Tobias Sutter

Curriculum vitae [pdf]

Open positions:

News

Two papers at NeurIPS 2024
- Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces [arXiv]
- Fishers and Hessians of Continuous Relaxations
New preprint [arXiv] on Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
New preprint [arXiv] on Probabilistic Verification of Neural Networks using Branch and Bound
New paper [arXiv] on Regularized Q-learning through Robust Averaging (accepted at ICML 2024)
New paper [arXiv] Joint Chance Constrained Optimal Control via Linear Programming, accepted to IEEE Control Systems Letters
New seminar series on Connecting Statistical Logic, Dynamical Systems and Optimization
New preprint [arXiv] on Computing Optimal Joint Chance Constrained Control Policies
Organization of workshop: Moments and Polynomials: Applications and Theory
Speaker at Workshop: Large Scale Learning and Control
New preprint [arXiv] on optimal learning via Moderate Deviations Theory
New preprint [arXiv] on Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
Two papers at ICML 2023
- End-to-End Learning for Stochastic Optimization: A Bayesian Perspective [arXiv]
- A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks [arXiv]

Teaching (see also Lectures)

Publications and Preprints

PhD Supervision at University of Konstanz

Research Interests

Control theory: stochastic control, approximate dynamic programming
Machine learning: reinforcement learning, data-driven decision making, distributional shift adaptation
Stochastic programming: distributionally robust optimization
Convex optimization: complexity of optimal first-order methods, smoothing techniques
Information theory: channel capacity approximation, quantum information theory

Awards