Sledovať
Tobias Sutter
Tobias Sutter
University of Konstanz
Overená e-mailová adresa na: uni-konstanz.de - Domovská stránka
Názov
Citované v
Citované v
Rok
Performance bounds for the scenario approach and an extension to a class of non-convex programs
PM Esfahani, T Sutter, J Lygeros
IEEE Transactions on Automatic Control 60 (1), 46-58, 2014
1712014
Efficient approximation of quantum channel capacities
D Sutter, T Sutter, PM Esfahani, R Renner
IEEE Transactions on Information Theory 62 (1), 578-598, 2015
512015
From infinite to finite programs: Explicit error bounds with applications to approximate dynamic programming
P Mohajerin Esfahani, T Sutter, D Kuhn, J Lygeros
SIAM journal on optimization 28 (3), 1968-1998, 2018
502018
A Pareto dominance principle for data-driven optimization
T Sutter, BPG Van Parys, D Kuhn
Operations Research 72 (5), 1976-1999, 2024
27*2024
A variational approach to path estimation and parameter inference of hidden diffusion processes
T Sutter, A Ganguly, H Koeppl
Journal of Machine Learning Research 17 (190), 1-37, 2016
232016
Efficient learning of a linear dynamical system with stability guarantees
W Jongeneel, T Sutter, D Kuhn
IEEE Transactions on Automatic Control 68 (5), 2790-2804, 2022
212022
On infinite linear programming and the moment approach to deterministic infinite horizon discounted optimal control problems
A Kamoutsi, T Sutter, PM Esfahani, J Lygeros
IEEE control systems letters 1 (1), 134-139, 2017
162017
Data-driven approximate dynamic programming: A linear programming approach
T Sutter, A Kamoutsi, PM Esfahani, J Lygeros
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 5174-5179, 2017
152017
Approximation of constrained average cost Markov control processes
T Sutter, PM Esfahani, J Lygeros
53rd IEEE Conference on Decision and Control, 6597-6602, 2014
152014
Robust generalization despite distribution shift via minimum discriminating information
T Sutter, A Krause, D Kuhn
Advances in Neural Information Processing Systems 34, 29754-29767, 2021
122021
Distributionally robust optimization with Markovian data
M Li, T Sutter, D Kuhn
International Conference on Machine Learning, 6493-6503, 2021
122021
Generalized maximum entropy estimation
T Sutter, D Sutter, PM Esfahani, J Lygeros
Journal of Machine Learning Research 20 (138), 1-29, 2019
122019
Policy gradient algorithms for robust mdps with non-rectangular uncertainty sets
M Li, D Kuhn, T Sutter
arXiv preprint arXiv:2305.19004, 2023
112023
End-to-end learning for stochastic optimization: A bayesian perspective
Y Rychener, D Kuhn, T Sutter
International Conference on Machine Learning, 29455-29472, 2023
102023
ISAAC Newton: Input-based Approximate Curvature for Newton's Method
F Petersen, T Sutter, C Borgelt, D Huh, H Kuehne, Y Sun, O Deussen
arXiv preprint arXiv:2305.00604, 2023
92023
Topological linear system identification via moderate deviations theory
W Jongeneel, T Sutter, D Kuhn
IEEE Control Systems Letters 6, 307-312, 2021
82021
Efficient approximation of discrete memoryless channel capacities
D Sutter, PM Esfahani, T Sutter, J Lygeros
2014 IEEE International Symposium on Information Theory, 2904-2908, 2014
82014
Quantum speedups for convex dynamic programming
D Sutter, G Nannicini, T Sutter, S Woerner
arXiv preprint arXiv:2011.11654, 2020
72020
Capacity approximation of memoryless channels with countable output alphabets
T Sutter, PM Esfahani, D Sutter, J Lygeros
2014 IEEE International Symposium on Information Theory, 2909-2913, 2014
52014
A general framework for optimal Data-Driven optimization. October 2020
T Sutter, BPG Van Parys, D Kuhn
URL http://arxiv. org/abs/2010 6606 (6.5), 6.6, 2010
52010
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–20