Preprints
R. Salac, M.Kupper and T. Sutter, Asymptotic Optimality in Data-driven Decision Making [arXiv]
A. Wolter, T. Sutter, A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance [arXiv]
M. Li, D. Kuhn and T. Sutter, Towards Optimal Offline Reinforcement Learning [arXiv]
A. Ganguly and T. Sutter, Optimal learning via Moderate Deviations Theory [arXiv]
Journals
M. Li, D. Kuhn and T. Sutter, Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets, accepted at SIAM Journal on Optimization (SIOPT), 2026
N. Schmid, M. Fochesato, S. Li, T. Sutter and J. Lygeros, Computing Optimal Joint Chance Constrained Control Policies, accepted at IEEE Transactions on Automatic Control, 2025 [DOI, arXiv]
T. Sutter, B. van Parys and D. Kuhn, A Pareto Dominance Principle for Data-Driven Optimization, Operations Research, 2024, vol. 72, no. 5, pp. 1976-1999 [DOI, arXiv]
N. Schmid, M. Fochesato, T. Sutter and J. Lygeros, Joint Chance Constrained Optimal Control via Linear Programming, IEEE Control Systems Letters, vol. 8, pp. 736-74, 2024 [DOI, arXiv]
W. Jongeneel, T. Sutter, and D. Kuhn, Efficient Learning of a Linear Dynamical System with Stability Guarantees, IEEE Transactions on Automatic Control, 2023, vol.68, pp.2790-2804 [DOI, arXiv]
W. Jongeneel, T. Sutter, and D. Kuhn, Topological Linear System Identification via Moderate Deviations Theory, IEEE Control Systems Letters, 2021, vol. 6, pp. 307-312 [DOI, arXiv]
T. Sutter, D. Sutter, P. Mohajerin Esfahani and J. Lygeros, Generalized maximum entropy estimation, Journal on Machine Learning Research, vol. 20, 2019, [DOI, arXiv]
P. Mohajerin Esfahani, T. Sutter, D. Kuhn and J. Lygeros, From Infinite to Finite Programs: Explicit Error Bounds with an Application to Approximate Dynamic Programming, SIAM Journal on Optimization, 2018, vol. 28, no. 3, pp. 1968-1998, [DOI, arXiv]
T. Sutter, D. Sutter and J. Lygeros, Capacity of Random Channels with Large Alphabets, Advances in Mathematics of Communications, 2017, vol. 11, no. 4, pp. 813 - 835, [DOI, arXiv]
A. Kamoutsi, T. Sutter, P. Mohajerin Esfahani and J. Lygeros, On Infinite Linear Programming and the Moment Approach to Deterministic Infinite Horizon Discounted Optimal Control Problems, IEEE Control Systems Letters, vol. 1, no. 1, 2017, [DOI, arXiv]
T. Sutter, A. Ganguly, and H. Koeppl, A Variational Approach to Path Estimation and Parameter Inference of Hidden Diffusion Processes, Journal on Machine Learning Research, vol. 17, 2016, [DOI, arXiv]
D. Sutter, T. Sutter, P. Mohajerin Esfahani and R. Renner, Efficient Approximation of Quantum Channel Capacities, IEEE Transactions on Information Theory, vol. 62, no. 1, 2016, [DOI, arXiv]
T. Sutter and J. Lygeros, Signals and Systems II: A Flipped Classroom Experiment for Undergraduate Control Education, ASME Control and Dynamics Magazine, 2016, [DOI, Paper]
T. Sutter, D. Sutter, P. Mohajerin Esfahani and J. Lygeros, Efficient Approximation of Channel Capacities, IEEE Transactions on Information Theory, vol. 61, no. 4, 2015, [DOI, arXiv]
P. Mohajerin Esfahani, T. Sutter, and J. Lygeros, Performance Bounds for the Scenario Approach and an Extension to a Class of Non-convex Programs, IEEE Transactions on Automatic Control, vol. 60, no. 1, 2015, [DOI, arXiv] ==> George S. Axelby Outstanding Paper Award 2016(picture)
T. Sutter, D. Chatterjee, F. Ramponi, and J. Lygeros, Isospectral flows on a class of finite-dimensional Jacobi matrices, Systems and Control Letters, vol. 62, no. 5, 2013, [DOI, arXiv]
Peer Reviewed Conferences
L. Pleiss, T. Sutter and M. Schiffer, Reliability-Adjusted Prioritized Experience Replay, International Conference on Learning Representations (ICLR), 2026, accepted [arXiv]
G. He, T. Sutter and L. Gonon, Distributional Adversarial Attacks and Training in Deep Hedging, Conference on Neural Information Processing Systems (NeurIPS), 2025 [arXiv, DOI]
D. Boetius, S. Leue, T. Sutter, Probabilistic Verification of Neural Networks using Branch and Bound, International Conference on Machine Learning (ICML), 2025 [DOI , arXiv]
A. Kamoutsi, P. Schmitt-Förster, T. Sutter, V. Cevher, J. Lygeros, Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces, Conference on Neural Information Processing Systems (NeurIPS), 2024 [DOI, arXiv]
F. Petersen, C. Borgelt, T. Sutter, H. Kuehne, O. Deussen, S. Ermon, Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms, Conference on Neural Information Processing Systems (NeurIPS), 2024 [DOI, arXiv]
P. Schmitt-Förster and T. Sutter, Regularized Q-learning through Robust Averaging, International Conference on Machine Learning (ICML), 2024, [DOI, arXiv]
U. Schlegel, D. Keim and T. Sutter, Finding the DeepDream for Time Series: Activation Maximization for Univariate Time Series, Workshop on Explainable AI for Time Series and Data Streams (TempXAI 2024), 2024, [Paper]
Y. Rychener, D. Kuhn and T. Sutter, End-to-End Learning for Stochastic Optimization: A Bayesian Perspective, International Conference on Machine Learning (ICML), 2023 [DOI], [arXiv]
D. Boetius, S. Leue and T. Sutter, A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks, International Conference on Machine Learning (ICML), 2023 [DOI], [arXiv]
F. Petersen, T. Sutter, C.Borgelt, D.Huh, H.Kuehne, Y.Sun, O.Deussen, ISAAC Newton: Input-based Approximate Curvature for Newton's Method, International Conference on Learning Representations (ICLR), 2023 [DOI], [video]
T. Sutter, A. Krause and D. Kuhn, Robust Generalization despite Distribution Shift via Minimum Discriminating Information, Conference on Neural Information Processing Systems (NeurIPS), 2021 [DOI, arXiv]
M. Li, T. Sutter and D. Kuhn, Distributionally Robust Optimization with Markovian Data, International Conference on Machine Learning (ICML), 2021, [DOI, arXiv]
T. Sutter, A. Kamoutsi, P. Mohajerin Esfahani and J. Lygeros, Data-driven approximate dynamic programming: A linear programming approach, IEEE Conference on Decision and Control (CDC), 2017, [DOI]
M. Thely, T. Sutter, P. Mohajerin Esfahani and J. Lygeros, Maximum Entropy Estimation via Gauss-LP Quadratures, IFAC World Congress, 2017, [DOI]
T. Sutter, P. Mohajerin Esfahani and J. Lygeros, Approximation of constrained average cost Markov control processes, IEEE Conference on Decision and Control (CDC), 2014, [DOI]
T. Sutter, D. Sutter, J. Lygeros, Asymptotic capacity of a random channel, 52nd Annual Allerton Conference on Communications, Control, and Computing, 2014, [DOI]
D. Sutter, T. Sutter, P. Esfahani, J. Lygeros, Efficient approximation of discrete memoryless channel capacities, IEEE International Symposium on Information Theory (ISIT), 2014, [DOI]
T. Sutter, D. Sutter, P. Esfahani, J. Lygeros, Capacity approximation of memoryless channels with countable output alphabets, IEEE International Symposium on Information Theory (ISIT), 2014, [DOI]
Doctoral / Master / Bachelor Theses
PhD thesis: Convex programming in optimal control and information theory, advisor John Lygeros, committee: Daniel Kuhn & Sean Meyn
Master thesis: Variational Inference for State Dependent Diffusion Processes, advisor Arnab Ganguly
Semester project: Isospectral Flows on a Class of Finite-Dimensional Jacobi Matrices, advisor John Lygeros & Debasish Chatterjee & Federico Ramponi
Bachelor thesis: A Dynamical Approach to Create Different Juggling Patterns Using Chaos, advisor Raffaello D'Andrea