Johannes Kirschner
Johannes Kirschner
Swiss Data Science Center, ETH Zurich
Verified email at - Homepage
Cited by
Cited by
Adaptive and safe Bayesian optimization in high dimensions via one-dimensional subspaces
J Kirschner, M Mutny, N Hiller, R Ischebeck, A Krause
International Conference on Machine Learning, 3429-3438, 2019
Information directed sampling and bandits with heteroscedastic noise
J Kirschner, A Krause
Conference On Learning Theory, 358-384, 2018
Information-directed exploration for deep reinforcement learning
N Nikolov, J Kirschner, F Berkenkamp, A Krause
arXiv preprint arXiv:1812.07544, 2018
Distributionally robust Bayesian optimization
J Kirschner, I Bogunovic, S Jegelka, A Krause
International Conference on Artificial Intelligence and Statistics, 2174-2184, 2020
Information directed sampling for linear partial monitoring
J Kirschner, T Lattimore, A Krause
Conference on Learning Theory, 2328-2369, 2020
Asymptotically optimal information-directed sampling
J Kirschner, T Lattimore, C Vernade, C Szepesvári
Conference on Learning Theory, 2777-2821, 2021
Stochastic bandits with context distributions
J Kirschner, A Krause
Advances in Neural Information Processing Systems, 14113-14122, 2019
Tuning particle accelerators with safety constraints using Bayesian optimization
J Kirschner, M Mutný, A Krause, J Coello de Portugal, N Hiller, ...
Physical Review Accelerators and Beams 25 (6), 062802, 2022
Bayesian optimisation for fast and safe parameter tuning of swissfel
J Kirschner, M Nonnenmacher, M Mutný, A Krause, N Hiller, R Ischebeck, ...
FEL2019, Proceedings of the 39th International Free-Electron Laser …, 2019
Efficient pure exploration for combinatorial bandits with semi-bandit feedback
M Jourdan, M Mutný, J Kirschner, A Krause
Algorithmic Learning Theory, 805-849, 2021
Bias-Robust Bayesian Optimization via Dueling Bandits
J Kirschner, A Krause
arXiv preprint arXiv:2105.11802, 2021
Experimental design for optimization of orthogonal projection pursuit models
M Mutny, J Kirschner, A Krause
Proceedings of the AAAI Conference on Artificial Intelligence 34 (06), 10235 …, 2020
Information-Directed Sampling-Frequentist Analysis and Applications
J Kirschner
ETH Zurich, 2021
Near-optimal policy identification in active reinforcement learning
X Li, V Mehta, J Kirschner, I Char, W Neiswanger, J Schneider, A Krause, ...
arXiv preprint arXiv:2212.09510, 2022
Linear partial monitoring for sequential decision making: Algorithms, regret bounds and applications
J Kirschner, T Lattimore, A Krause
The Journal of Machine Learning Research 24 (1), 16606-16650, 2023
Efficient planning in combinatorial action spaces with applications to cooperative multi-agent reinforcement learning
V Tkachuk, SA Bakhtiari, J Kirschner, M Jusup, I Bogunovic, C Szepesvári
International Conference on Artificial Intelligence and Statistics, 6342-6370, 2023
Regret minimization via saddle point optimization
J Kirschner, A Bakhtiari, K Chandak, V Tkachuk, C Szepesvári
Advances in Neural Information Processing Systems 36, 2024
Managing temporal resolution in continuous value estimation: A fundamental trade-off
ZV Zhang, J Kirschner, J Zhang, F Zanini, A Ayoub, M Dehghan, ...
Advances in Neural Information Processing Systems 36, 2024
Real-time railway (re-) scheduling without human-expert knowledge
F Corman, M Jusup, J Kirschner, T Birchler, S Curi, I Bogunovic, A Krause
22nd Swiss Transport Research Conference (STRC 2022), 2022
The system can't perform the operation now. Try again later.
Articles 1–19