007 on a thesis of Mechanical Engineering at the ETH Zürich (Switzerland), followed by the master’s degree in 2012. In 2017 he earned a PhD in Electrical Engineering (thesis: Convex programming in optimal control and information theory). After postdoctoral research positions at EPF Lausanne and ETH Zürich he is now Fellow of the Institute for Advanced Study at the University of Konstanz. He is Group leader at the Cluster of Excellence: Centre for the Advanced Study of Collective Behaviour and Program Committee of the Annual Learning for Dynamics & Control Conference (L4DC). His research is focused on Machine Learning, Stochastic Optimization and Control and Information Theory. Tobias Sutter has expert knowledge on data-driven decision making under uncertainty and information constraints (e.g., privacy), algorithmic fairness, especially fairness in Machine Learning, causal learning and decision making and uncertainty estimation and quantification.  

Research-related publications

• Wouter Jongeneel, Tobias Sutter, Daniel Kuhn. 2022. Efficient Learning of a Linear Dynamical System with Stability Guarantees. IEEE Transactions on Automatic Control. in print, doi: 10.1109/TAC.2022.3213770
• Tobias Sutter, Daniel Kuhn, and Andreas Krause. 2021. Robust generalization despite distribution shift via Minimum Discriminating Information, Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 29754-29767.
• Mengmeng Li, Tobias Sutter, and Daniel Kuhn. 2021. Distributionally robust optimization with Markovian data. Proceedings of the 38th International Conference on Machine Learning (ICML), PMLR. 139:6493-6503.
• Tobias Sutter, David Sutter, Peyman Mohajerin Esfahani, and John Lygeros. 2019. Generalized maximum entropy estimation. Journal on Machine Learning Research. 20(138):1--29.
• Peyman Esfahani Mohajerin, Tobias Sutter, Daniel Kuhn, and John Lygeros. 2018. From infinite to finite programs: Explicit error bounds with an application to approximate dynamic programming. SIAM Journal on Optimization. 28(3):1968-1998.
• Angeliki Kamoutsi, Tobias Sutter, Peyman Mohajerin Esfahani, and John Lygeros. 2017. On infinite linear programming and the moment approach to deterministic infinite horizon discounted optimal control problems. IEEE Control Systems Letters, 1(1):134-139. DOI: 10.1109/LCSYS.2017.2710234.
• David Sutter, Tobias Sutter, Peyman Mohajerin Esfahani, and Renato Renner. 2016. Efficient approximation of quantum channel capacities. IEEE Transactions on Information Theory. 62(1):578--598. DOI: 10.1109/TIT.2015.2503755.
• Tobias Sutter, Arnab Ganguly, and Heinz Koeppl. 2016. Path estimation and variational inference for hidden diffusion processes. Journal on Machine Learning Research. 17(190):1--37.
• Tobias Sutter, David Sutter, Peyman Mohajerin Esfahani, and John Lygeros. 2015. Efficient approximation of channel capacities. IEEE Transactions on Information Theory. 61(4):1649-1666. DOI: 10.1109/TIT.2015.2401002.
• Peyman Esfahani Mohajerin, Tobias Sutter, and John Lygeros. 2015. Performance bounds for the scenario approach and an extension to a class of non-convex programs. IEEE Transactions on Automatic Control. 60(1):46-58. DOI: 10.1109/TAC.2014.2330702.
• Tobias Sutter, Bart van Parys, Daniel Kuhn, A General Framework for Optimal Data-Driven Optimization, under review (2^nd round) in Operations Research, 2020, available at arXiv:2010.06606.